---
title: "CALM: Conflict-Aware Lifecycle Memory Governance for Long-Horizon Language Agents"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.38573v1"
permalink: "https://feed.astralor.com/items/itm_a7f5b29a294ca53959b12414"
published: "2026-10-28T10:06:57.000Z"
score: 54
channel: "tech"
tags: ["AI Agent","OpenAI","推理效率","RAG","CALM","Conflict-Aware Lifecycle Memory","Governance","Long-Horizon Language Agents"]
---

# CALM: Conflict-Aware Lifecycle Memory Governance for Long-Horizon Language Agents

## 速览

A memory can be outdated for present-day reasoning yet indispensable for reconstructing the past.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 elig…

## 关键点

- A memory can be outdated for present-day reasoning yet indispensable for reconstructing the past.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.

## 全文

A memory can be outdated for present-day reasoning yet indispensable for reconstructing the past.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 Historical-reconstruction experiments demonstrate that preserving superseded records supports accurate earlier-state reasoning without compromising current-state answers.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_a7f5b29a294ca53959b12414