Skip to content

MACE: Memory-Agent Co-Evolution with Adaptive Memory Graphs for Multi-Agent Systems

Sep 2026 · 0 citations · 11 references
Computer Science

TL;DR

MACE Loop is a memory-agent co-evolution framework that adapts memory organization and agent memory use through execution feedback that outperforms ten baselines with an average score of 81.11%, compared with 78.97% for the strongest baseline, SAGE.

Abstract

LLM-based multi-agent systems generate collaboration traces that record how agents plan tasks, verify intermediate results, and repair failures. Reusing these procedures requires preserving an action's prerequisites and the outputs needed by subsequent agents. Our empirical studies show that grouping these dependencies into functional memory units improves their retention, while connecting units increases retrieval of the units and links jointly required by a task. The preferred combination of units also changes between instructions and checklists, even when each combination's content is fixed across formats. Updating choices from the outcomes of each combination and format pairing outperforms scoring combinations and formats separately. These findings motivate MACE, a memory-agent co-evolution framework that adapts memory organization and agent memory use through execution feedback. Its MemGoG structure represents functional units as subgraphs of related conditions, actions, and outputs, connecting them through support, conflict, and repair relations. MACE Loop selects task-relevant units and relations within a memory budget and provides each agent with instructions or checklists for its current operation. It records the selected units, presentation formats, agent outputs, and task outcomes to update unit scores and relations for retrieval and inform subsequent presentation choices. Across eight benchmarks, MACE outperforms ten baselines with an average score of 81.11%, compared with 78.97% for the strongest baseline, SAGE.

View source

Similar papers

OpenMAS-GCom. A Diagnostic Benchmark for Graph-enhanced Multi-Agent Systems

OpenMAS-GCom is introduced, a benchmark for diagnosing how these components affect G-MAS performance through controlled interventions, and 400 G-MAS-Complex tasks requiring agents to combine information from multiple documents, resolve conflicting records, and return specified values with source identifiers are added.

Kai-Rui Yang, Xun-Kai Li, Kai-Xiang Zhang et al. · 0 citations
#artificial intelligence Preprint Sep 2026

MASkills: Continual Skills Optimization for Multi-Agent LLM Systems

MASkills presents a new agent-optimization pipeline that integrates skill-conditioned credit assignment, hierarchical credit aggregation, and momentum-smoothed optimization, enabling agent skill libraries to evolve through refinement, induction, consolidation, and pruning.

Huai-Yuan Yao, Xia-Oou Liu, Charles Fleming et al. · 2 citations · ⚡1
#artificial intelligence Preprint Aug 2026

Learning What to Retain: Gated-Memory Routing for Efficient Collaboration in Multi-Agent LLM Systems

Gated-Memory Routing is proposed, which conditions each decision on the query and a learned execution memory, and attains the best average accuracy, exceeding the strongest baseline by 2.44 points, while reducing HumanEval inference cost by 31.9% relative to that baseline.

Rakibul Hasan Rajib, Meng Zheng, Qian Lou · 3 citations

RoboFoundry: System-as-Policy Evolution for Self-Learning Embodied Agents

RoboFoundry is proposed, the first embodied agentic framework that formulates this process of system-as-policy evolution across foundation models as Self-Evolving System-as-Policy, highlighting its potential for fully autonomous embodied agents.

Jing-Song Liang, Shu-Hao Liao, Shi-Zhe Zhang et al. · 5 citations · ⚡2
Preprint Sep 2026

EpiCon: Collective Agent Learning through Co-Evolving Multimodal Memory

EpiCon, a shared multimodal memory framework for agent collective learning without updating host model parameters, links question-level memory evolution to a persistent experience bank through two independently trained 2B models: a memory controller and a tree self-organizer.

Ziyun Zeng, Hang Hua, S. Alshammari et al. · 1 citation

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

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