← Search

Yubin Wu

2 accepted papers

2026

AgentPO: Enhancing Multi-Agent Collaboration via Reinforcement Learning

ICLR 2026poster

Multi-Agent Systems (MAS) offer a powerful paradigm for solving complex problems through distributed reasoning and collaboration. However, their effectiveness is often hindered by the challenge of optimizing interactions among agents. To address this, we introduce AgentPO, a novel framework that dir…

Cited by 0SourceScholar