microsoft /RD-Agent

Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report

★ 15,387⑂ 2,053👁 89⑃ 1,342● 170▤ 12
PythonMITCreated 2024-04-03rdagent.azurewebsites.net/
下载:v1.0.0v1.0.0 ↓1.0.02026-09-23
+12
日增长
+173
周增长
+433
月增长
15,387
stars
2,053
forks
89
watchers
1,342
prs
170
issues
12
releases

README

🖥️ Live Demo |
  🎥 Demo Video ▶️YouTube   |
  📖 Documentation |
  📄 Tech Report |
   📃 Papers 


















  



 📰 News
| 🗞️ News        | 📝 Description                 |
| --            | ------      |
| Agent² RL-Bench Preprint | A benchmark for evaluating LLM agents on end-to-end post-training engineering. See the project page and code. |
| ICML 2026 Acceptance | We are thrilled to announce that our paper FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents has been accepted to ICML 2026. The FT-Agent implementation is available in the LLM fine-tuning guide. |
| ACL 2026 Findings Acceptance | We are thrilled to announce that our paper Reasoning as Gradient has been accepted to ACL 2026 Findings. Execution traces are available at Gome GPT-5 Traces |
| Web UI Release | We release a new frontend that can be built and served by rdagent server_ui for real-time interaction and trace viewing, currently excluding the data_science scenario. |
| NeurIPS 2025 Acceptance | We are thrilled to announce that our paper R&D-Agent-Quant has been accepted to NeurIPS 2025 | 
| Technical Report Release | Overall framework description and results on MLE-bench | 
| R&D-Agent-Quant Release | Apply R&D-Agent to quant trading | 
| MLE-Bench Results Released | R&D-Agent currently leads as the top-performing machine learning engineering agent on MLE-bench |
| Support LiteLLM Backend | We now fully support LiteLLM as our default backend for integration with multiple LLM providers. |
| General Data Science Agent | Data Science Agent |
| Kaggle Scenario release | We release Kaggle Agent, try the new features!                  |
| Official WeChat group release  | We created a WeChat group, welcome to join! (🗪QR Code) |
| Official Discord release  | We launch our first chatting channel in Discord (🗪) |
| First release | R&D-Agent is released on GitHub |


 🧪 Agent² RL-Bench


  Project Page ·
  Paper ·
  Code & Quick Start ·
  Microsoft Research


Agent² RL-Bench evaluates whether LLM agents can autonomously engineer end-to-end post-training pipelines, spanning static optimization and stateful online RL.


 🏆 The Best Machine Learning Engineering Agent!

MLE-bench is a comprehensive benchmark evaluating the performance of AI agents on machine learning engineering tasks. Utilizing datasets from 75 Kaggle competitions, MLE-bench provides robust assessments of AI systems' capabilities in real-world ML engineering scenarios.

R&D-Agent currently leads as the top-performing machine learning engineering agent on MLE-bench:

| Agent | Low == Lite (%) | Medium (%) | High (%) | All (%) |
|---------|--------|-----------|---------|----------|
| R&D-Agent o3(R)+GPT-4.1(D) | 51.52 ± 6.9 | 19.3 ± 5.5 | 26.67 ± 0 | 30.22 ± 1.5 |
| R&D-Agent o1-preview | 48.18 ± 2.49 | 8.95 ± 2.36 | 18.67 ± 2.98 | 22.4 ± 1.1 |
| AIDE o1-preview | 34.3 ± 2.4 | 8.8 ± 1.1 | 10.0 ± 1.9 | 16.9 ± 1.1 |

Notes:
- O3(R)+GPT-4.1(D): This version is designed to both reduce average time per loop and 

Top issues

Latest release

v1.0.0 v1.0.0 2026-09-23
1.0.0 (2026-09-23)


 ⚠ BREAKING CHANGES

 UI_SERVER_AUTH_TOKEN is required for localhost deployments. General Model uploads require an actual report file; URL and server-path inputs are no longer supported.

 Features

 [AutoRL-Bench] Update DeepSearchQA split and translate task instructions to English (1368) (471eb30)
 add a web UI server (1345) (be47e5b)
 add LLM-finetune scenario (1314) (1824e1c)
 rl: add AutoRL-Bench framework and benchmark integrations (1348) (3f24925)
 sync server UI history traces from backend (1386) (706e907)


 Bug Fixes

 (to main) litellm's Timeout error is not pic

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON