nit: Fix README.md

Author: sheilaliuxl

README.md

@@ -34,27 +34,31 @@
   </tr>
 </table>
 
+
 🚀 Repository for automated Java code migration research, part of the [MigrationBench](https://huggingface.co/collections/AmazonScience/migrationbench-68125452fc21a4564b92b6c3) project.
 
+
 ## 📦 Packages
 
 This repository contains two main packages for Java code migration:
 
-### 🤖 [java_migration_agent](./java_migration_agent)
+### 1. 🤖 [java_migration_agent](./java_migration_agent)
 LLM-based agent library for automated Java 8 to Java 17 migration, built on the [Strands Agents](https://strandsagents.com/latest/) framework. Supports multiple migration strategies including baseline, PE (prompt engineering), RAG, and hybrid approaches.
 
-### 🔧 [self_debug](./self_debug)
+### 2. 🔧 [self_debug](./self_debug)
 SDFeedback implementation for code migration with LLMs using self-debugging feedback. Includes both single-job and batch processing capabilities with AWS EMRS support.
 
+
 ## 📊 Data
 
 Agent trajectories and execution results are stored in the `data/` folder.
 
 ## 🔗 Resources
 
-- 🤗 [MigrationBench (Hugging Face)](https://huggingface.co/collections/AmazonScience/migrationbench-68125452fc21a4564b92b6c3)
-- 💻 [MigrationBench (GitHub)](https://github.com/amazon-science/MigrationBench)
-- 📄 [arXiv Paper](https://arxiv.org/abs/2505.09569)
+1. 🤗 [MigrationBench (Hugging Face)](https://huggingface.co/collections/AmazonScience/migrationbench-68125452fc21a4564b92b6c3)
+1. 💻 [MigrationBench (GitHub)](https://github.com/amazon-science/MigrationBench)
+1. 📄 [arXiv Paper](https://arxiv.org/abs/2505.09569)
+
 
 ## 📚 Citation
 

java_migration_agent/README.md

@@ -52,22 +52,22 @@
 
 ## 1. Overview
 
-Java Migration Agent is a library for automated code migration from Java 8 to Java 17 using LLM-based agents built on the [Strands Agents](https://github.com/strands-agents/strands-agents) framework.
+Java Migration Agent is a library for automated code migration from Java 8 to Java 17 using LLM-based agents built on the [Strands Agents](https://github.com/strands-agents) framework.
 
 It provides multiple agent strategies for migration:
-- **Baseline**: Direct LLM-based migration
-- **PE (Prompt Engineering)**: Baseline with enhanced prompts for dependency updates
-- **RAG**: Uses retrieval-augmented generation for dependency version lookup
-- **Hybrid**: Pre-processes dependencies before LLM migration
+1. **Baseline**: Direct LLM-based migration
+1. **PE (Prompt Engineering)** (Baseline + PE): Baseline with enhanced prompts for dependency updates
+1. **RAG** (Baseline + PE + RAG): Uses retrieval-augmented generation for dependency version lookup
+1. **Hybrid** (Seed change, followed by baseline + PE): Pre-processes dependencies before LLM migration
 
 The agent relies on the [MigrationBench](https://github.com/amazon-science/MigrationBench) package for evaluation.
 
-## 2. [MigrationBench](https://huggingface.co/collections/AmazonScience/migrationbench-68125452fc21a4564b92b6c3) Datasets
+## 2. [🤗 MigrationBench](https://huggingface.co/collections/AmazonScience/migrationbench-68125452fc21a4564b92b6c3) Datasets
 
 | Index | Dataset                                       | Size  | Notes                                                                                               |
 |-------|-----------------------------------------------|-------|-----------------------------------------------------------------------------------------------------|
-| 1     | [AmazonScience/migration-bench-java-full](https://huggingface.co/datasets/AmazonScience/migration-bench-java-full)         | 5,102 | Each repo has a test directory or at least one test case                              |
-| 2     | [AmazonScience/migration-bench-java-selected](https://huggingface.co/datasets/AmazonScience/migration-bench-java-selected) |   300 | A **subset** of migration-bench-java-full                                          |
+| 1     | [🤗 AmazonScience/migration-bench-java-full](https://huggingface.co/datasets/AmazonScience/migration-bench-java-full)         | 5,102 | Each repo has a test directory or at least one test case                              |
+| 2     | [🤗 AmazonScience/migration-bench-java-selected](https://huggingface.co/datasets/AmazonScience/migration-bench-java-selected) |   300 | A **subset** of migration-bench-java-full                                          |
 
