arXiv cs.AI· Chang Li, Xianhao Ou, Xinyan Ma, Hao Li, Haoyuan Xu, Jiafeng Liang, Xiaohan Wang, Jiajun Chai, Guojun Yin, Ming Liu·· 2 小时前AI 评分36
CALM：面向长程语言智能体的冲突感知生命周期记忆治理框架
CALM: Conflict-Aware Lifecycle Memory Governance for Long-Horizon Language Agents
AI 导读
arXiv 论文提出 CALM，一个冲突感知的生命周期记忆治理框架，将持久记忆保留与查询时证据准入解耦。CALM 把异构记录转化为基于证据的记忆单元，利用支持、冲突和依赖信号更新有效性与生命周期状态，并通过免训练或学习式门控进行查询条件准入。
正文 · 原文
Abstract:A memory can be outdated for present-day reasoning yet indispensable for reconstructing the past. Relevance-based retrieval overlooks this tension: semantic relevance, evidence-grounded validity, and query-specific eligibility are distinct. We propose CALM, a conflict-aware lifecycle memory governance framework that decouples persistent memory preservation from query-time admission. CALM converts heterogeneous records into evidence-grounded memory cells, updates validity and lifecycle states using support, conflict, and dependency signals, and admits query-appropriate evidence through training-free or learned gating informed by temporal applicability. Across LongMemEval-S and LoCoMo with Qwen and GPT backbones, CALM outperforms state-of-the-art baselines, achieving the best overall accuracy. Compared with simple filtering and reranking, query-conditioned admission further improves evidence selection. Conflict-blocking and robustness analyses show CALM suppresses erroneous retrieved memories while retaining useful evidence. Historical-reconstruction experiments demonstrate that preserving superseded records supports accurate earlier-state reasoning without compromising current-state answers.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.38573 [cs.AI] |
| (or arXiv:2610.38573v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.38573 arXiv-issued DOI via DataCite |
Submission history
From: Chang Li [view email]
[v1]
Wed, 28 Oct 2026 10:06:57 UTC (671 KB)
来源：arXiv cs.AI · arxiv.org