ICLR 2025 Agent-Related Papers

This repository contains a curated list of agent-related papers from ICLR 2025, sorted by their average ratings.

Papers

1. Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models (Rating: 8.00)
2. Spider 2.0: Can Language Models Resolve Real-World Enterprise Text-to-SQL Workflows? (Rating: 8.00)
3. Do as We Do, Not as You Think: the Conformity of Large Language Models (Rating: 7.50)
4. Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence (Rating: 7.00)
5. Online Neuro-Symbolic Predicate Invention for High-Level Planning (Rating: 7.00)
6. MLE-Bench: Evaluating Machine Learning Agents on Machine Learning Engineering (Rating: 7.00)
7. Monte Carlo Planning with Large Language Model for Text-Based Games (Rating: 7.00)
8. Self-Evolving Multi-Agent Networks for Software Development (Rating: 7.00)
9. Scaling Test-Time Compute Optimally Can be More Effective than Scaling LLM Parameters (Rating: 6.75)
10. Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice (Rating: 6.75)
11. PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks (Rating: 6.75)
12. OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning (Rating: 6.75)
13. AFlow: Automating Agentic Workflow Generation (Rating: 6.75)
14. Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents (Rating: 6.75)
15. EmbodiedSAM: Online Segment Any 3D Thing in Real Time (Rating: 6.67)
16. Strong Preferences Affect the Robustness of Value Alignment (Rating: 6.50)
17. Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning (Rating: 6.50)
18. Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel (Rating: 6.50)
19. Learning Closed-Loop Concept-Guided Policies from Unlabeled Demonstrations (Rating: 6.50)
20. VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks (Rating: 6.50)
21. Building Math Agents with Multi-Turn Iterative Preference Learning (Rating: 6.50)
22. An Investigation of Conformal Isometry Hypothesis for Grid Cells (Rating: 6.50)
23. Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage (Rating: 6.50)
24. VisualAgentBench: Towards Large Multimodal Models as Visual Agents (Rating: 6.50)
25. MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs (Rating: 6.40)
26. Robust Function-Calling for On-Device Language Model via Function Masking (Rating: 6.40)
27. Interleaved Scene Graph for Interleaved Text-and-Image Generation Assessment (Rating: 6.40)
28. DSBench: How Far Are Data Science Agents from Becoming Data Science Experts? (Rating: 6.40)
29. Active Task Disambiguation with LLMs (Rating: 6.33)
30. AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs (Rating: 6.33)
31. SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION (Rating: 6.33)
32. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code (Rating: 6.25)
33. An Intelligent Agentic System for Complex Image Restoration Problems (Rating: 6.25)
34. Discriminator-Guided Embodied Planning for LLM Agent (Rating: 6.25)
35. Evidence from the Synthetic Laboratory: Language Models as Auction Participants (Rating: 6.25)
36. Harnessing Webpage UIs for Text-Rich Visual Understanding (Rating: 6.25)
37. OSDA Agent: Leveraging Large Language Models for De Novo Design of Organic Structure Directing Agents (Rating: 6.25)
38. Learn-by-interact: A Data-Centric Framework For Self-Adaptive Agents in Realistic Environments (Rating: 6.25)
39. Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models (Rating: 6.25)
40. DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory (Rating: 6.25)
41. Can Multimodal Foundation Models Perform Visual Temporal Reasoning? (Rating: 6.25)
42. Visual Agents as Fast and Slow Thinkers (Rating: 6.25)
43. DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback (Rating: 6.25)
44. Generalized Principal-Agent Problem with a Learning Agent (Rating: 6.25)
45. RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code (Rating: 6.25)
46. AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents (Rating: 6.25)
47. {$\tau$}-bench: A Benchmark for \underline{T}ool-\underline{A}gent-\underline{U}ser Interaction in Real-World Domains (Rating: 6.25)
48. Counterfactual Concept Bottleneck Models (Rating: 6.25)
49. OS-ATLAS: Foundation Action Model for Generalist GUI Agents (Rating: 6.25)
50. MaestroMotif: Skill Design from Artificial Intelligence Feedback (Rating: 6.25)
51. DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agent (Rating: 6.25)
52. Lightweight Neural App Control (Rating: 6.25)
53. Language Agents Meet Causality -- Bridging LLMs and Causal World Models (Rating: 6.25)
54. Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction (Rating: 6.25)
55. On Bits and Bandits: Quantifying the Regret-Information Trade-off (Rating: 6.25)
56. DataGen: Unified Synthetic Dataset Generation via Large Language Models (Rating: 6.25)
57. MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark (Rating: 6.25)
58. ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer (Rating: 6.20)
59. Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs (Rating: 6.20)
60. Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology (Rating: 6.00)
61. OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures? (Rating: 6.00)
62. Multimodal Situational Safety (Rating: 6.00)
63. EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation (Rating: 6.00)
64. Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency (Rating: 6.00)
65. Autonomous agents from automatic reward modeling and planning (Rating: 6.00)
66. AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents (Rating: 6.00)
67. Training Language Models to Critique with Multi-Agent Feedback (Rating: 6.00)
68. ImProver: Agent-Based Automated Proof Optimization (Rating: 6.00)
69. PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration (Rating: 6.00)
70. Mixture-of-Agents Enhances Large Language Model Capabilities (Rating: 6.00)
71. Deep Learning Algorithms for Mean Field Optimal Stopping in Finite Space and Discrete Time (Rating: 6.00)
72. Agent S: An Open Agentic Framework that Uses Computers Like a Human (Rating: 6.00)
73. ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery (Rating: 6.00)
74. Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface (Rating: 6.00)
75. Aligned LLMs Are Not Aligned Browser Agents (Rating: 6.00)
76. COMBO: Compositional World Models for Embodied Multi-Agent Cooperation (Rating: 6.00)
77. MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding (Rating: 6.00)
78. Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents (Rating: 6.00)
79. OccProphet: Pushing the Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with an Observer-Forecaster-Refiner Framework (Rating: 6.00)
80. Neural Interactive Proofs (Rating: 6.00)
81. GOAL: A Generalist Combinatorial Optimization Agent Learning (Rating: 6.00)
82. Advantage Alignment Algorithms (Rating: 6.00)
83. Scaling Large Language Model-based Multi-Agent Collaboration (Rating: 6.00)
84. Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training (Rating: 6.00)
85. LoRA-Gen: Specializing Language Model via Online LoRA Generation (Rating: 6.00)
86. MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents (Rating: 6.00)
87. Do LLMs ``know'' internally when they follow instructions? (Rating: 6.00)
88. AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses (Rating: 5.83)
89. EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE (Rating: 5.80)
90. POIL: Preference Optimization for Imitation Learning (Rating: 5.80)
91. MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents (Rating: 5.75)
92. Discrete Latent Plans via Semantic Skill Abstractions (Rating: 5.75)
93. LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture (Rating: 5.75)
94. Graph Neural Networks Gone Hogwild (Rating: 5.75)
95. Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers (Rating: 5.75)
96. CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL (Rating: 5.75)
97. Audio Large Language Models Can Be Descriptive Speech Quality Evaluators (Rating: 5.75)
98. Tool-Planner: Task Planning with Clusters across Multiple Tools (Rating: 5.75)
99. WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models (Rating: 5.75)
100. Agent Skill Acquisition for Large Language Models via CycleQD (Rating: 5.75)
101. AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws (Rating: 5.75)
102. AgentHarm: Benchmarking Robustness of LLM Agents on Harmful Tasks (Rating: 5.75)
103. MindSearch: Mimicking Human Minds Elicits Deep AI Searcher (Rating: 5.75)
104. Grounding Multimodal Large Language Model in GUI World (Rating: 5.75)
105. Knowledge Graph Based Agent For Complex, Knowledge-Intensive QA in Medicine (Rating: 5.75)
106. InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation (Rating: 5.75)
107. LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs (Rating: 5.75)
108. OpenHands: An Open Platform for AI Software Developers as Generalist Agents (Rating: 5.75)
109. RL, but don't do anything I wouldn't do (Rating: 5.75)
110. SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Prediction (Rating: 5.75)
111. Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs (Rating: 5.75)
112. Benchmarking and Enhancing Large Language Models for Biological Pathway Reasoning (Rating: 5.75)
113. Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent (Rating: 5.75)
114. HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions (Rating: 5.75)
115. Integrating Expertise of Software Engineering Agents (Rating: 5.75)
116. Language Guided Skill Discovery (Rating: 5.75)
117. Collab: Controlled Decoding using Mixture of Agents for LLM Alignment (Rating: 5.75)
118. AgentQuest: Benchmarking LLM and VLM Agents on Long-Horizon Interactive Tasks (Rating: 5.75)
119. NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks in Open Domains (Rating: 5.75)
120. Neural Exploratory Landscape Analysis (Rating: 5.75)
121. CityNav: Language-Goal Aerial Navigation Dataset Using Geographic Information (Rating: 5.75)
122. Moral Alignment for LLM Agents (Rating: 5.67)
123. Robotouille: An Asynchronous Planning Benchmark for LLM Agents (Rating: 5.67)
124. CtD: Composition through Decomposition in Emergent Communication (Rating: 5.67)
125. Commit0: Library Generation from Scratch (Rating: 5.67)
126. MetaDesigner: Advancing Artistic Typography through AI-Driven, User-Centric, and Multilingual WordArt Synthesis (Rating: 5.67)
127. Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making (Rating: 5.67)
128. When Prompt Engineering Meets Software Engineering: CNL-P as Natural and Robust "APIs'' for Human-AI Interaction (Rating: 5.67)
129. Steering Large Language Models between Code Execution and Textual Reasoning (Rating: 5.67)
130. Agents' Room: Narrative Generation through Multi-step Collaboration (Rating: 5.67)
131. VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning (Rating: 5.60)
132. Benchmarking Agentic Workflow Generation (Rating: 5.60)
133. Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner (Rating: 5.60)
134. Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents (Rating: 5.60)
135. Scattered Forest Search: Smarter Code Space Exploration with LLMs (Rating: 5.60)
136. EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents (Rating: 5.50)
137. GUI-World: A GUI-oriented Dataset for Multimodal LLM-based Agents (Rating: 5.50)
138. CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation (Rating: 5.50)
139. When LLMs Play the Telephone Game: Cumulative Changes and Attractors in Iterated Cultural Transmissions (Rating: 5.50)
140. Can Textual Gradient Work in Federated Learning? (Rating: 5.50)
141. RLSF: Reinforcement Learning via Symbolic Feedback (Rating: 5.50)
142. Balancing Act: Diversity and Consistency in Large Language Model Ensembles (Rating: 5.50)
143. Language Model Non-Myopic Generation for Reasoning and Planning (Rating: 5.50)
144. Do LLMs estimate uncertainty well in instruction-following? (Rating: 5.50)
145. MIRAI: Evaluating LLM Agents for International Event Forecasting (Rating: 5.50)
146. DCA-Bench: A Benchmark for Dataset Curation Agents (Rating: 5.50)
147. ToolACE: Enhancing Function Calling with Accuracy, Complexity, and Diversity (Rating: 5.50)
148. Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function Approximation (Rating: 5.50)
149. FinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning (Rating: 5.50)
150. SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models (Rating: 5.50)
151. ML-Bench: Evaluating Large Language Models for Code Generation in Repository-Level Machine Learning Tasks (Rating: 5.50)
152. An Information-Theoretic Analysis of Thompson Sampling for Logistic Bandits (Rating: 5.50)
153. Mr.Steve: Instruction-Following Agents in Minecraft with What-Where-When Memory (Rating: 5.50)
154. Compositional Hardness of Code in Large Language Models - A Probabilistic Perspective (Rating: 5.50)
155. PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding (Rating: 5.50)
156. Meta-Referential Games to Learn Compositional Learning Behaviours (Rating: 5.50)
157. JudgeBench: A Benchmark for Evaluating LLM-Based Judges (Rating: 5.50)
158. Multi-Agent Collaborative Data Selection for Efficient Language Model Pretraining (Rating: 5.50)
159. Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation (Rating: 5.50)
160. AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments (Rating: 5.50)
161. LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models (Rating: 5.50)
162. Adaptive In-conversation Team Building for Language Model Agents (Rating: 5.50)
163. Eligibility Traces for Confounding Robust Off-Policy Evaluation: A Causal Approach (Rating: 5.50)
164. Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance (Rating: 5.50)
165. Modeling dynamic social vision highlights gaps between deep learning and humans (Rating: 5.50)
166. EmpathyRobot: A Dataset and Benchmark for Empathetic Task Planning of Robotic Agent (Rating: 5.50)
167. JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework (Rating: 5.50)
168. Tree Search for Language Model Agents (Rating: 5.50)
169. MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model (Rating: 5.50)
170. Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems (Rating: 5.50)
