Hugging Face Daily Papers · August 6, 2026 · 3 min read

OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

Like Read original ↗

One Prompt. One Day. One Agent. Turning open-ended requests into long-horizon execution.</p>\n","updatedAt":"2026-08-06T02:31:25.644Z","author":{"_id":"620b3bbb0668e435407c8d0a","avatarUrl":"/avatars/e0fccbb2577d76088e09f054c35cffbc.svg","fullname":"Ningyu Zhang","name":"Ningyu","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":52,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7934088110923767},"editors":["Ningyu"],"editorAvatarUrls":["/avatars/e0fccbb2577d76088e09f054c35cffbc.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.05013","authors":[{"_id":"6a73f1aac5e410d076869aa4","user":{"_id":"684bc1be17ae31ba66171292","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/684bc1be17ae31ba66171292/LFlkU4kArMjSzIbwjXd44.jpeg","isPro":false,"fullname":"Jingsheng Zheng","user":"JohnsonZheng03","type":"user","name":"JohnsonZheng03"},"name":"Jingsheng Zheng","status":"claimed_verified","statusLastChangedAt":"2026-08-06T08:45:05.509Z","hidden":false},{"_id":"6a73f1aac5e410d076869aa5","name":"Xinyuan Fang","hidden":false},{"_id":"6a73f1aac5e410d076869aa6","name":"Jintian Zhang","hidden":false},{"_id":"6a73f1aac5e410d076869aa7","name":"Zhengke Gui","hidden":false},{"_id":"6a73f1aac5e410d076869aa8","name":"Huajun Chen","hidden":false},{"_id":"6a73f1aac5e410d076869aa9","user":{"_id":"620b3bbb0668e435407c8d0a","avatarUrl":"/avatars/e0fccbb2577d76088e09f054c35cffbc.svg","isPro":true,"fullname":"Ningyu Zhang","user":"Ningyu","type":"user","name":"Ningyu"},"name":"Ningyu Zhang","status":"claimed_verified","statusLastChangedAt":"2026-08-06T08:45:05.516Z","hidden":false}],"publishedAt":"2026-08-04T00:00:00.000Z","submittedOnDailyAt":"2026-08-06T00:00:00.000Z","title":"OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents","submittedOnDailyBy":{"_id":"620b3bbb0668e435407c8d0a","avatarUrl":"/avatars/e0fccbb2577d76088e09f054c35cffbc.svg","isPro":true,"fullname":"Ningyu Zhang","user":"Ningyu","type":"user","name":"Ningyu"},"summary":"LLM agents are increasingly applied to open-ended everyday requests that span work, study, and life. These tasks are long-horizon, cross-environment, and multimodal, forcing the agent to preserve goals and constraints across many steps while navigating heterogeneous tools and attachments. While prior work has addressed individual failure modes such as goals drift, states loss, and context overflow, whether a single harness can manage them jointly and remain effective across backends has received less study. We present OneDayAgent, a long-horizon harness for autonomous agents. OneDayAgent turns an open-ended request into a managed execution process that decomposes tasks into bounded subtasks, maintains execution memory under context pressure, and verifies and repairs the final deliverable. We evaluate OneDayAgent on AgentIF-OneDay across 104 tasks. With the GLM-5.2 backend, OneDayAgent sets a new state of the art with an overall score of 0.821. The same harness runs across five backend LLMs from three model families, indicating the harness generalizes across backends without tuning, even as different models induce distinct execution styles under the same workflow.","upvotes":23,"discussionId":"6a73f1aac5e410d076869aaa","githubRepo":"https://github.com/zjunlp/OneDayAgent","githubRepoAddedBy":"user","githubStars":2,"organization":{"_id":"620a6fcd8d5e5dfed284bc91","name":"zjunlp","fullname":"ZJUNLP","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1644851027419-620a61cba53066560e226d30.