AgentR1/Agent-R1

Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning

62
/ 100
Established

Implements step-level MDPs with layered abstractions to enable multi-step agent training across custom workflows and tool-augmented environments. Built on the veRL framework, it provides end-to-end RL training for agents performing sequential interactions, as demonstrated by downstream projects like TableMind (table reasoning) and PaperScout (academic search with process-aware optimization).

1,313 stars. Actively maintained with 6 commits in the last 30 days.

No Package No Dependents
Maintenance 20 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

1,313

Forks

86

Language

Python

License

MIT

Last pushed

Mar 25, 2026

Commits (30d)

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/AgentR1/Agent-R1"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.