From af343008dc904a32c6a2245df49805b5076f062e Mon Sep 17 00:00:00 2001 From: Yusheng Su Date: Sat, 14 Oct 2023 19:43:10 +0400 Subject: [PATCH 01/27] update --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index 4e448d6cb..564b01009 100644 --- a/README.md +++ b/README.md @@ -33,6 +33,10 @@ **AgentVerse** offers a versatile framework that streamlines the process of creating custom multi-agent environments for large language models (LLMs). Designed to facilitate swift development and customization with minimal effort, our framework empowers researchers to concentrate on their research, rather than being bogged down by implementation details. +**AgentVerse** is designed to facilitate the deployment of mutiple LLM-based agents in various applications. + + + ⚠️⚠️⚠️ We're refactoring the code, and the goal is to provide a flexibility to construct simulation(without a predefined goal) and task-solving(with a specific goal) environments. Please note that this README is slightly outdated, we will update it soon. If you require a stable version that exclusively supports simulation environments, you can use [`release-0.1`](https://github.com/OpenBMB/AgentVerse/tree/release-0.1) branch. --- From 0a1a225715dabaa61ec24798890797ce53334e79 Mon Sep 17 00:00:00 2001 From: Yusheng Su Date: Sat, 14 Oct 2023 20:12:38 +0400 Subject: [PATCH 02/27] update --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 564b01009..ec14a4991 100644 --- a/README.md +++ b/README.md @@ -33,7 +33,9 @@ **AgentVerse** offers a versatile framework that streamlines the process of creating custom multi-agent environments for large language models (LLMs). Designed to facilitate swift development and customization with minimal effort, our framework empowers researchers to concentrate on their research, rather than being bogged down by implementation details. -**AgentVerse** is designed to facilitate the deployment of mutiple LLM-based agents in various applications. +**AgentVerse** is designed to facilitate the deployment of mutiple LLM-based agents in various applications. AgentVerse primarily provides two frameworks: simulation and task-solving. +- Task-solving: This framework assembles multiple agents as an automatic multi-agent system, such as software development systems, consulting systems, etc., to accomplish the corresponding tasks. +- Simulation: From 362dfce5b6977174b6056f672e121af5b147f8a3 Mon Sep 17 00:00:00 2001 From: Yusheng Su Date: Sun, 15 Oct 2023 00:13:09 +0400 Subject: [PATCH 03/27] update --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index ec14a4991..2054d8649 100644 --- a/README.md +++ b/README.md @@ -33,7 +33,7 @@ **AgentVerse** offers a versatile framework that streamlines the process of creating custom multi-agent environments for large language models (LLMs). Designed to facilitate swift development and customization with minimal effort, our framework empowers researchers to concentrate on their research, rather than being bogged down by implementation details. -**AgentVerse** is designed to facilitate the deployment of mutiple LLM-based agents in various applications. AgentVerse primarily provides two frameworks: simulation and task-solving. +**AgentVerse** is designed to facilitate the deployment of mutiple LLM-based agents in various applications. AgentVerse primarily provides two frameworks: **simulation** and **task-solving**. - Task-solving: This framework assembles multiple agents as an automatic multi-agent system, such as software development systems, consulting systems, etc., to accomplish the corresponding tasks. - Simulation: From 86f10c35195b3f8a46e04c48ebdfd029e80d10dd Mon Sep 17 00:00:00 2001 From: Yusheng Su Date: Sun, 15 Oct 2023 00:42:14 +0400 Subject: [PATCH 04/27] update --- README.md | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 2054d8649..0678602e6 100644 --- a/README.md +++ b/README.md @@ -31,12 +31,15 @@ 【English | Chinese】

