PrototypeCommon
Algorineko/AgenticArXiv-RL
Staged SFT→DPO→GRPO/OPD reinforcement learning pipeline for training a ReAct tool-use agent on arXiv paper retrieval tasks, with a deterministic snapshot-replay environment.
- Owner
- Algorineko (personal account)
- Stars
- Stars: 231
- Forks
- Forks: 85
- Language
- Python
- License
- MIT
- Created
- 2026
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- PKU-VaLuE-Lab/OmniReasoningStars: 231PythonPrototype
- RISE-X-Lab/SPROUTStars: 231PythonPrototype
- inclusionAI/IDMStars: 231PythonPrototype
- rspeer/ordered-setStars: 231PythonPrototype
- lxyu/weiboStars: 231PythonPrototype
- aldro61/pu-learningStars: 231PythonPrototype