171. Do LLM Agents Have Regret? A Case Study in Online Learning and Games (Rating: 5.50)
172. Generative World Explorer (Rating: 5.50)
173. KnowTrace: Explicit Knowledge Tracing for Structured Retrieval-Augmented Generation (Rating: 5.50)
174. Automated Red Teaming with GOAT: the Generative Offensive Agent Tester (Rating: 5.40)
175. RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards (Rating: 5.40)
176. MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct (Rating: 5.40)
177. General Scene Adaptation for Vision-and-Language Navigation (Rating: 5.40)
178. Empowering LLM Agents with Zero-Shot Optimal Decision-Making through Q-learning (Rating: 5.40)
179. DenseGrounding: Improving Dense Language-Vision Semantics for Ego-centric 3D Visual Grounding (Rating: 5.40)
180. Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale (Rating: 5.40)
181. Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning (Rating: 5.40)
182. Human Simulacra: Benchmarking the Personification of Large Language Models (Rating: 5.40)
183. On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking Functions (Rating: 5.33)
184. DoF: A Diffusion Factorization Framework for Offline Multi-Agent Decision Making (Rating: 5.33)
185. The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind (Rating: 5.33)
186. Agent-as-a-Judge: Evaluating Agents with Agents (Rating: 5.33)
187. Evolving Alignment via Asymmetric Self-Play (Rating: 5.33)
188. Grounding Robot Policies with Visuomotor Language Guidance (Rating: 5.33)
189. BraiNav: Incorporating Human Brain Activity to Enhance Robustness in Embodied Visual Navigation (Rating: 5.33)
190. Multiagent Finetuning of Language Models (Rating: 5.33)
191. What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices (Rating: 5.33)
192. Benchmarking Intelligent LLM Agents for Conversational Data Analysis (Rating: 5.33)
193. ADAM: An Embodied Causal Agent in Open-World Environments (Rating: 5.25)
194. Competing Large Language Models in Multi-Agent Gaming Environments (Rating: 5.25)
195. Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planning (Rating: 5.25)
196. Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models (Rating: 5.25)
197. AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML (Rating: 5.25)
198. GIVE: Structured Reasoning with Knowledge Graph Inspired Veracity Extrapolation (Rating: 5.25)
199. GuardAgent: Safeguard LLM Agent by a Guard Agent via Knowledge-Enabled Reasoning (Rating: 5.25)
200. Auction-Based Regulation for Artificial Intelligence (Rating: 5.25)
201. ToolBridge: An Open-Source Dataset to Equip LLMs with External Tool Capabilities (Rating: 5.25)
202. SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents (Rating: 5.25)
203. ACC-Debate: An Actor-Critic Approach to Multi-Agent Debate (Rating: 5.25)
204. Prompt Injection Benchmark for Foundation Model Integrated Systems (Rating: 5.25)
205. Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention (Rating: 5.25)
206. Monty Hall and Optimized Conformal Prediction to Improve Decision-Making with LLMs (Rating: 5.25)
207. Fourier Head: Helping Large Language Models Learn Complex Probability Distributions (Rating: 5.25)
208. Can External Validation Tools Improve Annotation Quality for LLM-as-a-Judge? (Rating: 5.25)
209. ThinkBot: Embodied Instruction Following with Thought Chain Reasoning (Rating: 5.25)
210. Agent-to-Sim: Learning Interactive Behavior Model from Casual Longitudinal Videos (Rating: 5.25)
211. MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization (Rating: 5.25)
212. Communicating Activations Between Language Model Agents (Rating: 5.25)
213. AgentGym: Evaluating and Evolving Large Language Model-based Agents across Diverse Envronments (Rating: 5.25)
214. How to Correctly Do Semantic Backpropagation on Language-based Agentic Systems (Rating: 5.25)
215. Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents (Rating: 5.25)
216. Efficiently Scanning and Resampling Spatio-Temporal Tasks with Irregular Observations (Rating: 5.25)
217. Adapting Communicating MLLMs on the Fly in Referring Expression Tasks (Rating: 5.25)
218. Towards Efficient and Scalable Multi-agent Reasoning via Bayesian Nash Equilibrium (Rating: 5.25)
219. Video Action Differencing (Rating: 5.25)
220. A Contextual Online Learning Theory of Brokerage (Rating: 5.25)
221. $\textit{RwR}$: A Reason-while-Retrieve framework for Reasoning on Scene Graphs with LLMs (Rating: 5.25)
222. Private Mechanism Design via Quantile Estimation (Rating: 5.25)
223. MVGS: Multi-view-regulated Gaussian Splatting for Novel View Synthesis (Rating: 5.25)
224. From Commands to Prompts: LLM-based Semantic File System (Rating: 5.25)
225. ToolGen: Unified Tool Retrieval and Calling via Generation (Rating: 5.25)
226. SpiritSight Agent: Advanced GUI Agent with One Look (Rating: 5.25)
227. Efficient Active Imitation Learning with Random Network Distillation (Rating: 5.25)
228. DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity (Rating: 5.25)
229. The Impact of Element Ordering on LM Agent Performance (Rating: 5.25)
230. Coding Reliable LLM-based Integrated Task and Knowledge Agents with GenieWorksheets (Rating: 5.20)
231. Tell Me What You Don't Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing (Rating: 5.20)
232. Federated Coordination: Private and Distributed Strategy Alignment (Rating: 5.20)
233. Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems (Rating: 5.20)
234. BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments (Rating: 5.20)
235. HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale (Rating: 5.17)
236. AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials (Rating: 5.00)
237. 3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination (Rating: 5.00)
238. ChemAgent: Self-updating Memories in Large Language Models Improves Chemical Reasoning (Rating: 5.00)
239. Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search (Rating: 5.00)
240. Zero-Shot Task-Level Adaptation via Coarse-to-Fine Policy Refinement and Holistic-Local Contrastive Representations (Rating: 5.00)
241. Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System (Rating: 5.00)
242. REvolve: Reward Evolution with Large Language Models using Human Feedback (Rating: 5.00)
243. Neuralized Markov Random Field for Interaction-Aware Stochastic Human Trajectory Prediction (Rating: 5.00)
244. Breaking Mental Set to Improve Reasoning through Diverse Multi-Agent Debate (Rating: 5.00)
245. BRIDGE: Bootstrapping Text to Guide Time-Series Generation via Multi-Agent Iterative Optimisation and Diffusion Modelling (Rating: 5.00)
246. Re-Aligning Language to Visual Objects with an Agentic Workflow (Rating: 5.00)
247. Can VLMs Play Action Role-Playing Games? Take Black Myth Wukong as a Study Case (Rating: 5.00)
248. Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems (Rating: 5.00)
249. On the Diversity of Synthetic Data and its Impact on Training Large Language Models (Rating: 5.00)
250. Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback (Rating: 5.00)