+ + +**AgentVerse** is designed to facilitate the deployment of mutiple LLM-based agents in various applications. AgentVerse primarily provides two frameworks: **task-solving** and **simulation**. -**AgentVerse** is designed to facilitate the deployment of mutiple LLM-based agents in various applications. AgentVerse primarily provides two frameworks: **simulation** and **task-solving**. -- Task-solving: This framework assembles multiple agents as an automatic multi-agent system, such as software development systems, consulting systems, etc., to accomplish the corresponding tasks. -- Simulation: +- Task-solving: This framework assembles multiple agents as an automatic multi-agent system ([Multi-agent as system](https://arxiv.org/abs/2309.02427)) to collaboratively accomplish the corresponding tasks. Applications: software development system, consulting system, etc. +- Simulation: This framework allows users to set up custom environments to observe behaviors among, or interact with, multiple agents. Applications: game, social behavior research of LLM-based agents, etc. ⚠️⚠️⚠️ We're refactoring the code, and the goal is to provide a flexibility to construct simulation(without a predefined goal) and task-solving(with a specific goal) environments. Please note that this README is slightly outdated, we will update it soon. If you require a stable version that exclusively supports simulation environments, you can use [`release-0.1`](https://github.com/OpenBMB/AgentVerse/tree/release-0.1) branch. From 1b2a86bcf3f9713e0abd4f1cb5e43f58b8ffc85a Mon Sep 17 00:00:00 2001 From: Yusheng Su Date: Sun, 15 Oct 2023 00:47:06 +0400 Subject: [PATCH 05/27] update --- README.md | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 0678602e6..df27003bb 100644 --- a/README.md +++ b/README.md @@ -39,10 +39,12 @@ - Task-solving: This framework assembles multiple agents as an automatic multi-agent system ([Multi-agent as system](https://arxiv.org/abs/2309.02427)) to collaboratively accomplish the corresponding tasks. Applications: software development system, consulting system, etc. -- Simulation: This framework allows users to set up custom environments to observe behaviors among, or interact with, multiple agents. Applications: game, social behavior research of LLM-based agents, etc. - +- Simulation: This framework allows users to set up custom environments to observe behaviors among, or interact with, multiple agents.(⚠️⚠️⚠️ We're refactoring the code. If you require a stable version that exclusively supports simulation framework, you can use [`release-0.1`](https://github.com/OpenBMB/AgentVerse/tree/release-0.1) branch. +) Applications: game, social behavior research of LLM-based agents, etc. + --- From f1261cf83edae40996915312fa9740fac58d0307 Mon Sep 17 00:00:00 2001 From: Yusheng Su Date: Sun, 15 Oct 2023 00:50:30 +0400 Subject: [PATCH 06/27] update --- README.md | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index df27003bb..e1a6a8146 100644 --- a/README.md +++ b/README.md @@ -39,9 +39,15 @@ - Task-solving: This framework assembles multiple agents as an automatic multi-agent system ([Multi-agent as system](https://arxiv.org/abs/2309.02427)) to collaboratively accomplish the corresponding tasks. Applications: software development system, consulting system, etc. +

+Screen Shot 2023-09-01 at 12 08 57 PM +

+ - Simulation: This framework allows users to set up custom environments to observe behaviors among, or interact with, multiple agents.(⚠️⚠️⚠️ We're refactoring the code. If you require a stable version that exclusively supports simulation framework, you can use [`release-0.1`](https://github.com/OpenBMB/AgentVerse/tree/release-0.1) branch. ) Applications: game, social behavior research of LLM-based agents, etc. +https://github.com/OpenBMB/AgentVerse/assets/11704492/4d07da68-f942-4205-b558-f155e95782e7 + @@ -60,9 +66,6 @@ - [2023/10/5] 💡 We release the code of our paper [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents](https://arxiv.org/abs/2308.10848), and refactor our codebase to enable the creation of both simulation and task-solving environment! We have placed the code for Minecraft example in the paper at the [`minecraft`](https://github.com/OpenBMB/AgentVerse/tree/minecraft) branch. Our tool-using example will soon be updated to the `main` branch. Stay tuned! - [2023/8/22] 📝 We're excited to share our work-in-progress paper [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents](https://arxiv.org/abs/2308.10848) related to this repository. -

