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

• URL: http://arxiv.org/abs/2607.27958v1
• Date: Thu, 30 Jul 2026 10:05:50 GMT
• Title: $Σ$-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems
• Abstract summary: Existing memory systems preserve interaction content rather than modeling which agents can be trusted and under what conditions.<n>We introduce $$-Mem, an online reliability memory that records historical competence evidence for individual peers and peer relationship evidence across the peer set.<n>$$-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.
• Score: 37.51924580838879
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Post-Calibration Reliability Reranking of Relevance Decisions via Label-wise Monotone Projection [35.67041829703622]
  Web search, product search, and question-answering retrieval systems often assign a relevance label and confidence score to each query-candidate pair.<n>Post-hoc calibration is needed because misaligned confidence can make systems over-trust wrong predictions or unnecessarily defer correct ones.<n>We address this gap with Label-wise Monotone Reliability Projection (MRP), which learns label-wise monotone functions that map calibrated confidence to correctness reliability.
  arXiv  Detail & Related papers  (2026-08-11T02:51:35Z)
• Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory [50.857546269660276]
  We introduce SeqMem-Eval, a diagnostic evaluation framework for sequentially evolving large language models (LLMs) memory.<n>Rather than focusing only on final performance, SeqMem-Eval evaluates how memory states evolve, generalize, consolidate experience, and retain useful information during sequential inference.
  arXiv  Detail & Related papers  (2026-05-14T20:15:22Z)
• EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium [10.71445877501096]
  Multi-agent debate (MAD) systems increasingly rely on shared memory to support long-horizon reasoning.<n>A single corrupted entry can contaminate the downstream memory-augmented reasoning, and debate alone fails to filter such errors.<n>We propose EquiMem, an inference-time calibration mechanism that quantifies each update algorithmically against the shared memory state.
  arXiv  Detail & Related papers  (2026-05-10T03:04:12Z)
• Confidence-Aware Alignment Makes Reasoning LLMs More Reliable [65.44962502963378]
  We introduce CASPO, a framework that aligns token-level confidence with step-wise logical correctness without training a separate reward model.<n>During inference, we propose Confidence-aware Thought (CaT), which dynamically prunes uncertain reasoning branches with negligible O(V) latency.<n>Experiments across ten benchmarks and multiple model families show that CASPO consistently improves reasoning reliability and inference efficiency.
  arXiv  Detail & Related papers  (2026-05-08T07:08:25Z)
• Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration [72.0672328514289]
  Multimodal learning often grapples with the challenge of low-quality data.<n>We propose a unified framework, termed Conformal Predictive Self-Calibration.<n>Our framework consistently outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-05T14:48:52Z)
• Process Supervision of Confidence Margin for Calibrated LLM Reasoning [52.373121066425455]
  Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability.<n>Yet, outcome-based reward often incentivizes models to be overconfident, leading to hallucinations, unreliable confidence-based control, and unnecessary compute allocation.<n>We introduce Reinforcement Learning with Confidence Margin (textbfRLCM), a calibration-aware RL framework that jointly optimize correctness and confidence reliability.
  arXiv  Detail & Related papers  (2026-04-25T14:40:13Z)
• The Model Agreed, But Didn't Learn: Diagnosing Surface Compliance in Large Language Models [12.743453676247903]
  Large Language Models (LLMs) internalize vast world knowledge as parametric memory, yet inevitably inherit the staleness and errors of their source corpora.<n> Knowledge editing offers a pivotal paradigm for surgically modifying memory without retraining.<n>We introduce a diagnostic framework that subjects models to discriminative self-assessment under in-context learning settings.
  arXiv  Detail & Related papers  (2026-04-07T15:20:41Z)
• Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems [94.9141394384021]
  Individual agents in multi-agent systems often lack robustness, tending to blindly conform to misleading peers.<n>We show this weakness stems from both sycophancy and inadequate ability to evaluate peer reliability.<n>We first formalize the learning problem of history-aware reference, introducing the historical interactions of peers as additional input.<n>We then develop Epistemic Context Learning (ECL), a reasoning framework that conditions predictions on explicitly-built peer profiles from history.
  arXiv  Detail & Related papers  (2026-01-29T13:59:32Z)
• DP-EMAR: A Differentially Private Framework for Autonomous Model Weight Repair in Federated IoT Systems [0.0]
  Federated Learning (FL) enables decentralized model training without sharing raw data.<n>In multi tier Federated IoT (Fed-IoT) systems, unstable connectivity and adversarial interference can silently alter transmitted parameters.<n>We propose DP-EMAR, a differentially private, error model based autonomous repair framework that detects and reconstructs transmission induced distortions.
  arXiv  Detail & Related papers  (2025-12-15T15:56:58Z)
• SEDM: Scalable Self-Evolving Distributed Memory for Agents [23.182291416527764]
  SEDM is a verifiable and adaptive framework that transforms memory from a passive repository into an active, self-optimizing component.<n>We show that SEDM improves reasoning accuracy while reducing token overhead compared with strong memory baselines.<n>Results highlight SEDM as a scalable and sustainable memory mechanism for open-ended multi-agent collaboration.
  arXiv  Detail & Related papers  (2025-09-11T14:37:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.