251. IGOR: Image-GOal Representations are the Atomic Building Blocks for Next-Level Generalization in Embodied AI (Rating: 5.00)
252. Mora: Enabling Generalist Video Generation via A Multi-Agent Framework (Rating: 5.00)
253. Rational Decision-Making Agent with Learning Internal Utility Judgment (Rating: 5.00)
254. Efficacy of Language Model Self-Play in Non-Zero-Sum Games (Rating: 5.00)
255. STEER-ME: Assessing the Microeconomic Reasoning of Large Language Models (Rating: 5.00)
256. AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions (Rating: 5.00)
257. Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models (Rating: 5.00)
258. Riemannian Manifold Learning for Stackelberg Games with Neural Flow Representations (Rating: 5.00)
259. Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View (Rating: 5.00)
260. AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMs (Rating: 5.00)
261. OmniParser for Pure Vision Based GUI Agent (Rating: 5.00)
262. Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation (Rating: 5.00)
263. Triples as the Key: Structuring Makes Decomposition and Verification Easier in LLM-based TableQA (Rating: 5.00)
264. Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistants (Rating: 5.00)
265. Towards Full Delegation: Designing Ideal Agentic Behaviors for Travel Planning (Rating: 5.00)
266. Sample Efficient Alignment for LLMs (Rating: 5.00)
267. Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling (Rating: 5.00)
268. ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL (Rating: 5.00)
269. Improving Large Language Model based Multi-Agent Framework through Dynamic Workflow Updating (Rating: 5.00)
270. Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems (Rating: 5.00)
271. CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing (Rating: 5.00)
272. Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision Processes (Rating: 5.00)
273. ChinaTravel: A Real-World Benchmark for Language Agents in Chinese Travel Planning (Rating: 5.00)
274. OptiBench: Benchmarking Large Language Models in Optimization Modeling with Equivalence-Detection Evaluation (Rating: 5.00)
275. DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace Editing (Rating: 5.00)
276. Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration (Rating: 5.00)
277. Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions (Rating: 5.00)
278. WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning (Rating: 5.00)
279. InvestAlign: Align LLMs with Investor Decision-Making under Herd Behavior (Rating: 5.00)
280. Informing Reinforcement Learning Agents by Grounding Language to Markov Decision Processes (Rating: 5.00)
281. Understanding Prejudice and Fidelity of Diverge-to-Converge Multi-Agent Systems (Rating: 5.00)
282. Who Should Join the Decision-Making Table? Targeted Expert Selection for Enhanced Human-AI Collaboration (Rating: 4.83)
283. Digi-Q: Transforming VLMs to Device-Control Agents via Value-Based Offline RL (Rating: 4.80)
284. MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning (Rating: 4.80)
285. On the Resilience of Multi-Agent Systems with Malicious Agents (Rating: 4.80)
286. Haland: Human-AI Coordination via Policy Generation from Language-guided Diffusion (Rating: 4.80)
287. AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems (Rating: 4.80)
288. Knapsack Schema Linking Agent for LLM-Based Text-to-SQL Generation (Rating: 4.80)
289. Stochastic Matching Bandits under Preference Feedback (Rating: 4.80)
290. How language models extrapolate outside the training data: A Case study in Textualized Gridworld (Rating: 4.80)
291. Empowering Users in Digital Privacy Management through Interactive LLM-Based Agents (Rating: 4.80)
292. Deep Exploration with PAC-Bayes (Rating: 4.75)
293. On the Modeling Capabilities of Large Language Models for Sequential Decision Making (Rating: 4.75)
294. War and Peace (WarAgent): LLM-based Multi-Agent Simulation of World Wars (Rating: 4.75)
295. Task-oriented Sequential Grounding in 3D Scenes (Rating: 4.75)
296. BioKGBench: A Knowledge Graph Checking Benchmark of AI Agent for Biomedical Science (Rating: 4.75)
297. 3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Referred Object Grounding (Rating: 4.75)
298. Automated Design of Agentic Systems (Rating: 4.75)
299. Language-conditioned Multi-Style Policies with Reinforcement Learning (Rating: 4.75)
300. LLF-Bench: A Benchmark for Interactive Learning from Language Feedback (Rating: 4.75)
301. MAD-Sherlock: Multi-Agent Debates for Out-of-Context Misinformation Detection (Rating: 4.75)
302. Research Town: Simulator of Research Community (Rating: 4.75)
303. ToM-agent: Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection (Rating: 4.75)
304. COMMA: A Communicative Multimodal Multi-Agent Benchmark (Rating: 4.75)
305. SWE-bench Multimodal: Do Autonomous Programming Systems Generalize to New Software Domains? (Rating: 4.75)
306. Dissecting Adversarial Robustness of Multimodal LM Agents (Rating: 4.75)
307. ESDMotion: End-to-end Motion Prediction Only with SD Maps (Rating: 4.75)
308. MetaTool: Facilitating Large Language Models to Master Tools with Meta-task Augmentation (Rating: 4.75)
309. Data Interpreter: An LLM Agent For Data Science (Rating: 4.75)
310. Sparse Rewards Can Self-Train Dialogue Agents (Rating: 4.75)
311. MISR: Measuring Instrumental Self-Reasoning in Frontier Models (Rating: 4.75)
312. Controlling Large Language Model Agents with Entropic Activation Steering (Rating: 4.75)
313. Emergence of Hierarchical Emotion Representations in Large Language Models (Rating: 4.75)
314. JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking (Rating: 4.75)
315. Truthful Aggregation of LLMs with an Application to Online Advertising (Rating: 4.75)
316. LifelongSotopia: Evaluating Social Intelligence Of Language Agents Over Lifelong Social Interactions (Rating: 4.75)
317. DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient Self-Driving (Rating: 4.75)
318. MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents (Rating: 4.75)
319. A Research on Result Interpretability of Medical AI Based on Large Language Model (Rating: 4.75)
320. DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects (Rating: 4.75)
321. WebCanvas: Benchmarking Web Agents in Online Environments (Rating: 4.75)
322. RoundTable: Investigating Group Decision-Making Mechanism in Multi-Agent Collaboration (Rating: 4.75)
323. Interactive Dialogue Agents via Reinforcement Learning with Hindsight Regenerations (Rating: 4.75)
324. STRIDE: A Tool-Assisted LLM Agent Framework for Strategic and Interactive Decision-Making (Rating: 4.75)
325. NNetscape Navigator: Complex Demonstrations for Web Agents Without a Demonstrator (Rating: 4.75)
326. Knowing What Not to Do: Leverage Language Model Insights for Action Space Pruning in Multi-agent Reinforcement Learning (Rating: 4.75)
327. ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents (Rating: 4.75)
328. Simulate Before Act: Model-Based Planning for Web Agents (Rating: 4.75)
329. Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning (Rating: 4.75)