-Screen Shot 2023-09-01 at 12 08 57 PM -

- [2023/6/5] 🎉 We are thrilled to present an array of [demos](#-simple-demo-video), including [NLP Classroom](#nlp-classroom), [Prisoner Dilemma](#prisoner-dilemma), [Software Design](#software-design), [Database Administrator](#database-administrator-dba), and a simple [H5 Pokemon Game](#pokemon) that enables the interaction with the characters in Pokemon! Try out these demos and have fun! - [2023/5/1] 🚀 [AgentVerse](https://github.com/OpenBMB/AgentVerse) is officially launched! @@ -92,12 +95,7 @@ Also, if you're passionate about advancing the frontiers of multi-agent environm ## 👾 Simple Demo Video We demonstrate the following cases that are expertly crafted by AgentVerse. - - - #### NLP Classroom In the NLP class, the professor and students engage in interactive communication. When students have a question, they raise their hands and patiently wait for the professor to call on them. Only after being called on by the professor, can students speak and ask their questions. From e477d7e4f16b1111d148226c8d700dbf657b1807 Mon Sep 17 00:00:00 2001 From: Yusheng Su Date: Sun, 15 Oct 2023 00:51:15 +0400 Subject: [PATCH 07/27] update --- README.md | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index e1a6a8146..cc887baf6 100644 --- a/README.md +++ b/README.md @@ -37,14 +37,16 @@ **AgentVerse** is designed to facilitate the deployment of mutiple LLM-based agents in various applications. AgentVerse primarily provides two frameworks: **task-solving** and **simulation**. -- Task-solving: This framework assembles multiple agents as an automatic multi-agent system ([Multi-agent as system](https://arxiv.org/abs/2309.02427)) to collaboratively accomplish the corresponding tasks. Applications: software development system, consulting system, etc. +- Task-solving: This framework assembles multiple agents as an automatic multi-agent system ([Multi-agent as system](https://arxiv.org/abs/2309.02427)) to collaboratively accomplish the corresponding tasks. +Applications: software development system, consulting system, etc.

Screen Shot 2023-09-01 at 12 08 57 PM

- Simulation: This framework allows users to set up custom environments to observe behaviors among, or interact with, multiple agents.(⚠️⚠️⚠️ We're refactoring the code. If you require a stable version that exclusively supports simulation framework, you can use [`release-0.1`](https://github.com/OpenBMB/AgentVerse/tree/release-0.1) branch. -) Applications: game, social behavior research of LLM-based agents, etc. +) +Applications: game, social behavior research of LLM-based agents, etc. https://github.com/OpenBMB/AgentVerse/assets/11704492/4d07da68-f942-4205-b558-f155e95782e7 From 0b1ed5e99324258a7106a4b56440292f0f41bcc4 Mon Sep 17 00:00:00 2001 From: Yusheng Su Date: Sun, 15 Oct 2023 00:52:22 +0400 Subject: [PATCH 08/27] update --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index cc887baf6..2d4c89145 100644 --- a/README.md +++ b/README.md @@ -1,8 +1,10 @@

🤖 AgentVerse 🪐

+

From b529052f8cc156eaa7b40d24eaeb89f56a0b3610 Mon Sep 17 00:00:00 2001 From: Yusheng Su Date: Sun, 15 Oct 2023 00:59:52 +0400 Subject: [PATCH 09/27] update --- README.md | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) diff --git a/README.md b/README.md index 2d4c89145..4463cbc2d 100644 --- a/README.md +++ b/README.md @@ -58,24 +58,19 @@ https://github.com/OpenBMB/AgentVerse/assets/11704492/4d07da68-f942-4205-b558-f1 --- -## ✨ Features - -- 🥳 **Efficient Environment Building:** Our framework provides a collection of essential building blocks for effortlessly creating a multi-agent environment. With only a few lines in a configuration file, you can easily construct basic environments such as a chat room for LLMs. This process entails defining the environment's settings and prompts for LLMs, enabling researchers like you to concentrate on experimentation and analysis. - -- ⚙️ **Customizable Components**: AgentVerse simplifies the multi-agent environment by dividing it