AI RESEARCH
APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents
arXiv CS.LG
•
ArXi:2605.21240v1 Announce Type: new LLM agents have shown strong performance across a wide range of complex tasks, including interactive environments that require long-horizon decision making. But these agents cannot learn on the fly at test time. Self-evolving agents address this by accumulating memory and reflection across episodes rather than requiring model-weight updates. However, these agents often suffer from exploration collapse: as memory grows, behavior concentrates around familiar high-reward routines, reducing the chance of discovering better alternatives.