330. Beyond Numeric Awards: In-Context Dueling Bandits with LLM Agents (Rating: 4.75)
331. BOIL: Learning Environment Personalized Information (Rating: 4.75)
332. Query-Efficient Planning with Language Models (Rating: 4.75)
333. GLEE: A Framework and Benchmark for LLM Evaluation in Language-based Economics (Rating: 4.75)
334. TestAgent: An Adaptive and Intelligent Expert for Human Assessment (Rating: 4.75)
335. Enhancing Language Model Agents using Diversity of Thoughts (Rating: 4.75)
336. Prioritize Alignment in Dataset Distillation (Rating: 4.75)
337. Wolf: Accurate Video Captioning with a World Summarization Framework (Rating: 4.75)
338. DialSim: A Real-Time Simulator for Evaluating Long-Term Multi-Party Dialogue Understanding of Conversational Agents (Rating: 4.75)
339. From an LLM Swarm to a PDDL-empowered Hive: Planning Self-executed Instructions in a Multi-modal Jungle (Rating: 4.67)
340. Deviation Ratings: A general, clone invariant rating method (Rating: 4.67)
341. ControlAgent: Automating Control System Design via Novel Integration of LLM Agents and Domain Expertise (Rating: 4.67)
342. Direct Multi-agent Motion Generation Preference Alignment with Implicit Feedback from Demonstrations (Rating: 4.67)
343. Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities (Rating: 4.67)
344. Improving the Efficiency of Test-Time Search in LLMs with Backtracking (Rating: 4.67)
345. Disentangling Reasoning Tokens and Boilerplate Tokens For Language Model Fine-tuning (Rating: 4.67)
346. VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use (Rating: 4.67)
347. Review and Rebuttal: Zero-shot In-context Adversarial Learning for Improving Research Ideation (Rating: 4.67)
348. LAM Simulator: Advancing Large Action Model Training for Agent via Online Exploration and Feedback Simulation (Rating: 4.67)
349. GridAgent: A 2D Grid-Based Game Framework And Benchmark For Multimodal Large Language Models (Rating: 4.67)
350. Vision-Language Models Provide Promptable Representations for Reinforcement Learning (Rating: 4.67)
351. A Generalist Hanabi Agent (Rating: 4.64)
352. Unlocking Video-LLM via Agent-of-Thoughts Distillation (Rating: 4.60)
353. DPM: Dual Preferences-based Multi-Agent Reinforcement Learning (Rating: 4.60)
354. IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction (Rating: 4.60)
355. LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence (Rating: 4.50)
356. Cognitive Insights and Stable Coalition Matching for Fostering Multi-Agent Cooperation (Rating: 4.50)
357. Chain of Ideas: Revolutionizing Research in Idea Development with LLM Agents (Rating: 4.50)
358. Agent Workflow Memory (Rating: 4.50)
359. MALLM-GAN: Multi-Agent Large Language Model as Generative Adversarial Network for Synthesizing Tabular Data (Rating: 4.50)
360. RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation (Rating: 4.50)
361. UrbanWorld: An Urban World Model for 3D City Generation (Rating: 4.50)
362. Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses (Rating: 4.50)
363. Large Legislative Models: Towards Efficient AI Policymaking in Economic Simulations (Rating: 4.50)
364. Progressive LLM Alignments Using Two-Player Games (Rating: 4.50)
365. Uncertainty-aware Human Mobility Modeling and Anomaly Detection (Rating: 4.50)
366. MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models (Rating: 4.50)
367. Personalized Federated Learning via Variational Massage Passing (Rating: 4.50)
368. Towards Safe and Honest AI Agents with Neural Self-Other Overlap (Rating: 4.50)
369. Improving Planning with Large Language Models: A Modular Agentic Architecture (Rating: 4.50)
370. Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration (Rating: 4.50)
371. Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs (Rating: 4.50)
372. DiverseAgentEntropy: Quantifying Black-Box LLM Uncertainty through Diverse Perspectives and Multi-Agent Interaction (Rating: 4.50)
373. CURATe: Benchmarking Personalised Alignment of Conversational AI Assistants (Rating: 4.50)
374. Visually Descriptive Language Model for Vector Graphics Reasoning (Rating: 4.50)
375. PREDICT: Preference Reasoning by Evaluating Decomposed preferences Inferred from Candidate Trajectories (Rating: 4.50)
376. Large Language Model-driven Large Neighborhood Search for Large-Scale MILP Problems (Rating: 4.50)
377. Towards Human-like Virtual Beings: Simulating Human Behavior in 3D Scenes (Rating: 4.50)
378. Zodiac: A Cardiologist-Level LLM Framework for Multi-Agent Diagnostics (Rating: 4.50)
379. RedCodeAgent: Automatic Red-teaming Agent against Code Agents (Rating: 4.50)
380. Advancing Algorithmic Trading with Large Language Models: A Reinforcement Learning Approach for Stock Market Optimization (Rating: 4.50)
381. NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative (Rating: 4.50)
382. PokeChamp: an Expert-level Minimax Language Agent for Competitive Pokemon (Rating: 4.50)
383. LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval (Rating: 4.50)
384. AISciVision: A Framework for Specializing Large Multimodal Models in Scientific Image Classification (Rating: 4.50)
385. CycleResearcher: Improving Automated Research via Automated Review (Rating: 4.50)
386. Shell Games: Control Protocols for Adversarial AI Agents (Rating: 4.50)
387. Versatile Motion-Language Models for Multi-turn Interactive Agents (Rating: 4.50)
388. FlowAgent: a New Paradigm for Workflow Agent (Rating: 4.50)
389. Q* Agent: Optimizing Language Agents with Q-Guided Exploration (Rating: 4.50)
390. Simulating Human-like Daily Activities with Desire-driven Autonomy (Rating: 4.50)
391. AgentRefine: Enhancing Agent Generalization through Refinement Tuning (Rating: 4.50)
392. RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning (Rating: 4.50)
393. Natural GaLore: Accelerating GaLore for memory-efficient LLM Training and Fine-tuning (Rating: 4.40)
394. CP-Guard+: A New Paradigm for Malicious Agent Detection and Defense in Collaborative Perception (Rating: 4.40)
395. ICDA: Interactive Causal Discovery through Large Language Model Agents (Rating: 4.40)
396. Adversarial Attacks on Cooperative Multi-agent Bandits (Rating: 4.40)
397. Adaptive Video Understanding Agent: Enhancing Efficiency with Dynamic Frame Sampling and Feedback-driven Reasoning (Rating: 4.40)
398. ReFeR: Improving Evaluation and Reasoning through Hierarchy of Models (Rating: 4.40)
399. Synthesizing Bonds: Enhancing Adult Attachment Predictions with LLM-Generated Data (Rating: 4.33)
400. Multi-Agent Path Finding via Decision Transformer and LLM Collaboration (Rating: 4.33)
401. Flex: End-to-End Text-Instructed Visual Navigation with Foundation Models (Rating: 4.33)
402. Efficient Reinforcement Learning for Global Decision Making in the Presence of Local Agents at Scale (Rating: 4.33)
403. Enhance Reasoning for Large Language Models with Reinforcement Learning in the Game Werewolf (Rating: 4.33)
404. Towards Specialized Web Agents Using Production-Scale Workflow Data (Rating: 4.33)
405. Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation (Rating: 4.33)
