论文提出情景与程序记忆方法:让工具型 Agent 不再重复失败
A Matrix with Steps: An Episodic and Procedural Memory Method for Tool-Using Agents and Robots
做 Agent 或机器人的工程师可以看看这篇,它给记忆系统设计了一个挺干净的架构:外部验证才算成功,矩阵负责找流程,记录负责存顺序。实验数据也扎实,10 万条 episode 查询只要 16ms,比常见向量库方案更省事。
一篇新论文描述了为生产级 Agent 平台构建的双层记忆系统:每次运行记录为一个 episode,只有外部检查、测试、工具结果或人工确认的结果才算数,模型自报的成功永远不被采信。记忆分为两部分——用 delta rule 写入的关联矩阵负责根据情境找到适用的流程,另一段有序、可寻址的步骤记录负责回答某一步之后该做什么,步骤定义为 Agent 的目标而非动作。矩阵只做查找器,顺序、成功计数和删除都放在记录中。
模拟实验显示:机器人自评成功时报告 96% 任务完成、实际解出 35%,引入外部验证后解出率升至 79%。在 100000 条合成 episode(磁盘 457MB)的存储中,最旧记录仍可被优先找到,他人记忆不会被误召回,仅由模型担保的成功从不被召回;笔记本上中位查询耗时 16ms,服务器节点 40ms。任务结果在约 10000 条确认记录时测量,精确记录让每次重访首次尝试即解决。
对做 Agent 和机器人落地的开发者来说,这套设计回应了两个常见痛点:重复已失败的操作,以及只从自认为成功的运行中学习。它把验证权和知识结构分离的思路可以直接迁移到工具调用型系统的记忆设计里。
A Matrix with Steps: An Episodic and Procedural Memory Method for Tool-Using Agents and Robots
Agents that call tools and robots that execute tasks are challenged by two shortcomings: they repeat what failed before, and they learn from runs that they only believe succeeded. We describe the construction of a memory that addresses both, built for a production agent platform. Every run is recorded as an episode, and only an outcome confirmed by an external check, a test, a tool result or a person counts; the agent's own claim never does. What is learned from episodes is kept in a memory with two parts: an associative matrix, written with the delta rule, which finds the procedure that applies to a situation; and a section of ordered, addressable step records that answers what comes after a given step, where a step is a goal of the agent, not a motion. Because the matrix sums its associations, it keeps no order and cannot return or delete a single one; it serves as the finder, and order, outcome counts and deletion live in the records. We describe how execution outcomes are stored, how episodes are recalled and used for solving tasks, and the file format that stores the memory. In simulation, a robot that judged its own success and stopped when it believed it was done reported $96\%$ of its tasks as done and solved $35\%$; with external verification it solved $79%$. In a store of $100000$ synthetic episodes ($457$MB on disk), the oldest episode was still found first, no episode from another person's memory was returned, and a success vouched for only by the model was never recalled; a lookup took $16$ms on a laptop and $40$ms on a server node (median). Task outcomes were measured up to about $10000$ confirmed records, where the exact records solved every revisit at the first attempt.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Agent, memory systems, agents, arXiv.
Source attribution: curated from arXiv cs.AI (@Jürgen Paulhart, Peter Schüller).