MeClear：基于合作博弈归因的LLM智能体记忆清理
MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents
MeClear解决了LLM智能体长交互中的记忆污染问题，通过智能清理冲突记忆，显著提升任务完成率。
MeClear是一种任务条件记忆清理框架，通过合作归因识别具有负面下游效用的记忆。该框架结合留一法筛选和采样合作Shapley归因，解决了冗余冲突掩盖问题。在十个长对话记忆池的实验中，MeClear实现了85.9%的目标召回率和82.3%的整体任务恢复率，比留一法基线提高25.5个百分点。
MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents
Long horizon Large Language Model (LLM) agents rely on external memory systems to preserve user preferences and task knowledge across extended interactions. Conventional retrieval mechanisms optimize semantic compatibility rather than downstream utility, frequently introducing outdated, misleading, or conflicting evidence into the active context. We present MeClear, a task conditioned memory clearance framework that identifies memories featuring negative downstream utility through cooperative attribution and selectively suppresses them from agent execution. MeClear combines Leave One Out screening with sampled cooperative Shapley attribution to distribute utility across interacting evidence, effectively resolving redundant conflict masking where single removal evaluations fail. Utilizing attribution rankings, MeClear executes a query scoped minimal clearance strategy over a nested filtration, verifying task recovery on the cleared context without permanently altering the persistent memory bank. Comprehensive experimental evaluations across ten long dialogue memory pools demonstrate that MeClear achieves a target recall of 85.9% and an overall task recovery rate of 82.3%, representing a 25.5 percentage point improvement over Leave One Out (LOO) baselines.