 ## 3. Installation
 
@@ -95,19 +95,26 @@ If you haven't done it yet, follow the instructions in [MigrationBench](https://
 ### 3.2 Install Package
 
 ```bash
-cd java_migration_agent
-pip install -e .
+# cd .../JavaMigration/
+
+cd java_migration_agent/
+pip install -r requirements.txt -e .
 ```
 
 Or with uv:
 
 ```bash
-cd java_migration_agent
+# cd .../JavaMigration/
+
+cd java_migration_agent/
 uv pip install -e .
 ```
 
 ## 4. Usage
 
+See the full binary script at [java_migration_agent/src/java_migration_agent/main.py](https://github.com/amazon-science/JavaMigration/blob/main/java_migration_agent/src/java_migration_agent/main.py).
+
+
 ### 4.1 Agent Types
 
 | Agent Type | Description |
@@ -133,16 +140,18 @@ python -m java_migration_agent \
 
 ### 4.3 Command Line Options
 
-| Option | Default | Description |
-|--------|---------|-------------|
-| `--agent-type` | (required) | Agent type: `baseline`, `pe`, `rag`, or `hybrid` |
-| `--exp-id` | (required) | Experiment identifier for organizing results |
-| `--hf-dataset` | `AmazonScience/migration-bench-java-selected` | HuggingFace dataset name |
-| `--model-id` | `global.anthropic.claude-sonnet-4-5-20250929-v1:0` | Bedrock model ID |
-| `--temperature` | `1.0` | Model temperature |
-| `--max-messages` | `80` | Maximum messages per conversation |
-| `--max-workers` | `8` | Maximum parallel workers |
-| `--output-dir` | `./migration_results` | Output directory for results |
+
+| Flag   | Type | Default | Description |
+|--------|------|---------|-------------|
+| `--agent-type` | `str` | (required) | Agent type: `baseline`, `pe`, `rag`, or `hybrid` |
+| `--exp-id` | `str` | (required) | Experiment identifier for organizing results |
+| `--hf-dataset` | `str` | `AmazonScience/migration-bench-java-selected` | HuggingFace dataset name |
+| `--model-id` | `str` | `global.anthropic.claude-sonnet-4-5-20250929-v1:0` | Bedrock model ID |
+| `--temperature` | `float` | `1.0` | Model temperature |
+| `--max-messages` | `int`  | `80` | Maximum messages per conversation |
+| `--max-workers` | `int`  | `8` | Maximum parallel workers |
+| `--output-dir` | `str` | `./migration_results` | Output directory for results |
+
 
