cs.AINov 17, 2026

RegimeCouncil: Paired-Evidence Routing For Memory Conflict Governance In LLM Agents

Authors: Qingcan Kang, Mingyang Liu, Shixiong Kai, Tao Zhong, Mingxuan Yuan

Organizations: Huawei Noah’s Ark Lab, Hong Kong · City University of Hong Kong, Hong Kong

Abstract

Language agents rely on long-term memory to personalize responses across extended interactions, yet stored facts quietly go stale as the world changes, and an agent often learns that using memory hurt only through delayed feedback after acting on an outdated record. Before the memory store is updated, how far should that negative feedback propagate: should it suppress memory use only on future queries for that same fact (a local policy), or also across other stored facts (a global policy)? Existing memory systems implicitly fix one of these two sharing scopes at design time. We formulate this online scope choice under hidden validity and delayed feedback as memory conflict governance, and prove that neither fixed policy is sufficient on its own. We then propose RegimeCouncil, a lightweight paired-evidence router that retains both scopes as advisors and arbitrates between them online without retraining the LLM. Using revealed comparisons between answering with memory and answering without memory (the no-memory anchor), a Local Advisor tracks the latest outcome on the queried fact alone, while a Global Advisor pools recent outcomes across all stored facts. A Meta Governor follows the Local Advisor by default to avoid cross-fact interference and switches to the Global Advisor only when global pooling accumulates a strictly positive recent utility margin, guaranteeing finite-time switching under delayed feedback. Across LongMemEval update streams and real-world historical drift on TempLAMA and TAQA with Qwen3-30B-A3B and GPT-4o, RegimeCouncil outperforms the better fixed-scope policy by 5.2-7.3 points on primary disagreement episodes and across all 30 held-out settings, while ablations show that removing any of its three modules reduces accuracy by 2-7 points.

Figures & tables

Appendix figures & tables17 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Accept Changes, Reject Attacks: Robust Memory Management for LLM Agents

    Oct 29, 2026Runze Zhao, Dongruo Zhou, Sumit Kumar Jha +2Memory Management for LLM AgentsAgent Memory Poisoning

  2. STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?

    May 7, 2026Hanxiang Chao, Yihan Bai, Rui Sheng +2Agent MemoryLLM Agent Evaluation

  3. Whose Memory Is It? Scope-Aware Commit Rules for Long-Term LLM Memory

    Oct 6, 2026Hongyu Gu, Xinchang LiLong-Term Conversational MemoryAgent Memory Management