https://www.tgltommy.com/courses/agent-rl/lectures/65840533
Agent RL 思维导图（持续更新） | TGLTommy
这是一门面向大模型 Agent 后训练与强化学习落地的系统实战课。 课程不只讲 RLHF、PPO、DPO、GRPO、RLVR 的算法概念，而是围绕 Agent 项目真实落地中的奖励设计、信用分配、长轨迹归因、训练系统、评测反馈和 Skill...
agent
https://huggingface.co/papers/2608.17528
Paper page - Agent Lightning v1.0: Towards Harnessed Agentic RL
Join the discussion on this paper page
paperagentlightningtowardsharnessed
https://c3lab.poliba.it/node/108
Multi-agent RL | C3LAB
multiagent
https://www.atlaso.ai/lab/adaptive-stigmergy-gates
Adaptive Stigmergy Gates for Multi-Agent RL Coordination — Atlaso
Apr 6, 2026 - An adaptive gate that turns on coordination only under population-level distress outperforms both always-on and always-off baselines by +34% on the hard task...
adaptivestigmergygatesmultiagent
https://www.sean-weldon.com/blog/2026-07-02-using-rl-agent-to-detect-and-remediate-etl-pipeline-failures-anna-marie-benzon
Using RL Agent to Detect and Remediate ETL Pipeline Failures - Anna Marie Benzon | Sean Weldon
Jul 2, 2026 - An RL-guided system can automatically select bounded remediation actions for ETL failures while maintaining safety constraints, reducing manual incident resp...
rl agentanna marieusingdetectremediate
https://arxiv.org/abs/2507.05720v1
[2507.05720v1] MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online...
Abstract page for arXiv paper 2507.05720v1: MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment
reinforcement learningadvancingmobileguiagent