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
More from this author
+12
Daily
+173
Weekly
+433
Monthly
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
#880Update QR Code of RD-Agent's WeChat group90 comments · 2025-05-16#1308AttributeError: 'NoneType' object has no attribute 'merge'17 comments · 2025-12-01#646Where should I place daily_pv.h5 file so that it can be found?14 comments · 2025-02-26#788rdagent fin_factor error13 comments · 2025-04-14#1283How to specify my own dataset and custom factors using rdagent fin_quant8 comments · 2025-11-04#1224[Bug Report] TypeError: data must be str, not dict during fin_quant coding step**8 comments · 2025-09-04#1023WSL bug RuntimeError: Failed to create chat completion after 10 retries.6 comments · 2025-07-06#916Json loads failed when LLM outputs contain boolean value6 comments · 2025-05-30
Latest release
v1.0.0 v1.0.0 2026-09-231.0.0 (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