https://github.com/AIGeeksGroup/MMA

\n","updatedAt":"2026-02-19T03:18:16.420Z","author":{"_id":"64ec877bb93654d4ca5c92e9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64ec877bb93654d4ca5c92e9/GvHk_KSdE9Rhnk_o-NaZX.jpeg","fullname":"Zeyu Zhang","name":"SteveZeyuZhang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7996612191200256},"editors":["SteveZeyuZhang"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/64ec877bb93654d4ca5c92e9/GvHk_KSdE9Rhnk_o-NaZX.jpeg"],"reactions":[],"isReport":false}},{"id":"6997bb63f0b5adaaf027ded2","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false},"createdAt":"2026-02-20T01:39:47.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [BMAM: Brain-inspired Multi-Agent Memory Framework](https://huggingface.co/papers/2601.20465) (2026)\n* [SYNAPSE: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activation](https://huggingface.co/papers/2601.02744) (2026)\n* [HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents](https://huggingface.co/papers/2601.06377) (2026)\n* [MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents](https://huggingface.co/papers/2601.03236) (2026)\n* [KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions](https://huggingface.co/papers/2601.04745) (2026)\n* [PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Multimodal Agents](https://huggingface.co/papers/2602.00415) (2026)\n* [AMA: Adaptive Memory via Multi-Agent Collaboration](https://huggingface.co/papers/2601.20352) (2026)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2026-02-20T01:39:47.767Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.713767945766449},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2602.16493","authors":[{"_id":"69967f361268a6b79e0d02e4","name":"Yihao Lu","hidden":false},{"_id":"69967f361268a6b79e0d02e5","name":"Wanru Cheng","hidden":false},{"_id":"69967f361268a6b79e0d02e6","name":"Zeyu Zhang","hidden":false},{"_id":"69967f361268a6b79e0d02e7","name":"Hao Tang","hidden":false}],"publishedAt":"2026-02-18T14:30:35.000Z","submittedOnDailyAt":"2026-02-19T00:48:16.410Z","title":"MMA: Multimodal Memory Agent","submittedOnDailyBy":{"_id":"64ec877bb93654d4ca5c92e9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64ec877bb93654d4ca5c92e9/GvHk_KSdE9Rhnk_o-NaZX.jpeg","isPro":false,"fullname":"Zeyu Zhang","user":"SteveZeyuZhang","type":"user"},"summary":"Long-horizon multimodal agents depend on external memory; however, similarity-based retrieval often surfaces stale, low-credibility, or conflicting items, which can trigger overconfident errors. We propose Multimodal Memory Agent (MMA), which assigns each retrieved memory item a dynamic reliability score by combining source credibility, temporal decay, and conflict-aware network consensus, and uses this signal to reweight evidence and abstain when support is insufficient. We also introduce MMA-Bench, a programmatically generated benchmark for belief dynamics with controlled speaker reliability and structured text-vision contradictions. Using this framework, we uncover the \"Visual Placebo Effect\", revealing how RAG-based agents inherit latent visual biases from foundation models. On FEVER, MMA matches baseline accuracy while reducing variance by 35.2% and improving selective utility; on LoCoMo, a safety-oriented configuration improves actionable accuracy and reduces wrong answers; on MMA-Bench, MMA reaches 41.18% Type-B accuracy in Vision mode, while the baseline collapses to 0.0% under the same protocol. Code: https://github.com/AIGeeksGroup/MMA.","upvotes":5,"discussionId":"69967f371268a6b79e0d02e8","githubRepo":"https://github.com/AIGeeksGroup/MMA","githubRepoAddedBy":"user","ai_summary":"Multimodal Memory Agent (MMA) improves long-horizon agent performance by dynamically scoring memory reliability and handling visual biases in retrieval-augmented systems.","ai_keywords":["multimodal agents","external memory","similarity-based retrieval","reliability scoring","source credibility","temporal decay","conflict-aware network consensus","evidence reweighting","belief dynamics","RAG-based agents","visual placebo effect","retrieval-augmented generation","MMA-Bench","Type-B accuracy"],"githubStars":5,"organization":{"_id":"61dcd8e344f59573371b5cb6","name":"PekingUniversity","fullname":"Peking University","avatar":"https://cdn-uploads.huggingface.co/production/uploads/noauth/vavgrBsnkSejriUF4lXDE.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"66935bdc5489e4f73c76bc7b","avatarUrl":"/avatars/129d1e86bbaf764b507501f4feb177db.svg","isPro":false,"fullname":"Abidoye Aanuoluwapo","user":"Aanuoluwapo65","type":"user"},{"_id":"6270324ebecab9e2dcf245de","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6270324ebecab9e2dcf245de/cMbtWSasyNlYc9hvsEEzt.jpeg","isPro":false,"fullname":"Kye Gomez","user":"kye","type":"user"},{"_id":"69234f5207820287f17451b3","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/rz9KC4VJ47VR9q0yVagBx.png","isPro":false,"fullname":"Stephen Moore","user":"shootstuff","type":"user"},{"_id":"684d57f26e04c265777ead3f","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/cuOj-bQqukSZreXgUJlfm.png","isPro":false,"fullname":"Joakim Lee","user":"Reinforcement4All","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0,"organization":{"_id":"61dcd8e344f59573371b5cb6","name":"PekingUniversity","fullname":"Peking University","avatar":"https://cdn-uploads.huggingface.co/production/uploads/noauth/vavgrBsnkSejriUF4lXDE.png"}}">

Papers

arxiv:2602.16493

MMA: Multimodal Memory Agent

Published on Feb 18

· Submitted by

Zeyu Zhang on Feb 19

Peking University

Upvote

Authors:

Abstract

Multimodal Memory Agent (MMA) improves long-horizon agent performance by dynamically scoring memory reliability and handling visual biases in retrieval-augmented systems.

AI-generated summary

Long-horizon multimodal agents depend on external memory; however, similarity-based retrieval often surfaces stale, low-credibility, or conflicting items, which can trigger overconfident errors. We propose Multimodal Memory Agent (MMA), which assigns each retrieved memory item a dynamic reliability score by combining source credibility, temporal decay, and conflict-aware network consensus, and uses this signal to reweight evidence and abstain when support is insufficient. We also introduce MMA-Bench, a programmatically generated benchmark for belief dynamics with controlled speaker reliability and structured text-vision contradictions. Using this framework, we uncover the "Visual Placebo Effect", revealing how RAG-based agents inherit latent visual biases from foundation models. On FEVER, MMA matches baseline accuracy while reducing variance by 35.2% and improving selective utility; on LoCoMo, a safety-oriented configuration improves actionable accuracy and reduces wrong answers; on MMA-Bench, MMA reaches 41.18% Type-B accuracy in Vision mode, while the baseline collapses to 0.0% under the same protocol. Code: https://github.com/AIGeeksGroup/MMA.