406. CogMath: Evaluating LLMs' Authentic Mathematical Ability from a Cognitive Perspective (Rating: 4.33)
407. Detecting Out-of-Context Misinformation via Multi-Agent and Multi-Grained Retrieval (Rating: 4.33)
408. Last Iterate Convergence in Monotone Mean Field Games (Rating: 4.33)
409. EcoAct: Economic Agent Determines When to Register What Action (Rating: 4.33)
410. Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation (Rating: 4.33)
411. CAAP: Context-Aware Action Planning Prompting to Solve Computer Tasks with Front-End UI Only (Rating: 4.33)
412. CodeCloak: A Method for Mitigating Code Leakage by LLM Code Assistants (Rating: 4.33)
413. MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants (Rating: 4.25)
414. Decoding Intelligence: A Framework for Certifying Knowledge Comprehension in LLMs (Rating: 4.25)
415. VideoAgent: Self-Improving Video Generation (Rating: 4.25)
416. Audio-Agent: Leveraging LLMs For Audio Generation, Editing and Composition (Rating: 4.25)
417. CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents (Rating: 4.25)
418. SnapMem: Snapshot-based 3D Scene Memory for Embodied Exploration and Reasoning (Rating: 4.25)
419. MetaAgent: Automatically Building Multi-Agent System based on Finite State Machine (Rating: 4.25)
420. Teaching Transformers Causal Reasoning through Axiomatic Training (Rating: 4.25)
421. Learning 4D Embodied World Models (Rating: 4.25)
422. Contextual Experience Replay for Continual Learning of Language Agents (Rating: 4.25)
423. Large Language Models Can Self-Improve At Web Agent Tasks (Rating: 4.25)
424. Talking Vehicles: Cooperative Driving via Natural Language (Rating: 4.25)
425. Open-World Planning via Lifted Regression with LLM-based Affordances for Embodied Agents (Rating: 4.25)
426. Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction (Rating: 4.25)
427. ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents (Rating: 4.25)
428. Towards Evaluating Generalist Agents: An Automated Benchmark in Open World (Rating: 4.25)
429. SMART: Self-Learning Meta-strategy Agent for Reasoning Tasks (Rating: 4.25)
430. OpenCity: A Scalable Platform to Simulate Urban Activities with Massive LLM Agents (Rating: 4.25)
431. OASIS: Open Agents Social Interaction Simulations on a Large Scale (Rating: 4.25)
432. Students Rather Than Experts: A New AI for Education Pipeline to Model More Human-like and Personalised Early Adolescences (Rating: 4.25)
433. Provably Efficient and Practical Self-Play for Better LLM Alignment (Rating: 4.25)
434. Agents Help Agents: Exploring Training-Free Knowledge Distillation for Small Language Models in Data Science Code Generation (Rating: 4.25)
435. Evaluating the Goal-Directedness of Large Language Models (Rating: 4.25)
436. SimSiam Naming Game: A Unified Approach for Representation Learning and Emergent Communication (Rating: 4.25)
437. In-Context Learning for Games (Rating: 4.25)
438. Optimizing Inference-Time Reasoning in LLMs via Retrieval-Augmented Reflection (Rating: 4.25)
439. AltDev: Achieving Real-Time Alignment in Multi-Agent Software Development (Rating: 4.25)
440. A Third-Person Appraisal Agent: Learning to Reason About Emotions in Conversational Contexts (Rating: 4.25)
441. How Can LLM Guide RL? A Value-Based Approach (Rating: 4.25)
442. Explicit-Constrained Single Agent for Enhanced Task-Solving in LLMs (Rating: 4.25)
443. LLMs for Generalizable Language-Conditioned Policy Learning under Minimal Data Requirements (Rating: 4.25)
444. MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaboration (Rating: 4.25)
445. Uncertainty Quantification with Generative-Semantic Entropy Estimation for Large Language Models (Rating: 4.25)
446. UI-Pro: A Hidden Recipe for Building Vision-Language Models for GUI Grounding (Rating: 4.25)
447. AgentSquare: Automatic LLM Agent Search in Modular Design Space (Rating: 4.25)
448. CogniPair - Dynamic LLM Matching Algorithm in Chaotic Environments Mimicking Human Cognitive Processes for Relationship Pairing (Rating: 4.25)
449. Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion? (Rating: 4.25)
450. AutoHijacker: Automatic Indirect Prompt Injection Against Black-box LLM Agents (Rating: 4.25)
451. Skill Discovery using Language Models (Rating: 4.25)
452. ReAcTree: Hierarchical Task Planning with Dynamic Tree Expansion using LLM Agent Nodes (Rating: 4.25)
453. Odyssey: Empowering Minecraft Agents with Open-World Skills (Rating: 4.25)
454. 'No' Matters: Out-of-Distribution Detection in Multimodality Long Dialogue (Rating: 4.20)
455. ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World (Rating: 4.20)
456. B-MoCA: Benchmarking Mobile Device Control Agents across Diverse Configurations (Rating: 4.20)
457. AdvWeb: Controllable Black-box Attacks on VLM-powered Web Agents (Rating: 4.20)
458. LossAgent: Towards Any Optimization Objectives for Image Processing with LLM Agents (Rating: 4.20)
459. Large-Scale Dynamic Graph Generation via LLM-based Agent Simulation (Rating: 4.20)
460. PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play (Rating: 4.20)
461. VeSX: A Framework Featured by Verification, Self-Correction and In-context Learning for Web Automation Tasks (Rating: 4.20)
462. Improving Model Alignment Through Collective Intelligence of Open-Source Models (Rating: 4.20)
463. Evolving Symbolic 3D Visual Grounder with Weakly Supervised Reflection (Rating: 4.17)
464. Plan B: Training LLMs to fail less severely (Rating: 4.00)
465. Memory-Driven Multimodal Chain of Thought for Embodied Long-Horizon Task Planning (Rating: 4.00)
466. The Ability of Large Language Models to Evaluate Constraint-satisfaction in Agent Responses to Open-ended Requests (Rating: 4.00)
467. Towards Reliable Offline Reinforcement Learning via Lyapunov Uncertainty Control (Rating: 4.00)
468. Computing Ex Ante Equilibrium in Heterogeneous Zero-Sum Team Games (Rating: 4.00)
469. MS$^3$M: Multi-Stage State Space Model for Motion Forecasting (Rating: 4.00)
470. Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines (Rating: 4.00)
471. Two Heads Are Better Than One: A Multi-Agent System Has the Potential to Improve Scientific Idea Generation (Rating: 4.00)
472. Leveraging Imitation Learning and LLMs for Efficient Hierarchical Reinforcement Learning (Rating: 4.00)
473. GenoAgent: A Baseline method for LLM-Based Exploration of Gene Expression Data in Alignment with Bioinformaticians (Rating: 4.00)
474. EnvBridge: Bridging Diverse Environments with Cross-Environment Knowledge Transfer for Embodied AI (Rating: 4.00)
475. Efficient Predictive Counterfactual Regret Minimization$^+$ Algorithm in Solving Extensive-Form Games (Rating: 4.00)
476. Contextual Bandits with Entropy-based Human Feedback (Rating: 4.00)
477. LeanAgent: Lifelong Learning for Formal Theorem Proving (Rating: 4.00)
478. MultiMedia-Agent: A Multimodal Agent for Multimedia Content Generation (Rating: 4.00)
479. SWE-Bench+: Enhanced Coding Benchmark for LLMs (Rating: 4.00)
480. Scaling Laws for Pre-training Agents and World Models (Rating: 4.00)
