AgentR1 / Agent-R1
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
Why this job: says: reinforcement learning
What it does
Unlike single-turn RL pipelines that treat interaction as one growing prompt-response sequence, Agent-R1 models every turn as a step-level MDP transition. This makes tool use, environment state, context management, reward assignment, and policy optimization explicit parts of the same training substrate.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 3 months ago
- Stars
- 1,717
- +6 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 44% closed
- 35 still open
- Pull requests
- 32 merged
- 17 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| DaoyuanLi2816 / mini-verl | 310 | 55 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- agent
- agentic-rl
- llm
Project record
- JobFine-tuning
- StatusListed
- Commits19
- Forks121
- Watching12
- Stars in 28 days+30
- CreatedMar 4, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026