{"id":7317,"date":"2025-08-18T10:34:00","date_gmt":"2025-08-18T01:34:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=7317"},"modified":"2025-08-17T22:37:02","modified_gmt":"2025-08-17T13:37:02","slug":"seeing-listening-remembering-and-reasoning-a-multimodal-agent-with-long-term-memory","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=7317","title":{"rendered":"Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory\u00a0<\/strong>[11.7]<br>\u672c\u7a3f\u3067\u306f,\u9577\u671f\u8a18\u61b6\u3092\u5099\u3048\u305f\u65b0\u3057\u3044\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3042\u308bM3-Agent\u3092\u7d39\u4ecb\u3059\u308b\u3002 M3-Agent\u306f\u3001\u30ea\u30a2\u30eb\u30bf\u30a4\u30e0\u306e\u8996\u899a\u304a\u3088\u3073\u8074\u899a\u5165\u529b\u3092\u51e6\u7406\u3057\u3066\u3001\u9577\u671f\u8a18\u61b6\u306e\u69cb\u7bc9\u3068\u66f4\u65b0\u3092\u884c\u3046\u3053\u3068\u304c\u3067\u304d\u308b\u3002 \u6211\u3005\u306f,M3-Bench\u3068\u3044\u3046\u9577\u30d3\u30c7\u30aa\u8cea\u554f\u5fdc\u7b54\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3092\u958b\u767a\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2508.09736v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2508.09736v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 13 Aug 2025 12:03:03 GMT)<\/li>\n\n\n\n<li>\u3053\u3061\u3089\u3082\u9577\u671f\u8a18\u61b6\u3092\u5099\u3048\u305f\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u306e\u63d0\u6848\u3002\u300cCompared to the strongest baseline, Gemini-GPT4o-Hybrid, which implements M3-Agent framework by prompting Gemini-1.5-Pro [41] for memorization and GPT-4o [15] for control, M3-Agent improves accuracy by 6.7%, 7.7%, and 5.3% on M3-Bench-robot, M3-Bench-web, and VideoMME-long, respectively. Our ablation study demonstrates the importance of semantic memory: removing it reduces accuracy by 17.1%, 19.2% and 13.1% on M3-Bench-robot, M3-Bench-web, and VideoMME-long, respectively.\u300d\u3068\u52b9\u679c\u3092\u5831\u544a\u3057\u3066\u3044\u308b\u3002<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/m3-agent.github.io\/\">Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[42,244],"class_list":["post-7317","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-autonomous-agent","tag-memory"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7317","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=7317"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7317\/revisions"}],"predecessor-version":[{"id":7318,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7317\/revisions\/7318"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7317"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7317"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7317"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}