thinkwee/AgentsMeetRL resource

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1799 stars · 72 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A curated awesome list of open-source repositories for training LLM agents with reinforcement learning, organized by taxonomy categories like frameworks, environments, rewards, and multi-agent systems. It includes an interactive dashboard and focuses on the RL frameworks, algorithms, rewards, and environments each listed project depends on.

Use cases

• find open-source repos for training LLM agents with reinforcement learning
• survey RL frameworks and environments used by agentic LLM projects
• research RLHF and RLVR approaches for tool-using agents
• compare multi-turn and tool-integrated reasoning training setups
• discover agentic coding and search/RAG agent training projects
• find reward and environment designs for agent RL training

When to choose

• you need a curated, categorized survey of agentic RL repositories
• you're researching technical choices (frameworks, rewards, environments) of agent RL projects
• you want a regularly updated list with an interactive dashboard

When to avoid

• you need runnable software rather than a reference list
• you need guaranteed-complete or fully verified coverage, since entries are LLM-assisted and may contain errors

Facets

learning-resource · maturity active

agent-framework llm-training reinforcement-learning rag artificial-intelligence large-language-models reinforcement-learning awesome-lists awesome-list agentic-rl rlhf rlvr tool-learning multi-agent curated-resources llm-agents ai-agents web

Member repositories

For agents

markdown · JSON · MCP: product_card(name="thinkwee/AgentsMeetRL")