4 papers · 1 filter
SRPO: Setwise Relative Policy Optimization for Multi-Agent LLMs
Shengtian Yang, Ziyu Xiong, Yu Li +3
Multi-agent large language models solve complex tasks by coordinating several policies in a shared environment. However, existing reinforcement learning methods usually optimize ea…
AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories
Zhiyi Lyu, Yewen Li, Longtao Zheng +7
LLM-based agents are increasingly deployed in real-world applications through tool-use APIs, yet training them for specific environments remains fundamentally difficult: real-world…
PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning
Yu Li, Guangfeng Cai, Shengtian Yang +5
Recent advancements in Large Language Model (LLM) agents have demonstrated strong capabilities in executing complex tasks through tool use. However, long-horizon multi-step tool pl…
Phase-Aware Mixture of Experts for Agentic Reinforcement Learning
Shengtian Yang, Yu Li, Shuo He +4
Reinforcement learning (RL) has equipped LLM agents with a strong ability to solve complex tasks. However, existing RL methods normally use a \emph{single} policy network, causing…