cs.AINov 15, 2026

A Matrix with Steps: An Episodic and Procedural Memory Method for Tool-Using Agents and Robots

Authors: Jürgen Paulhart, Peter Schüller

Organizations: [core] Informationstechnologie / Eldric · NeuraMix AI GmbH and Technische Universität Wien · NeuraMix AI GmbH · Technische Universität Wien

Abstract

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%96\% of its tasks as done and solved 35%35\%; with external verification it solved 7979%. In a store of 100000100000 synthetic episodes (457457MB 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 1616ms on a laptop and 4040ms on a server node (median). Task outcomes were measured up to about 1000010000 confirmed records, where the exact records solved every revisit at the first attempt.

Figures & tables

Explore similar work

CardsList
  1. ReSight: Task-Driven Self-Improving Memory for Embodied Agents

    Oct 24, 2026Lirong Che, Yang Chen, Yimeng Su +8Long-Term Memory for Embodied AgentsRobotic Spatial Memory

  2. Delivered, Not Used: Evaluating Agent Memory at Its Point of Use

    Nov 1, 2026Changran Xu, Zeju Li, Qiang XuAgent MemoryLLM Agent Evaluation

  3. MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedback

    Jun 6, 2026Suleyman Armagan Er, Danilo Ribeiro, Yogesh Virkar +5Tool-Using AgentsLLM Tool Use