Memory cleaning improves task success for long running AI conversations
MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents
Artificial IntelligenceSoftware Engineering
Summary
When AI systems like chatbots remember too much over a long time, they sometimes use outdated or conflicting information that confuses their responses. The authors introduce MeClear, a new method that carefully checks which remembered information actually helps the current task and removes the parts that hurt the AI’s performance. By doing this in a smart way, MeClear improves how well AI agents complete complex tasks over long chats. Their tests show it works better than existing methods that remove bad memories one by one.
What this means in practice
- •For conversational ai developers: Improve AI chatbot memory management to maintain relevant information and avoid confusing responses in long interactions.
- •For customer support automation teams: Enhance performance of automated support agents by selectively filtering outdated user preferences and task knowledge from memory.
Authors
Boyu Yang, Jiazheng Sun, Zilong Lu, Zhi Qiu, Xin Peng, Jun Zheng
Abstract
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retrieval mechanisms optimize semantic compatibility rather than downstream utility, frequently introducing outdated, misleading, or conflicting evidence into the active context.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.