 ## 5. 📚 Citation
 ```bibtex

self_debug/README.md

@@ -1,4 +1,4 @@
-# SDFeedback
+# JavaMigratio - SDFeedback
 
 <table>
   <tr>
@@ -44,12 +44,12 @@ markdown-toc -i README.md
 
 - [1. 📖 Overview](#1--overview)
   * [1.1 MigrationBench: Datasets and Evaluation Framework](#11-migrationbench-datasets-and-evaluation-framework)
-  * [1.2 SDFeedback: Migration with LLMs](#12-sdfeedback-migration-with-llms)
+  * [1.2 JavaMigration (SDFeedback): Migration with LLMs](#12-sdfeedback-migration-with-llms)
 - [2. 🤗 MigrationBench Datasets](#2--migrationbench-datasets)
 - [3. Code Migration with LLMs](#3-code-migration-with-llms)
   * [3.1 Single Job](#31-single-job)
     + [3.1.1 Basic Setup](#311-basic-setup)
-    + [3.1.2 Install MigrationBench and SDFeedback](#312-install-migrationbench-and-sdfeedback)
+    + [3.1.2 Install MigrationBench and JavaMigration (SDFeedback)](#312-install-migrationbench-and-sdfeedback)
     + [3.1.3 Local Run](#313-local-run)
   * [3.2 Batch Job](#32-batch-job)
     + [3.2.1 ~~Local Run~~](#321-local-run)
@@ -60,7 +60,7 @@ markdown-toc -i README.md
 
 ## 1. 📖 Overview
 
-[SDFeedback](https://github.com/amazon-science/SDFeedback)
+[JavaMigration (SDFeedback)](https://github.com/amazon-science/JavaMigration/tree/main/self_debug)
 is a library to conduct code migration with LLMs,
 and improves efficacy by providing feedback to LLMs as specific as possible,
 motivated by [Teaching Large Language Models to Self-Debug](https://arxiv.org/abs/2304.05128).
@@ -79,9 +79,9 @@ across multiple programming languages.
 is the **evaluation framework** to assess code migration success,
 from `java 8` to `17` or any other long-term support versions.
 
-### 1.2 [SDFeedback](https://github.com/amazon-science/SDFeedback): Migration with LLMs
+### 1.2 [JavaMigration (SDFeedback)](https://github.com/amazon-science/JavaMigration/tree/main/self_debug): Migration with LLMs
 
-[SDFeedback](https://github.com/amazon-science/SDFeedback)
+[JavaMigration (SDFeedback)](https://github.com/amazon-science/JavaMigration/tree/main/self_debug)
 (current package)
 is to conduct code migration with LLMs as a baseline solution,
 and it relies on the
@@ -145,13 +145,13 @@ $ conda --version
 conda 25.1.1
 ```
 
-#### 3.1.2 Install [SDFeedback](https://github.com/amazon-science/SDFeedback)
+#### 3.1.2 Install [JavaMigration (SDFeedback)](https://github.com/amazon-science/JavaMigration/self_debug)
 
 **Option A: Using uv (Recommended)**
 
 ```bash
-git clone https://github.com/amazon-science/SDFeedback.git
-cd SDFeedback
+git clone https://github.com/amazon-science/JavaMigration.git
+cd JavaMigration/self_debug
 
 # Create and activate virtual environment with uv
 uv venv --python 3.9
@@ -167,23 +167,26 @@ uv pip install -e ".[dev]"
 **Option B: Using conda/pip**
 
 ```bash
-git clone https://github.com/amazon-science/SDFeedback.git
-cd SDFeedback
+git clone https://github.com/amazon-science/JavaMigration.git
+cd JavaMigration/self_debug
 
 # Optional: create a conda env
 # conda create -n sd-feedback python=3.9
 # conda activate sd-feedback
 
 # Install package (MigrationBench is installed automatically as a dependency)
-pip install -e .
+pip install -r requirements.txt -e .
+
+# conda deactivate
 ```
 
 #### 3.1.3 Local Run
 
 To run code migration for a single repository:
 
 ```
-cd ~/SDFeedback/src/self_debug
+# cd .../JavaMigration/self_debug/
+cd src/self_debug/
 
 # Explicit `max_iteration` will override it in the `config_file`
 python run_self_debugging.py --config_file configs/java_config.pbtxt  # --max_iterations 3
@@ -214,7 +217,8 @@ Before submitting a job to EMRS, make sure you have the following ready:
 1. Build an ECR image
 
 ```
-cd ~/SDFeedback/src/self_debug/container
+# cd .../JavaMigration/self_debug/
+cd src/self_debug/container
 
 # To build ECR image: 552793110740.dkr.ecr.us-east-1.amazonaws.com/$USER:java
 ./image.sh java $USER 1 docker/java.Dockerfile  # 999999999999.dkr.ecr.us-west-2.amazonaws.com
@@ -225,7 +229,8 @@ cd ~/SDFeedback/src/self_debug/container
 Note that security keys might be subject to `12h` timeout.
 
 ```
-cd ~/SDFeedback/src/self_debug/batch
+# cd .../JavaMigration/self_debug/
+cd src/self_debug/batch
 
 # Update config file as needed for `emrs.py`, e.g. use the right ECR image in step `#1`
 CONFIG=...