agentic-reinforcement-learning

论文提出 Multi-Session Agentic 强化学习设定，并提出 Mosaic 方法，通过层次化优势估计优化会话级贡献与分配，在 BrowseComp 上以更少会话数优于广播式优势方法。

This paper presents InternReviewer and InternAdvocate, a framework for developing AI agents in academic peer review and rebuttal using agentic reinforcement learning with objective rewards to improve reasoning depth, citation accuracy, and reduce hallucinations.

IBM has launched Granite 4.2, a family of open-weight large language models with variants up to 30B parameters, featuring a 128,000-token context window and agentic reinforcement learning for enhanced capabilities.

Agent Lightning v1.0 is a lightweight framework that enables reproducible reinforcement learning for agent harnesses, significantly boosting coding-agent performance on benchmarks like SWE-bench Verified.