When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents? 事件

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents? arXiv:2605.28224v1 Announce Type: new Abstract: Multi-trajectory inference for tool-use LLM agents - generating multiple reasoning attempts and selecting among them - benefits from transferring knowledge across attempts so that later ones avoid the pitfalls of earlier ones. Existing cross-trajectory memory methods (trajectory-level reflection, atomic fact extraction, raw observation injection) are each evaluated under a s