Σ-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems

Hugging Face Daily Papers Papers
multi-agent-systems memory llm reliability online-adaptation arxiv

Summary

The paper introduces Σ-Mem, an online reliability memory for LLM-based multi-agent systems that tracks historical competence of peers and peer relationships, enabling stable adaptation via spectral bounds and improving coordination through residual steering, routing, and weighted voting.

Memory is central to long-horizon LLM agents, yet existing memory systems primarily preserve interaction content rather than modeling which agents can be trusted and under what conditions. This limitation is particularly important in multi-agent systems, where a central model may be unable to directly verify plausible or correlated peer responses. We introduce Σ-Mem, an online reliability memory that records historical competence evidence for individual peers and peer relationship evidence across the peer set. Both forms of evidence are maintained as real symmetric states and updated from post-decision correctness feedback. By Weyl's inequality, the spectral change caused by each event-level update is bounded, enabling stable online adaptation without retraining the underlying models. Σ-Mem provides a general write-and-read interface: the same memory can be used for residual steering of a central model, response-free peer routing, or reliability-weighted voting. Across five Qwen-family models, Σ-Mem adapts to counterfactual reliability shifts and generalizes to unseen peers and task domains. Direct memory readouts also outperform majority voting and the best fixed peer over the full OOD evaluation set. Moreover, performance improves consistently as more correctness feedback becomes available, indicating that Σ-Mem progressively accumulates actionable reliability information. These results establish reliability memory as a reusable foundation for adaptive coordination in LLM-based multi-agent systems.
Original Article
View Cached Full Text

Cached at: 07/31/26, 09:53 AM

Paper page - Σ-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems

Source: https://huggingface.co/papers/2607.27958

Abstract

Memoryiscentraltolong-horizonLLMagents,yetexistingmemorysystemsprimarilypreserveinteractioncontentratherthanmodelingwhichagentscanbetrustedandunderwhatconditions.Thislimitationisparticularlyimportantinmulti-agentsystems,whereacentralmodelmaybeunabletodirectlyverifyplausibleorcorrelatedpeerresponses.WeintroduceΣ-Mem,anonlinereliabilitymemorythatrecordshistoricalcompetenceevidenceforindividualpeersandpeerrelationshipevidenceacrossthepeerset.Bothformsofevidencearemaintainedasrealsymmetricstatesandupdatedfrompost-decisioncorrectnessfeedback.ByWeyl’sinequality,thespectralchangecausedbyeachevent-levelupdateisbounded,enablingstableonlineadaptationwithoutretrainingtheunderlyingmodels.Σ-Memprovidesageneralwrite-and-readinterface:thesamememorycanbeusedforresidualsteeringofacentralmodel,response-freepeerrouting,orreliability-weightedvoting.AcrossfiveQwen-familymodels,Σ-Memadaptstocounterfactualreliabilityshiftsandgeneralizestounseenpeersandtaskdomains.DirectmemoryreadoutsalsooutperformmajorityvotingandthebestfixedpeeroverthefullOODevaluationset.Moreover,performanceimprovesconsistentlyasmorecorrectnessfeedbackbecomesavailable,indicatingthatΣ-Memprogressivelyaccumulatesactionablereliabilityinformation.TheseresultsestablishreliabilitymemoryasareusablefoundationforadaptivecoordinationinLLM-basedmulti-agentsystems.

View arXiv pageView PDFAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.27958 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.27958 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.27958 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Governed Shared Memory for Multi-Agent LLM Systems

arXiv cs.AI

This paper introduces MemClaw, a governed shared memory architecture for multi-agent LLM systems, formalizing failure modes like unauthorized leakage and stale propagation, and evaluating the system via the ArgusFleet harness.

AdMem: Advanced Memory for Task-solving Agents

arXiv cs.AI

This paper introduces AdMem, a unified memory framework for LLM-based agents that integrates semantic, episodic, and procedural memory with a bi-level short-term and long-term store, using a multi-agent architecture for automatic memory generation and adaptive retrieval. Experiments show improved robustness and success on long multi-turn tasks.

SimpleMem: Efficient Lifelong Memory for LLM Agents

Papers with Code Trending

Introduces SimpleMem, an efficient memory framework for LLM agents that uses semantic lossless compression to improve accuracy and reduce token consumption, achieving 26.4% F1 improvement and up to 30x reduction in inference-time token usage.