# Paper: Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory

---
type: paper
title: "Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory"
authors: Mingxi Zou, Zhihan Guo, Langzhang Liang, Zhuo Wang, Qifan Wang, Qingsong Wen, Irwin King, Lizhen Qu, et al.
year: 2026
venue: arXiv
url: https://arxiv.org/abs/2605.10870
code_url:
source: arxiv
collected_at: 2026-07-08
published_at: 2026-05-11
updated_at: 2026-05-11
status: skimmed
relevance: high
topics:
  - agent-evaluation
  - memory
  - planning
methods:
  - decision-rate-distortion
  - k-slot-memory
  - certified-memory-split
benchmarks:
  - LoCoMo
  - synthetic-decision-diagnostics
models:
  -
datasets:
  - cs.AI
related_concepts:
  - decision-sufficient-state
  - selective-forgetting
related_jobs:
  -
related_experiments:
  - KC-001-agent-memory-pilot
related_projects:
  - learning/agent-memory
collection_score: 13
collection_queries: language-agent
---

## One-line Takeaway

Memory 应保留会改变决策的历史差异，而不是优先保留描述最相似或最完整的记录。

## Pilot Skim

- problem: relevance、salience 和 summary fidelity 没有直接刻画 memory 对未来决策的价值。
- method: 在 K 个 runtime state 预算下定义 decision distortion、forgetting boundary，并按 certified conflict 拆分 state。
- evidence: LoCoMo 子集上描述相似度与 evidence compatibility 的相关仅 0.103；matched budget 下 DeMem gold evidence recall 为 83%，描述检索为 66%。
- boundary: 理论主要在 contextual bandit 和有限状态设定中建立，实际 LLM 冲突判定仍依赖 judge 与近似算法。

## Used In

- [Agent Memory evidence matrix](../../learning/agent-memory/evidence-matrix.md)

## Links

- arXiv: https://arxiv.org/abs/2605.10870