将用户对话压缩至1/11长度，还能精准检索。
Structured Distillation for Personalized Agent Memory: 11x Token Reduction with Retrieval Preservation
- 用四字段结构化压缩每段对话，平均仅38词
- 4182次对话压缩后仍保持96%检索效果
- 适合需要长期记忆的AI助手开发者
长对话会积累大量历史数据，直接保存成本高。本文研究个性化代理记忆：将单个用户的对话历史压缩为可检索的紧凑层。每段对话被转化为包含四个字段的复合对象（exchange_core, specific_context, thematic_room_assignments, regex-extracted files_touched）。压缩后的可搜索文本平均每条38词。在6个软件工程项目的4,182次对话（共14,340次交互）上应用，平均每条对话长度从371词降至38词，实现11倍压缩。通过201个召回查询、107种配置（5种纯模式和5种跨层模式）、5个LLM评分器（共214,519对共识评分），评估压缩后的召回能力。最佳纯压缩配置达到基准原始文本MRR的96%（0.717 vs 0.745）。所有向量搜索配置经邦弗朗尼校正后均不显著，而所有BM25配置显著退化（效应量|d|=0.031-0.756）。最佳跨层方案略超最优原始基线（MRR 0.759）。结构化蒸馏在降低1/11上下文开销的同时，保留了有效检索能力。数千条交互可纳入单个提示，原始数据仍可用于深入分析。代码与分析流程已开源。
原文摘要 · Abstract (English)
Long conversations with an AI agent create a simple problem for one user: the history is useful, but carrying it verbatim is expensive. We study personalized agent memory: one user's conversation history with an agent, distilled into a compact retrieval layer for later search. Each exchange is compressed into a compound object with four fields (exchange_core, specific_context, thematic room_assignments, and regex-extracted files_touched). The searchable distilled text averages 38 tokens per exchange. Applied to 4,182 conversations (14,340 exchanges) from 6 software engineering projects, the method reduces average exchange length from 371 to 38 tokens, yielding 11x compression. We evaluate whether personalized recall survives that compression using 201 recall-oriented queries, 107 configurations spanning 5 pure and 5 cross-layer search modes, and 5 LLM graders (214,519 consensus-graded query-result pairs). The best pure distilled configuration reaches 96% of the best verbatim MRR (0.717 vs 0.745). Results are mechanism-dependent. All 20 vector search configurations remain non-significant after Bonferroni correction, while all 20 BM25 configurations degrade significantly (effect sizes |d|=0.031-0.756). The best cross-layer setup slightly exceeds the best pure verbatim baseline (MRR 0.759). Structured distillation compresses single-user agent memory without uniformly sacrificing retrieval quality. At 1/11 the context cost, thousands of exchanges fit within a single prompt while the verbatim source remains available for drill-down. We release the implementation and analysis pipeline as open-source software.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。