Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics
-
Updated
Aug 23, 2026 - Python
#
agent-rl
Here are 13 public repositories matching this topic...
RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios
reinforcement-learning ppo multi-agent-reinforcement-learning rlhf llm-agent llm-reasoning entropy-method gui-agent grpo coding-agent agent-rl
-
Updated
Jun 12, 2026 - Python
Scalable and extensible reinforcement learning for LM agents.
nlp training agent framework reinforcement-learning system tool mcp rl multi-modal reward reasoning tool-use vision-language chat-template llm agentic agentrl agent-rl agentfly
-
Updated
Sep 17, 2026 - Python
[NeurIPS 2026] FedAgent: A Library for Decentralized Agent Learning. 🏆 Best Paper Award at the AAAI'26 TrustAgent Workshop, 🏆 Outstanding Paper Award in the AAAI'26 PerFM Workshop.
reinforcement-learning federated-learning neurips rl-framework llm llm-agents decentralized-ai agentic-ai agent-rl neurips-2026 multi-turn-rl
-
Updated
Sep 27, 2026 - Python
Apprentissage par renforcement pour la régulation des feux de signalisation sur un boulevard typique de Kinshasa
-
Updated
Feb 25, 2026 - Python
A curated list of training & evaluation environments for LLM/VLM agents (SWE-Gym, GEM, RAGEN, AgentGym, WebArena, OSWorld, ToolBench…). Updated weekly.
agent benchmark awesome reinforcement-learning evaluation gym rl awesome-list vla ppo tool-use web-agent browser-agent llm llm-agent agentic-ai swe-agent grpo computer-use-agent agent-rl
-
Updated
Sep 30, 2026
An end-to-end framework for Agentic Reinforcement Learning.
agent reinforcement-learning rl slime harness harbor post-training ppo large-language-models llm agentic llm-agents agentic-framework agentic-ai grpo coding-agent dapo agent-rl
-
Updated
Sep 28, 2026 - Python
Train SLM to use Tools with RL
tools reinforcement-learning rl-agents slm agent-tool llm-training agent-tools rl-agent agent-tool-rl agent-rl
-
Updated
Jul 23, 2025 - Python
Project pages for RAGEN, RAGEN-2 (reasoning collapse in agentic RL), and BAGEN (budget-aware LLM agents)
reinforcement-learning llm-agents agent-rl multi-turn-rl agentic-reinforcement-learning reasoning-collapse budget-aware-agents
-
Updated
Sep 2, 2026 - Astro
前沿 LLM 中文代码教材：KDA、AttnRes、MSA、mHC、Engram、MTP、Muon、Agent RL、多教师蒸馏、FP4 与本地 Serving · 18 章课程 · 无需云资源
education pytorch laptop chinese moe quantization knowledge-distillation dpo fastapi kda sparse-attention llm rlhf llm-training speculative-decoding grpo agent-rl
-
Updated
Oct 4, 2026 - Python
Agent-RL Credit Auditor: CPU-first audit and exact benchmark for credit estimators in agent RL. Explicit estimands, import-isolated Bellman/enumeration oracles, matched budgets, mechanism gates, claim ceilings.
python benchmark reinforcement-learning audit credit-assignment post-training llm rlhf grpo agent-rl
-
Updated
Sep 29, 2026 - Python
Compiler feedback as process reward for coding agent RL training (Junhao Fu, 2025)
-
Updated
May 11, 2026 - Python
Add this topic to your repo
To associate your repository with the agent-rl topic, visit your repo's landing page and select "manage topics."