481. AutoRedTeamer: An Autonomous Red Teaming Agent Against Language Models (Rating: 4.00)
482. SmartBackdoor: Malicious Language Model Agents that Avoid Being Caught (Rating: 4.00)
483. CALF: Benchmarking Evaluation of LFQA Using Chinese Examinations (Rating: 4.00)
484. Sketch-Plan-Generalize: Learning Inductive Representations for Grounded Spatial Concepts (Rating: 4.00)
485. Shapley Value Approximation based on k-Additive Games (Rating: 4.00)
486. MAC: A Multimodal Benchmark for Understanding and Generating Academic Journal Covers (Rating: 4.00)
487. On Inherent 3D Reasoning of VLMs in Indoor Scene Layout Design (Rating: 4.00)
488. YOLO-MARL: You Only LLM Once for Multi-agent Reinforcement Learning (Rating: 4.00)
489. Entropy-Based Uncertainty Modeling for Trajectory Prediction in Autonomous Driving (Rating: 4.00)
490. Large Language Model Critics for Execution-Free Evaluation of Code Changes (Rating: 4.00)
491. iAgent: LLM Agent as a Shield between User and Recommender Systems (Rating: 4.00)
492. Benchmark for Temporal, Ambiguous, and Grounded Embodied Question-Answering (Rating: 4.00)
493. ReGen: Generative Robot Simulation via Inverse Design (Rating: 4.00)
494. Optimal Transport-Based Domain Alignment as a Preprocessing Step for Federated Learning (Rating: 4.00)
495. Understanding Data Poisoning Attacks for RAG: Insights and Algorithms (Rating: 4.00)
496. DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation (Rating: 4.00)
497. SecCodePLT: A Unified Platform for Evaluating the Security of Code GenAI (Rating: 4.00)
498. Improving Autonomous AI Agents with Reflective Tree Search and Self-Learning (Rating: 4.00)
499. Grey-box Prompt Optimization and Fine-Tuning for Cloud-Edge LLM Agents (Rating: 4.00)
500. Gödel Agent: A Self-Referential Framework Helps for Recursively Self-Improvement (Rating: 4.00)
501. MuLan: Multimodal-LLM Agent for Progressive and Interactive Multi-Object Diffusion (Rating: 4.00)
502. ANALOGXPERT: AUTOMATING ANALOG TOPOLOGY SYNTHESIS BY INCORPORATING CIRCUIT DESIGN EXPERTISE INTO LARGE LANGUAGE MODELS (Rating: 4.00)
503. Designing Deep Learning Programs with Large Language Models (Rating: 4.00)
504. Inverse Attention Agent in Multi-Agent System (Rating: 4.00)
505. Multi-Grained Knowledge for Retrieval-Augmented Question Answering on Hyper-long Contexts (Rating: 4.00)
506. SCALE: Augmenting Content Analysis via LLM Agents and AI-Human Collaboration (Rating: 4.00)
507. Embodied Instruction Following in Unknown Environments (Rating: 4.00)
508. Language-Guided Object-Centric World Models for Predictive Control (Rating: 4.00)
509. Denial-of-Service Poisoning Attacks against Large Language Models (Rating: 4.00)
510. Symbolic Learning Enables Self-Evolving Agents (Rating: 4.00)
511. AD-H: Autonomous Driving with Hierarchical Agents (Rating: 4.00)
512. Towards LLM4Floorplan: Agents Can Do What Engineers Do in Chip Design (Rating: 4.00)
513. Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback (Rating: 4.00)
514. A Super-Aligned Driving Generalist Is Your Cockpit (Rating: 3.83)
515. Make LLMs better zero-shot reasoners: structure-oriented autonomous reasoning (Rating: 3.83)
516. LLM-Mediated Guidance of MARL Systems (Rating: 3.80)
517. LLMPhy: Complex Physical Reasoning Using Large Language Models and World Models (Rating: 3.80)
518. HeurAgenix: A Multi-Agent LLM-Based Paradigm for Adaptive Heuristic Evolution and Selection in Combinatorial Optimization (Rating: 3.80)
519. Unlocking Speech Instruction Data Potential with Query Rewriting (Rating: 3.75)
520. Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages (Rating: 3.75)
521. Verbalized Bayesian Persuasion (Rating: 3.75)
522. S3E: Semantic Symbolic State Estimation With Vision-Language Foundation Models (Rating: 3.75)
523. Egocentric Vision Language Planning (Rating: 3.75)
524. Thought-Retriever: Don’t Just Retrieve Raw Data, Retrieve Thoughts (Rating: 3.75)
525. SparsitySolver: Efficient Reinforcement Learning-based Pruning for LLMs (Rating: 3.75)
526. MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control (Rating: 3.75)
527. Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial? (Rating: 3.75)
528. Inductive Linguistic Reasoning with Large Language Models (Rating: 3.75)
529. Feynman: Knowledge-Infused Diagramming Agent for Scaling Visual Reasoning Data (Rating: 3.75)
530. EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment (Rating: 3.75)
531. NextBestPath: Efficient 3D Mapping of Unseen Environments (Rating: 3.75)
532. Large language models as windows on the mental structure of psychopathology (Rating: 3.75)
533. Harnessing Input-adaptive Inference for Efficient Vision-and-Language Navigation (Rating: 3.75)
534. From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledge (Rating: 3.67)
535. A little less conversation, a little more action, please: Investigating the physical common-sense of LLMs in a 3D embodied environment (Rating: 3.67)
536. Adversarial Testing in LLMs: Insights into Decision-Making Vulnerabilities (Rating: 3.67)
537. Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysis (Rating: 3.67)
538. InteractiveCOT: Aligning Dynamic Chain-of-Thought Planning for Embodied Decision-Making (Rating: 3.67)
539. Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chess (Rating: 3.67)
540. Decentralized Blockchain-based Robust Multi-agent Multi-armed Bandit (Rating: 3.67)
541. DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning (Rating: 3.67)
542. Solving Robotics Problems in Zero-Shot with Vision-Language Models (Rating: 3.67)
543. Scalable and Accurate Graph Reasoning with LLM-based Multi-Agents (Rating: 3.67)
544. Boundless Socratic Learning (Rating: 3.60)
545. Learning a Bi-directional Driving Data Generator via Large Multi-modal Model Tuning (Rating: 3.60)
546. A Scalable Communication Protocol for Networks of Large Language Models (Rating: 3.50)
547. SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning (Rating: 3.50)
548. ALIA: An LLM for Industrial Assets using Synthetic Data (Rating: 3.50)
549. FAIRMINDSIM: ALIGNMENT OF BEHAVIOR, EMO- TION, AND BELIEF IN HUMANS AND LLM AGENTS AMID ETHICAL DILEMMAS (Rating: 3.50)
550. Defend against Jailbreak Attacks via Debate with Partially Perceptive Agents (Rating: 3.50)
551. Cracking the Collective Mind: Adversarial Manipulation in Multi-Agent Systems (Rating: 3.50)
552. Beyond Browsing: API-Based Web Agents (Rating: 3.50)
553. AutoCoder: Enhancing Code Large Language Model with AIEV-INSTRUCT (Rating: 3.50)
554. FEABench: Evaluating Language Models on Real World Physics Reasoning Ability (Rating: 3.50)
555. AutoPR: Automatically Pull Request Generation for Fix Issued Bugs of CodeBase (Rating: 3.50)
556. Massively Multi-Agents Reveal That Large Language Models Can Understand Value (Rating: 3.50)
557. SimUSER: When Language Models Pretend to Be Believable Users in Recommender Systems (Rating: 3.50)
558. Enhancing Software Agents with Monte Carlo Tree Search and Hindsight Feedback (Rating: 3.50)
559. Zero-Shot Goal Dialogue via Reinforcement Learning on Imagined Conversations (Rating: 3.50)
