# Paper: Compiled Memory: Not More Information, but More Precise Instructions for Language Agents

---
type: paper
title: "Compiled Memory: Not More Information, but More Precise Instructions for Language Agents"
authors: James Rhodes, George Kang
year: 2026
venue: arXiv
url: https://arxiv.org/abs/2603.15666
code_url:
source: arxiv
collected_at: 2026-07-08
published_at: 2026-03-12
updated_at: 2026-03-12
status: skimmed
relevance: high
topics:
  - memory
  - rag
methods:
  - verified-experience-distillation
  - instruction-rewriting
  - promotion-gate
benchmarks:
  - CUAD
  - HotpotQA
models:
  -
datasets:
  - cs.AI
related_concepts:
  - procedural-memory
  - prompt-compilation
related_jobs:
  -
related_experiments:
  - KC-001-agent-memory-pilot
related_projects:
  - learning/agent-memory
collection_score: 13
collection_queries: language-agent
---

## One-line Takeaway

对稳定重复任务，经过验证的经验可以被编译成行为规则，而不必每次作为 retrieved context 注入。

## Pilot Skim

- problem: 有更多历史不代表 Agent 知道哪些经验应改变未来行为。
- method: Atlas 用多层 promotion 和 verification 把经验写成 system prompt 子规则。
- evidence: CUAD token F1 +8.7pp，HotpotQA joint F1 +3.16pp；跨模型复用同一 prompt 时 +2.31pp。
- boundary: evolved prompt 更长且缺少 length-matched control；改进严格受训练信号覆盖范围限制。

## Used In

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

## Links

- arXiv: https://arxiv.org/abs/2603.15666