into five functional modules and defining their respective interfaces. For complex environments that cannot be constructed directly using the basic modules offered in AgentVerse, you can customize one or more of the interfaces within these five functional modules to efficiently create your own multi-agent environment according to your requirements. - -- 🛠 **Tools (Plugins) Utilization**: AgentVerse supports the multi-agent environments with tools. Currently, AgentVerse supports tools provided in [BMTools](https://github.com/OpenBMB/BMTools). ## 📰 What's New -- [2023/10/5] 💡 We release the code of our paper [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents](https://arxiv.org/abs/2308.10848), and refactor our codebase to enable the creation of both simulation and task-solving environment! We have placed the code for Minecraft example in the paper at the [`minecraft`](https://github.com/OpenBMB/AgentVerse/tree/minecraft) branch. Our tool-using example will soon be updated to the `main` branch. Stay tuned! +- [2023/10/5] Re-factor our codebase to enable the deployment of both simulation and task-solving framework! We have placed the code for Minecraft example in the paper at the [`minecraft`](https://github.com/OpenBMB/AgentVerse/tree/minecraft) branch. Our tool-using example will soon be updated to the `main` branch. Stay tuned! -- [2023/8/22] 📝 We're excited to share our work-in-progress paper [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents](https://arxiv.org/abs/2308.10848) related to this repository. +- [2023/8/22] We're excited to share our paper [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents](https://arxiv.org/abs/2308.10848) that illistrate the task-solving framework +in detail of AgentVerse. -- [2023/6/5] 🎉 We are thrilled to present an array of [demos](#-simple-demo-video), including [NLP Classroom](#nlp-classroom), [Prisoner Dilemma](#prisoner-dilemma), [Software Design](#software-design), [Database Administrator](#database-administrator-dba), and a simple [H5 Pokemon Game](#pokemon) that enables the interaction with the characters in Pokemon! Try out these demos and have fun! +- [2023/6/5] We are thrilled to present an array of [demos](#-simple-demo-video), including [NLP Classroom](#nlp-classroom), [Prisoner Dilemma](#prisoner-dilemma), [Software Design](#software-design), [Database Administrator](#database-administrator-dba), and a simple [H5 Pokemon Game](#pokemon) that enables the interaction with the characters in Pokemon! Try out these demos and have fun! - [2023/5/1] 🚀 [AgentVerse](https://github.com/OpenBMB/AgentVerse) is officially launched! ## 🌟 Join Us! AgentVerse is on a mission to revolutionize the multi-agent environment for large language models, and we're eagerly looking for passionate collaborators to join us on this exciting journey. + ### How Can You Contribute? - **Code Development**: If you're an engineer, help us refine, optimize, and expand the current framework. We're always looking for talented developers to enhance our existing features and develop new modules. From 51f4c8bc5e8032826d261c72a0b3a05e00394e8c Mon Sep 17 00:00:00 2001 From: Yusheng Su Date: Sun, 15 Oct 2023 01:06:41 +0400 Subject: [PATCH 10/27] update --- README.md | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) diff --git a/README.md b/README.md index 4463cbc2d..b1f908857 100644 --- a/README.md +++ b/README.md @@ -33,10 +33,6 @@ 【English | Chinese】

- - **AgentVerse** is designed to facilitate the deployment of mutiple LLM-based agents in various applications. AgentVerse primarily provides two frameworks: **task-solving** and **simulation**. - Task-solving: This framework assembles multiple agents as an automatic multi-agent system ([Multi-agent as system](https://arxiv.org/abs/2309.02427)) to collaboratively accomplish the corresponding tasks. @@ -52,10 +48,6 @@ Applications: game, social behavior research of LLM-based agents, etc. https://github.com/OpenBMB/AgentVerse/assets/11704492/4d07da68-f942-4205-b558-f155e95782e7 - - --- @@ -80,7 +72,7 @@ AgentVerse is on a mission to revolutionize the multi-agent environment for larg - **Feedback and