A Latency optimized parallel write Agent Memory System.</p>\n","updatedAt":"2026-05-26T05:42:50.930Z","author":{"_id":"6399c67bf78f75ae73146760","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6399c67bf78f75ae73146760/LAZxoSRD-hte-S9736iyg.jpeg","fullname":"CHEN Han","name":"Concyclics","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6094540953636169},"editors":["Concyclics"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/6399c67bf78f75ae73146760/LAZxoSRD-hte-S9736iyg.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.23986","authors":[{"_id":"6a15321bb57a1823d5708bb4","user":{"_id":"6399c67bf78f75ae73146760","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6399c67bf78f75ae73146760/LAZxoSRD-hte-S9736iyg.jpeg","isPro":false,"fullname":"CHEN Han","user":"Concyclics","type":"user","name":"Concyclics"},"name":"Han Chen","status":"claimed_verified","statusLastChangedAt":"2026-05-26T07:08:41.046Z","hidden":false},{"_id":"6a15321bb57a1823d5708bb5","name":"Zining Zhang","hidden":false},{"_id":"6a15321bb57a1823d5708bb6","name":"Wenqi Pei","hidden":false},{"_id":"6a15321bb57a1823d5708bb7","name":"Bingsheng He","hidden":false},{"_id":"6a15321bb57a1823d5708bb8","name":"Ming Wu","hidden":false},{"_id":"6a15321bb57a1823d5708bb9","name":"Jason Zeng","hidden":false},{"_id":"6a15321bb57a1823d5708bba","name":"Michael Heinrich","hidden":false},{"_id":"6a15321bb57a1823d5708bbb","name":"Wei Wu","hidden":false},{"_id":"6a15321bb57a1823d5708bbc","name":"Hongbao Zhang","hidden":false}],"publishedAt":"2026-05-16T00:00:00.000Z","submittedOnDailyAt":"2026-05-26T00:00:00.000Z","title":"MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing","submittedOnDailyBy":{"_id":"6399c67bf78f75ae73146760","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6399c67bf78f75ae73146760/LAZxoSRD-hte-S9736iyg.jpeg","isPro":false,"fullname":"CHEN Han","user":"Concyclics","type":"user","name":"Concyclics"},"summary":"Memory is a fundamental component for enabling long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, existing systems suffer from significant maintenance overhead due to two key limitations: coarse-grained state management and inherently sequential update pipelines. In particular, updates are often tightly coupled with LLM inference and require full-state rewrites, leading to poor scalability and growing latency as memory accumulates. To address these challenges, we present MemForest, a memory framework that reformulates agent memory as a write-efficient temporal data management problem. MemForest breaks the sequential bottleneck via parallel chunk extraction, decoupling memory construction into concurrent, independent operations. To further eliminate coarse-grained maintenance, we introduce MemTree, a hierarchical temporal index that organizes memory as time-ordered trees rather than flat global summaries. This design replaces full-state rewrites with localized per-node updates, reducing maintenance cost to the affected tree paths while naturally preserving temporally evolving states. We evaluate MemForest on two long-context memory benchmarks, LongMemEval-S and LoCoMo. On LongMemEval-S, MemForest achieves the best overall performance among stateful baselines, reaching 79.8% pass@1 accuracy while sustaining a memory construction throughput approximately 6x higher than state-of-the-art approaches including EverMemOS.","upvotes":4,"discussionId":"6a15321bb57a1823d5708bbd","githubRepo":"https://github.com/Concyclics/MemForest","githubRepoAddedBy":"user","ai_summary":"MemForest presents a memory framework for long-context LLM agents that improves scalability and reduces latency through parallel chunk extraction and hierarchical temporal indexing.","ai_keywords":["memory framework","long-context LLM agents","temporal data management","parallel chunk extraction","MemTree","hierarchical temporal index","full-state rewrites","localized per-node updates"],"githubStars":5},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6399c67bf78f75ae73146760","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6399c67bf78f75ae73146760/LAZxoSRD-hte-S9736iyg.jpeg","isPro":false,"fullname":"CHEN Han","user":"Concyclics","type":"user"},{"_id":"6a1544af74783caf16505978","avatarUrl":"/avatars/e996454afd29ba08c81f3fd827f22481.svg","isPro":false,"fullname":"Pricecheng","user":"Pricecheng","type":"user"},{"_id":"6356bf52e983d3c51d212205","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1666629451430-noauth.jpeg","isPro":false,"fullname":"Yiqi Zhang","user":"Viscent","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.23986.md"}">
MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
Abstract
MemForest presents a memory framework for long-context LLM agents that improves scalability and reduces latency through parallel chunk extraction and hierarchical temporal indexing.
AI-generated summary
Memory is a fundamental component for enabling long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, existing systems suffer from significant maintenance overhead due to two key limitations: coarse-grained state management and inherently sequential update pipelines. In particular, updates are often tightly coupled with LLM inference and require full-state rewrites, leading to poor scalability and growing latency as memory accumulates. To address these challenges, we present MemForest, a memory framework that reformulates agent memory as a write-efficient temporal data management problem. MemForest breaks the sequential bottleneck via parallel chunk extraction, decoupling memory construction into concurrent, independent operations. To further eliminate coarse-grained maintenance, we introduce MemTree, a hierarchical temporal index that organizes memory as time-ordered trees rather than flat global summaries. This design replaces full-state rewrites with localized per-node updates, reducing maintenance cost to the affected tree paths while naturally preserving temporally evolving states. We evaluate MemForest on two long-context memory benchmarks, LongMemEval-S and LoCoMo. On LongMemEval-S, MemForest achieves the best overall performance among stateful baselines, reaching 79.8% pass@1 accuracy while sustaining a memory construction throughput approximately 6x higher than state-of-the-art approaches including EverMemOS.
Community
A Latency optimized parallel write Agent Memory System.
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/2605.23986 in a model README.md to link it from this page.
Cite arxiv.org/abs/2605.23986 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2605.23986 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.