Skip to content
Preprint

SEPM: Self-Evolving Procedural Memory Grounded in Task Graphs for Multi-Agent Collaboration

Oct 2026 · 0 citations · 26 references
Computer Science

TL;DR

Self-Evolving Procedural Memory (SEPM), a framework that uses task dependency graphs as a common representation for online coordination and procedural memory evolution, is proposed, which achieves the highest task scores among the compared methods in all six benchmark settings.

Abstract

Long-horizon multi-agent collaboration requires memory that preserves both successful actions and the coordination structure underlying them. Existing memory systems support information sharing or procedural reuse, but often leave the evolution of shared procedures disconnected from the task dependencies and execution states of collaborating agents. This coupling also limits the direct transfer of procedural memory designed for individual agents to team settings. We propose Self-Evolving Procedural Memory (SEPM), a framework that uses task dependency graphs as a common representation for online coordination and procedural memory evolution. During execution, a lightweight shared blackboard records structured evidence alongside task dependencies, supporting the detection of goal, plan, and world-state divergence and evidence-based realignment. After execution, verified actions and dependencies are distilled into reusable procedures, while recurring failures inform warnings and constraints. The shared procedure pool evolves through creation, refinement, specialization, and retirement, guided by success and cost utility and constrained by evidence and safety requirements. Together, these mechanisms preserve the collaborative structure and applicability conditions needed to reuse experience across tasks. Evaluations on ALFWorld, WebArena, and OfficeBench under AutoGen and DyLAN show that SEPM achieves the highest task scores among the compared methods in all six benchmark settings. Under AutoGen, it improves task scores over the no-added-memory baseline by 29.85, 25.86, and 13.00 percentage points, respectively. The codebase is available at https://github.com/cookieApril/SEPM.

View source

Similar papers

#artificial intelligence Preprint Sep 2026

Topological Coherence for Self-evolving Multi-agent Systems

This work introduces TOCOMAS, a Topology-Coherent Multi-Agent System, a Topology-Coherent Multi-Agent System that improves task success over baselines across backbones and shows gains over the self-evolving baseline in verified progress, handoffs, and memory isolation.

Sen Zhao, Rui-Qi Kong, Zuyu Zhang et al. · 0 citations
#artificial intelligence Review Oct 2026

Interlock: From Local Correctness to Task Completion in Long-Horizon Agents

Large language model agents increasingly undertake long-horizon tasks in complex environments characterized by fragmented evidence, partially completed states, and dependencies across resources and artifacts, and Interlock, a framework for task synthesis that represents each task as a typed completion graph is proposed...

Lin-Ji Hao, Yan-Ji He, Zi-Han Wang et al. · 0 citations
Preprint Oct 2026

InstAgent: A Recursively Self-Improving Agent Operating System for Heterogeneous Robot Collaboration

Heterogeneous robot teams enable complex, long-horizon tasks by combining complementary sensing, mobility, and manipulation capabilities across multiple embodiments. Yet existing systems struggle to retain execution-time corrections as reusable experience, maintain task-relevant context memory across space and time for...

Hao-Yang Luo, J. Qin, Jin-Yan Cao et al. · 1 citation
#artificial intelligence Preprint Sep 2026

Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

The Procedural Graph is introduced: just as a knowledge graph organizes factual knowledge into (entity, relation, entity) triplets for what-is questions, a Procedural Graph organizes procedural knowledge into (procedure, relation, procedure) triplets for what-to-do questions.

Yu-Xing Lu, Yi-Cheng Chen, Shan-Chan Wu et al. · 1 citation
#artificial intelligence Preprint Oct 2026

AgentEvolver: System-Wide Self-Evolution Through Task Execution

This work presents AgentEvolver, a system for developing capabilities during task execution while keeping the foundation model fixed, and evaluates task outcomes on SWE-bench Pro Public and examines capability changes in six application cases.

Wen-Tao Zhang, Fu-Chao Yang, Yi-Lei Zhao et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.