We introduce Σ-Mem, a persistent online reliability memory for LLM-based multi-agent systems. Instead of memorizing interaction content, Σ-Mem continuously learns which peers are reliable under different conditions from correctness feedback, enabling adaptive routing, voting, and model steering without retraining. Experiments across multiple Qwen-family agents show improved robustness under reliability shifts and strong generalization to unseen peers and domains.<br><a href=\"https://cdn-uploads.huggingface.co/production/uploads/66dee1c3c788a0ecfa63dd21/uQ9nG8ME6fZhYAgq_Lvku.png\" rel=\"nofollow\"><img src=\"https://cdn-uploads.huggingface.co/production/uploads/66dee1c3c788a0ecfa63dd21/uQ9nG8ME6fZhYAgq_Lvku.png\" alt=\"Introduction\"></a></p>\n","updatedAt":"2026-07-31T09:53:07.282Z","author":{"_id":"66dee1c3c788a0ecfa63dd21","avatarUrl":"/avatars/9483c8350b529aa223d1a55fd0baadd9.svg","fullname":"Suorong Yang","name":"Jackbrocp","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8177376389503479},"editors":["Jackbrocp"],"editorAvatarUrls":["/avatars/9483c8350b529aa223d1a55fd0baadd9.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2607.27958","authors":[{"_id":"6a6c0f17202e2d9e3ffdb718","name":"Peilin Feng","hidden":false},{"_id":"6a6c0f17202e2d9e3ffdb719","user":{"_id":"66dee1c3c788a0ecfa63dd21","avatarUrl":"/avatars/9483c8350b529aa223d1a55fd0baadd9.svg","isPro":false,"fullname":"Suorong Yang","user":"Jackbrocp","type":"user","name":"Jackbrocp"},"name":"Suorong Yang","status":"claimed_verified","statusLastChangedAt":"2026-07-31T08:45:05.542Z","hidden":false},{"_id":"6a6c0f17202e2d9e3ffdb71a","name":"Soujanya Poria","hidden":false}],"publishedAt":"2026-07-30T00:00:00.000Z","submittedOnDailyAt":"2026-07-31T00:00:00.000Z","title":"Σ-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems","submittedOnDailyBy":{"_id":"66dee1c3c788a0ecfa63dd21","avatarUrl":"/avatars/9483c8350b529aa223d1a55fd0baadd9.svg","isPro":false,"fullname":"Suorong Yang","user":"Jackbrocp","type":"user","name":"Jackbrocp"},"summary":"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.","upvotes":1,"discussionId":"6a6c0f17202e2d9e3ffdb71b","organization":{"_id":"6508b28cf36bb51c50faad98","name":"NanyangTechnologicalUniversity","fullname":"Nanyang Technological University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/630ca0817dacb93b33506ce7/ZPD1fvei0bcIGeDXxeSkn.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"66dee1c3c788a0ecfa63dd21","avatarUrl":"/avatars/9483c8350b529aa223d1a55fd0baadd9.svg","isPro":false,"fullname":"Suorong Yang","user":"Jackbrocp","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"6508b28cf36bb51c50faad98","name":"NanyangTechnologicalUniversity","fullname":"Nanyang Technological University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/630ca0817dacb93b33506ce7/ZPD1fvei0bcIGeDXxeSkn.png"},"query":{}}">
Σ-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems
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.
Community
We introduce Σ-Mem, a persistent online reliability memory for LLM-based multi-agent systems. Instead of memorizing interaction content, Σ-Mem continuously learns which peers are reliable under different conditions from correctness feedback, enabling adaptive routing, voting, and model steering without retraining. Experiments across multiple Qwen-family agents show improved robustness under reliability shifts and strong generalization to unseen peers and domains.
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2607.27958 in a model README.md to link it from this page.
Cite arxiv.org/abs/2607.27958 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2607.27958 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.