560. AIME: AI System Optimization via Multiple LLM Evaluators (Rating: 3.50)
561. Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1 (Rating: 3.50)
562. REDO: Execution-Free Runtime Error Detection for Coding Agents (Rating: 3.50)
563. Agent-G: An Agentic Framework for Graph Retrieval Augmented Generation (Rating: 3.50)
564. LLM-Exp: Exploring the Policy in Reinforcement Learning with Large Language Models (Rating: 3.50)
565. Value Explicit Pretraining for Learning Transferable Representations (Rating: 3.50)
566. Logic Agent: Enhancing Validity with Logic Rule Invocation (Rating: 3.50)
567. iMotion-LLM: Motion Prediction Instruction Tuning (Rating: 3.50)
568. Autoverse: an Evolvable Game Language for Learning Robust Embodied Agents (Rating: 3.50)
569. Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning (Rating: 3.50)
570. Self-controller: Controlling LLMs with Multi-round Step-by-step Self-awareness (Rating: 3.50)
571. LASER: Script Execution by Autonomous Agents for On-demand Traffic Simulation (Rating: 3.50)
572. EconAI: Preference-driven Agents Simulating Economic Activities via Large Language Model (Rating: 3.50)
573. VISION-LANGUAGE MODELS AS TRAINERS FOR INSTRUCTION-FOLLOWING AGENTS (Rating: 3.50)
574. Your Agent Can Defend Itself against Backdoor Attacks (Rating: 3.50)
575. Probing the contents of text, behavior, and brain data toward improving human-LLM alignment (Rating: 3.50)
576. LLMs Synergy : From Closed-Source Prototyping to Open-Source Model based Instruction Following (Rating: 3.40)
577. Training Open-ended Policies to follow Video-prompt Instructions with Reinforcement Learning (Rating: 3.40)
578. Multi-Agent Causal Discovery Using Large Language Models (Rating: 3.40)
579. GFLAgent: Green Federated Learning Agent for Alleviating Heterogeneity (Rating: 3.40)
580. MAC-CAFE: Multi-actor, Centralized Critic Architecture for Feedback-driven Editing (Rating: 3.25)
581. TeamCraft: A Benchmark for Embodied Multi-Agent Systems in Minecraft (Rating: 3.25)
582. DataSciBench: An LLM Agent Benchmark for Data Science (Rating: 3.20)
583. How Social is It? A Benchmark for LLMs' Capabilities in Multi-user Multi-turn Social Agent Tasks (Rating: 3.00)
584. HomieBot: an Adaptive System for Embodied Mobile Manipulation in Open Environments (Rating: 3.00)
585. Entering Real Social World! Benchmarking the Theory of Mind and Socialization Capabilities of LLMs from a First-person Perspective (Rating: 3.00)
586. SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPs (Rating: 3.00)
587. ProCEED: Prototype Consolidation and Ensemble-based Exemplar-Free Deep Incremental Learning (Rating: 3.00)
588. EchoQA: Tuning into the Heart of Echocardiogram Reports (Rating: 3.00)
589. Seeker: Enhancing Exception Handling in Code with a LLM-based Multi-Agent Approach (Rating: 3.00)
590. Enhancing Multi-Agent Learning in Real-World Interactive Environments through Process Reward Decomposition (Rating: 3.00)
591. Test-Time RAG: Enhancing Long Context Understanding in LLMs with Retrieval-Augmented Mechanisms (Rating: 3.00)
592. Grounded Robotic Action-Rule Induction through Language Models (GRAIL) (Rating: 3.00)
593. Investigating Self-Attention: Its Impact on Sample Efficiency in Deep Reinforcement Learning (Rating: 3.00)
594. Orca: Enhancing Role-Playing Abilities of Large Language Models by Integrating Personality Traits (Rating: 3.00)
595. Rapfi: Distilling Efficient Neural Network for the Game of Gomoku (Rating: 3.00)
596. Planning with MCTS: Enhancing Problem-Solving in Large Language Models (Rating: 3.00)
597. StarCraft II Arena: Evaluating LLMs in Strategic Planning, Real-Time Decision Making, and Adaptability (Rating: 3.00)
598. ChemThinker: Thinking Like a Chemist with Multi-Agent LLMs for Deep Molecular Insights (Rating: 3.00)
599. DebUnc: Improving Large Language Model Agent Communication Via Uncertainty Metrics (Rating: 3.00)
600. AutoModel: Autonomous Model Development for Image Classification with LLM Agents (Rating: 3.00)
601. Very Large-Scale Multi-Agent Simulation with LLM-Powered Agents (Rating: 3.00)
602. On the Design and Analysis of LLM-Based Algorithms (Rating: 3.00)
603. I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy (Rating: 3.00)
604. Human-like Communication Strategies for Improved Multi-Agent Reinforcement Learning (Rating: 3.00)
605. GLIMO: Grounding Large Language Models With Imperfect World Models (Rating: 3.00)
606. IDS-Agent: An LLM Agent for Explainable Intrusion Detection in IoT Networks (Rating: 3.00)
607. Foundation Models for Enhanced Exploration in Reinforcement Learning (Rating: 3.00)
608. ActionFiller: Fill-In-The-Blank Prompting for OS Agent (Rating: 3.00)
609. FALCON: A Feedback-Driven Adaptive Long/Short-Term Memory Reinforced Coding Optimization (Rating: 3.00)
610. LOB-Bench: Benchmarking Generative AI for Finance - with an Application to Limit Order Book Markets (Rating: 2.67)
611. RePrompt: Prompt Engineering for Large Language Models Agents through Reflection (Rating: 2.50)
612. Towards Autonomous Agents: Adaptive-planning, Reasoning, and Acting in Language Models (Rating: 2.50)
613. Adversarial Multi-Agent Evaluation of Large Language Models through Iterative Debate (Rating: 2.50)
614. DrugAgent: Multi-Agent Large Language Model-Based Reasoning for Drug-Target Interaction Prediction and Repurposing (Rating: 2.50)
615. Why Solving Multi-agent Path Finding with Large Language Models has not Succeeded Yet (Rating: 2.50)
616. EMERGENCE OF GROUNDED, OPTIMALLY COMPOSITIONAL SPATIAL LANGUAGE AMONG HOMOGENEOUS AGENTS (Rating: 2.33)
617. Leveraging System-Prompt Attention to Counteract Novel Jailbreak Attacks (Rating: 2.33)
618. D2Coder: large language models based agent for coding with dynamic debugging tools (Rating: 2.33)
619. Poly-Autoregressive Modeling for Interacting Entities (Rating: 2.33)
620. EReLELA: Exploration in Reinforcement Learning via Emergent Language Abstractions (Rating: 2.33)
621. Generate explorative goals with large language model guidance (Rating: 2.00)
622. CELI: CONTROLLER-EMBEDDED LANGUAGE MODEL INTERACTIONS (Rating: N/A)
623. Tooling or Not Tooling? The Impact of Tools on Language Agents for Chemistry Problem Solving (Rating: N/A)
624. Agential AI for integrated continual learning, deliberative behavior, and comprehensible models (Rating: N/A)
625. Self-Improving Logic from Experimental Observations (Rating: N/A)
626. Collaborative Theorem Proving with Large Language Models: Enhancing Formal Proofs with ProofRefiner (Rating: N/A)
627. Hindsight Planner: A Closed-loop few-shot planner for Embodied Instruction Following (Rating: N/A)
628. A collaborative Multi-Agent LLM Approach for Knowledge Graph Curation and query from multimodal data sources (Rating: N/A)
629. WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents (Rating: N/A)

Note

The ratings are based on the reviews from ICLR 2025 reviewers. Papers are sorted by their average ratings.

Contributing

Feel free to submit a PR or issue if you find any errors or have suggestions for improvement.