Suggestions**: Use AgentVerse and provide us with feedback. Your insights can lead to potential improvements and ensure that our framework remains top-notch. -Also, if you're passionate about advancing the frontiers of multi-agent environments and are eager to dive deeper into research, we invite you to join our team at THUNLP. To explore this exciting opportunity and embark on a collaborative journey with us, please reach out to [chenweize1998@gmail.com](chenweize1998@gmail.com) and [yushengsu.thu@gmail.com](yushengsu.thu@gmail.com) and express your interest. We're keen to welcome motivated individuals like you to our lab! +Also, if you're passionate about advancing the frontiers of multi-agent applications and are eager to dive deeper into research, we invite you to join AgentVerse team. Please reach out [AgentVerse Team](agentverse2@gmail.com) and CC to [chenweize1998@gmail.com](chenweize1998@gmail.com) and [yushengsu.thu@gmail.com](yushengsu.thu@gmail.com). We're keen to welcome motivated individuals like you to our team! 👉Also, check our Discord: https://discord.gg/cnutfCtC. @@ -423,7 +415,11 @@ If you find this repo helpful, feel free to cite us. ## Contact -Weize Chen: chenweize1998@gmail.com +AgentVerse Team: agentverse2@gmail.com + +Project leaders: + +- Weize Chen: chenweize1998@gmail.com -[Yusheng Su](https://yushengsu-thu.github.io/): yushengsu.thu@gmail.com +- [Yusheng Su](https://yushengsu-thu.github.io/): yushengsu.thu@gmail.com From bc9216e543c32c3505c3340843b0afd0fa2ffbd4 Mon Sep 17 00:00:00 2001 From: Yusheng Su Date: Sun, 15 Oct 2023 01:12:41 +0400 Subject: [PATCH 11/27] update --- README.md | 41 ++++++++++++++++++++++++++++------------- 1 file changed, 28 insertions(+), 13 deletions(-) diff --git a/README.md b/README.md index b1f908857..f29fad997 100644 --- a/README.md +++ b/README.md @@ -60,21 +60,8 @@ in detail of AgentVerse. - [2023/6/5] We are thrilled to present an array of [demos](#-simple-demo-video), including [NLP Classroom](#nlp-classroom), [Prisoner Dilemma](#prisoner-dilemma), [Software Design](#software-design), [Database Administrator](#database-administrator-dba), and a simple [H5 Pokemon Game](#pokemon) that enables the interaction with the characters in Pokemon! Try out these demos and have fun! - [2023/5/1] 🚀 [AgentVerse](https://github.com/OpenBMB/AgentVerse) is officially launched! -## 🌟 Join Us! -AgentVerse is on a mission to revolutionize the multi-agent environment for large language models, and we're eagerly looking for passionate collaborators to join us on this exciting journey. - -### How Can You Contribute? -- **Code Development**: If you're an engineer, help us refine, optimize, and expand the current framework. We're always looking for talented developers to enhance our existing features and develop new modules. -- **Documentation and Tutorials**: If you have a knack for writing, help us improve our documentation, create tutorials, or write blog posts to make AgentVerse more accessible to the broader community. -- **Application Exploration**: If you're intrigued by multi-agent applications and are eager to experiment using AgentVerse, we'd be thrilled to support your journey and see what you create! - -- **Feedback and Suggestions**: Use AgentVerse and provide us with feedback. Your insights can lead to potential improvements and ensure that our framework remains top-notch. - -Also, if you're passionate about advancing the frontiers of multi-agent applications and are eager to dive deeper into research, we invite you to join AgentVerse team. Please reach out [AgentVerse Team](agentverse2@gmail.com) and CC to [chenweize1998@gmail.com](chenweize1998@gmail.com) and [yushengsu.thu@gmail.com](yushengsu.thu@gmail.com). We're keen to welcome motivated individuals like you to our team! - -👉Also, check our Discord: https://discord.gg/cnutfCtC. ## 🗓 Coming Soon - [x] Code release of our [paper](https://arxiv.org/abs/2308.10848) @@ -277,6 +264,7 @@ agentverse-tasksolving --task tasksolving/humaneval/gpt-3.5 --dataset_path data/ You can take a look at `agentverse/tasks/tasksolving` for more experiments we have done in our paper. + + + + + + +## 