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"620b3bbb0668e435407c8d0a","avatarUrl":"/avatars/e0fccbb2577d76088e09f054c35cffbc.svg","isPro":true,"fullname":"Ningyu Zhang","user":"Ningyu","type":"user"},{"_id":"684bc1be17ae31ba66171292","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/684bc1be17ae31ba66171292/LFlkU4kArMjSzIbwjXd44.jpeg","isPro":false,"fullname":"Jingsheng Zheng","user":"JohnsonZheng03","type":"user"},{"_id":"64bf898d979949d2e2585c9a","avatarUrl":"/avatars/da77c856ec997e2b812c06272a01c8b2.svg","isPro":false,"fullname":"mengruwang","user":"mengru","type":"user"},{"_id":"6a17c715d8eef017751231f6","avatarUrl":"/avatars/5a48c70c73b21aa4a86fbaa6c442ffaf.svg","isPro":false,"fullname":"Xiaoben Lu","user":"xiaoben7","type":"user"},{"_id":"6a1443f02a9759cfbdf80a48","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6a1443f02a9759cfbdf80a48/dIoHGMzJ3U6k7VTOaBd4Y.jpeg","isPro":false,"fullname":"Haoxiong Wang","user":"WangHX2026","type":"user"},{"_id":"64d1fe7a15b26cc7f72bcd23","avatarUrl":"/avatars/7dcbd2765d6a6fa3df860e89c70fcd8c.svg","isPro":false,"fullname":"Johnson Zheng","user":"Cililla","type":"user"},{"_id":"68e7a69bb3ddb12973cff0c6","avatarUrl":"/avatars/320049931441b266c24f8b21c56574ae.svg","isPro":false,"fullname":"Zheng","user":"JingshengZheng","type":"user"},{"_id":"6964741b74c62474c54b3c74","avatarUrl":"/avatars/c888b45ebebc7e82cd6675df90d46137.svg","isPro":false,"fullname":"Guo","user":"Lotor03","type":"user"},{"_id":"66abc6da92b9eb71fe476118","avatarUrl":"/avatars/6d1618f45cc76da80335ad926ad24552.svg","isPro":false,"fullname":"xy.r","user":"ShawnRu","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"6a73f5b150f4665f34688358","avatarUrl":"/avatars/d80e7a4583e804e56a7311f4a3fac01b.svg","isPro":false,"fullname":"zhou","user":"quanjay22","type":"user"},{"_id":"650bd44ad4a0852d3c832d84","avatarUrl":"/avatars/0b586f4e705a338e36fa58e806f52845.svg","isPro":false,"fullname":"Li Tiancheng","user":"AlanLi0913","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"620a6fcd8d5e5dfed284bc91","name":"zjunlp","fullname":"ZJUNLP","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1644851027419-620a61cba53066560e226d30.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.05013.md","query":{}}">

Papers

arxiv:2608.05013

OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents

Published on Aug 4

· Submitted by

Ningyu Zhang on Aug 6

ZJUNLP

Upvote

Authors:

Jingsheng Zheng ,

Ningyu Zhang

Abstract

LLM agents are increasingly applied to open-ended everyday requests that span work, study, and life. These tasks are long-horizon, cross-environment, and multimodal, forcing the agent to preserve goals and constraints across many steps while navigating heterogeneous tools and attachments. While prior work has addressed individual failure modes such as goals drift, states loss, and context overflow, whether a single harness can manage them jointly and remain effective across backends has received less study. We present OneDayAgent, a long-horizon harness for autonomous agents. OneDayAgent turns an open-ended request into a managed execution process that decomposes tasks into bounded subtasks, maintains execution memory under context pressure, and verifies and repairs the final deliverable. We evaluate OneDayAgent on AgentIF-OneDay across 104 tasks. With the GLM-5.2 backend, OneDayAgent sets a new state of the art with an overall score of 0.821. The same harness runs across five backend LLMs from three model families, indicating the harness generalizes across backends without tuning, even as different models induce distinct execution styles under the same workflow.

View arXiv page View PDF GitHub 2 Add to collection