让AI协作系统记住有用信息，自动丢弃无用对话，提升任务完成率。
Shared Selective Persistent Memory for Agentic LLM Systems
- 只保留任务配置、数据结构等可复用信息，丢弃具体推理过程。
- 任务完成率达96%，比不存记忆高17个百分点，比全量保存高25个百分点。
- 适合需要持续协作的开发、数据分析场景，支持跨用户共享记忆。
通过多轮工具调用生成代码的智能体系统面临根本性上下文问题：每次会话从零开始，先前会话中积累的配置选择、领域约束、数据模式和工具使用模式被丢弃。简单持久化完整对话历史既浪费token又降低生成质量。本文提出共享选择性持久记忆架构，识别并保留四类可复用上下文（任务规范、数据模式、工具配置、输出约束），同时丢弃会话特异性的推理痕迹。关键在于该记忆可共享：封装了选择性记忆的工作区可通过基于角色的访问控制在用户间转移，实现协作复用而不重复设定。我们在一个已部署的协作工作平台中实现该机制，让大模型代理从异构数据源（CSV、SQL、REST API、MCP服务器）生成、编辑并维护版本化的成果（仪表盘、报告、数据驱动文档）。配套的零token数据刷新机制将生成程序与运行时数据解耦，实现成果复用无需重新调用。在三个企业场景中，共享选择性持久记忆使任务完成率达到96%（无记忆为79%，全历史为71%）。零token刷新消除重复更新对LLM的调用需求（任务时间减少14倍），摘要生成方式使单次调用的token开销相比直接注入原始数据降低97倍。在四个公开数据集上的复现验证了通用性，零token刷新在12次试验中全部成功。值得注意的是，简单全历史持久化反而因引入过时痕迹而降低完成率，而选择性记忆表现优于两者。
原文摘要 · Abstract (English)
Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive. Naively persisting entire conversation histories is token-inefficient and counterproductive: irrelevant context degrades generation quality. We introduce shared selective persistent memory, an architecture that identifies and retains four categories of reusable context (task specifications, data schemas, tool configurations, and output constraints) while discarding session-specific reasoning traces. Crucially, this memory is shared: workspaces encapsulating selective memory can be transferred across users with role-based access control, enabling collaborative reuse without redundant specification. We implement it in a deployed collaborative workspace platform where LLM agents produce, edit, and maintain git-versioned artifacts (dashboards, reports, and data-driven documents) from heterogeneous sources (CSV, SQL, REST APIs, and MCP servers). A complementary zero-token data refresh mechanism decouples generated programs from runtime data, enabling artifact reuse without re-invocation. Across three enterprise scenarios, shared selective persistent memory achieves 96% task completion (vs. 79% without memory and 71% with full history). Zero-token refresh eliminates LLM re-invocation for recurring updates (14x task-time reduction), while summary-driven generation cuts per-invocation token cost by 97x versus raw data injection. A replication on four public datasets confirms generalizability, with zero-token refresh succeeding in 12/12 trials. Notably, naive full-history persistence actively degrades completion by biasing the agent with stale traces, while selective memory outperforms both extremes.
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。