🌟 Join Us! +AgentVerse is on a mission to revolutionize the multi-agent environment for large language models, and we're eagerly looking for passionate collaborators to join us on this exciting journey. + +### How Can You Contribute? +- **Code Development**: If you're an engineer, help us refine, optimize, and expand the current framework. We're always looking for talented developers to enhance our existing features and develop new modules. + +- **Documentation and Tutorials**: If you have a knack for writing, help us improve our documentation, create tutorials, or write blog posts to make AgentVerse more accessible to the broader community. + +- **Application Exploration**: If you're intrigued by multi-agent applications and are eager to experiment using AgentVerse, we'd be thrilled to support your journey and see what you create! + +- **Feedback and Suggestions**: Use AgentVerse and provide us with feedback. Your insights can lead to potential improvements and ensure that our framework remains top-notch. + +Also, if you're passionate about advancing the frontiers of multi-agent applications and are eager to dive deeper into research, we invite you to join AgentVerse team. Please reach out [AgentVerse Team](agentverse2@gmail.com) and CC to [chenweize1998@gmail.com](chenweize1998@gmail.com) and [yushengsu.thu@gmail.com](yushengsu.thu@gmail.com). We're keen to welcome motivated individuals like you to our team! + + +### Social Media and Community + +- Twitter: https://twitter.com/Agentverse71134 + +- Discord: https://discord.gg/cnutfCtC. ## Star History From dd49c21c81157fdd454bfd0d6fdc8e68a56b2dbd Mon Sep 17 00:00:00 2001 From: Yusheng Su Date: Sun, 15 Oct 2023 01:14:46 +0400 Subject: [PATCH 12/27] update --- README.md | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/README.md b/README.md index f29fad997..93baee406 100644 --- a/README.md +++ b/README.md @@ -70,6 +70,8 @@ in detail of AgentVerse. - [ ] Add support for local LLM + ## Contents @@ -221,13 +224,7 @@ python setup.py develop ``` - + ### Simulation CLI Example @@ -264,6 +261,8 @@ agentverse-tasksolving --task tasksolving/humaneval/gpt-3.5 --dataset_path data/ You can take a look at `agentverse/tasks/tasksolving` for more experiments we have done in our paper. + + - + + + +## Contents +- [📰 What's New](#-whats-new) +- [🗓 Coming Soon](#-coming-soon) +- [Contents](#contents) +- [🚀 Getting Started](#-getting-started) + - [Installation](#installation) + - [Simulation CLI Example](#simulation-cli-example) + - [Simulation Local Website Demo](#simulation-local-website-demo) + - [Task-Solving CLI Example](#task-solving-cli-example) +- [🔎 Examples](#-examples) +- [🌟 Join Us!](#-join-us) + - [How Can You Contribute?](#how-can-you-contribute) +- [Social Media and Community](#social-media-and-community) +- [Star History](#star-history) +- [Citation](#citation) +- [Contact](#contact) + + ## 🚀 Getting Started @@ -224,8 +245,6 @@ python setup.py develop ``` - - ### Simulation CLI Example You can create a multi-agent environments provided by us. Using the classroom scenario as an example. In this scenario, there are nine agents, one playing the role of a professor and the other eight as students. From d13c412a6eae45a59ce1ad824d68e4753ff342b9 Mon Sep 17 00:00:00 2001 From: Yusheng Su Date: Sun, 15 Oct 2023 02:00:15 +0400 Subject: [PATCH 17/27] update --- README.md | 8 ++++ README_simulation_cases.md | 75 +++++++++++++++++++++++++++++++++++++ README_tasksolving_cases.md | 0 setup.py | 4 +- 4 files changed, 85 insertions(+), 2 deletions(-) create mode 100644 README_simulation_cases.md create mode 100644 README_tasksolving_cases.md diff --git a/README.md b/README.md index a72a6db18..a8f876637 100644 --- a/README.md +++ b/README.md @@ -280,6 +280,14 @@ agentverse-tasksolving --task tasksolving/humaneval/gpt-3.5 --dataset_path data/ You can take a look at `agentverse/tasks/tasksolving` for more experiments we have done in our paper. +## AgentVerse Showcases + +### Simulation Showcases +Refer to + +### Task-Solving Showcases +Refer to + -## Contents +# Contents - [📰 What's New](#-whats-new) - [🗓 Coming Soon](#-coming-soon) - [Contents](#contents) @@ -207,9 +207,9 @@ https://github.com/OpenBMB/AgentVerse/assets/11704492/4d07da68-f942-4205-b558-f1 -## 🚀 Getting Started +# 🚀 Getting Started -### Installation +## Installation ```bash pip install -U agentverse @@ -245,9 +245,9 @@ pip install -r requirements.txt python setup.py develop ``` -### Simulation +## Simulation -#### Framework Required Modules +### Framework Required Modules ``` - agentverse - agents @@ -256,7 +256,7 @@ python setup.py develop - simulation_env ``` -#### CLI Example +### CLI Example You can create a multi-agent environments provided by us. Using the classroom scenario as an example. In this scenario, there are nine agents, one playing the role of a professor and the other eight as students. @@ -266,7 +266,7 @@ python3 agentverse_command/main_simulation_cli.py --task simulation/nlp_classroo agentverse-simulation --task simulation/nlp_classroom_9players ``` -#### GUI Example (Local) +### GUI Example (Local) We also provide a local website demo for this environment. You can launch it with @@ -278,10 +278,10 @@ agentverse-simulation-gui --task simulation/nlp_classroom_9players After successfully launching the local server, you can visit [http://127.0.0.1:7860/](http://127.0.0.1:7860/) to view the classroom environment. -### Task-Solving +## Task-Solving -#### Framework Required Modules +### Framework Required Modules ``` - agentverse - agents @@ -290,7 +290,7 @@ After successfully launching the local server, you can visit [http://127.0.0.1:7 - tasksolving_env ``` -#### CLI Example +### CLI Example To run the experiments with the task-solving environment proposed in our [paper](https://arxiv.org/abs/2308.10848), you can use the following command: @@ -304,12 +304,12 @@ agentverse-tasksolving --task tasksolving/humaneval/gpt-3.5 --dataset_path data/ You can take a look at `agentverse/tasks/tasksolving` for more experiments we have done in our paper. -## AgentVerse Showcases +# AgentVerse Showcases -### Simulation Showcases +## Simulation Showcases Refer to [simulation showcases](README_simulation_cases.md) -### Task-Solving Showcases +## Task-Solving Showcases Refer to [tasksolving showcases](README_tasksolving_cases.md) @@ -447,14 +447,14 @@ Here's a brief overview of each example: --> -## 🌟 Join Us! +# 🌟 Join Us! AgentVerse is on a mission to revolutionize the multi-agent environment for large language models, and we're eagerly looking for passionate collaborators to join us on this exciting journey. -### Leaders +## Leaders Leader Leader -### Contributors +## Contributors Contributor Contributor Contributor @@ -469,7 +469,7 @@ AgentVerse is on a mission to revolutionize the multi-agent environment for larg Contributor -### How Can You Contribute? +## How Can You Contribute? - **Code Development**: If you're an engineer, help us refine, optimize, and expand the current framework. We're always looking for talented developers to enhance our existing features and develop new modules. - **Documentation and Tutorials**: If you have a knack for writing, help us improve our documentation, create tutorials, or write blog posts to make AgentVerse more accessible to the broader community. @@ -481,14 +481,14 @@ AgentVerse is on a mission to revolutionize the multi-agent environment for larg Also, if you're passionate about advancing the frontiers of multi-agent applications, become core AgentVerse team members, or are eager to dive deeper into agent research. Please reach out [AgentVerse Team](agentverse2@gmail.com), and CC to [chenweize1998@gmail.com](chenweize1998@gmail.com) and [yushengsu.thu@gmail.com](yushengsu.thu@gmail.com). We're keen to welcome motivated individuals like you to our team! -### Social Media and Community +## Social Media and Community - Twitter: https://twitter.com/Agentverse71134 - Discord: https://discord.gg/cnutfCtC. -## Star History +# Star History [![Star History Chart](https://api.star-history.com/svg?repos=OpenBMB/AgentVerse&type=Date)](https://star-history.com/#OpenBMB/AgentVerse&Date) @@ -504,7 +504,7 @@ If you find this repo helpful, feel free to cite us. } ``` -## Contact +# Contact AgentVerse Team: agentverse2@gmail.com