programming in the large\nagent in the small -> agent in the large\n\nPera, a Perception-Centered Architecture for Persistent Agents, provides a framework for this transition by enabling agents to perceive relevant changes, turn them into lifecycle tasks, and continuously adapt over time.","html":"<p>programming in the small -&gt; programming in the large<br>agent in the small -&gt; agent in the large</p>\n<p>Pera, a Perception-Centered Architecture for Persistent Agents, provides a framework for this transition by enabling agents to perceive relevant changes, turn them into lifecycle tasks, and continuously adapt over time.</p>\n","updatedAt":"2026-09-02T06:17:37.294Z","author":{"_id":"65435cad429b80b14922ab8d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/N8oWq4ZZn3dRxmXi18FrA.jpeg","fullname":"Shichun Liu","name":"Liusc2020","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":6,"isUserFollowing":false}},"numEdits":1,"identifiedLanguage":{"language":"en","probability":0.8966822624206543},"editors":["Liusc2020"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/N8oWq4ZZn3dRxmXi18FrA.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.30478","authors":[{"_id":"6a97ad0dfe3c2f89286c3aaa","name":"Shihan Dou","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3aab","name":"Haoxiang Jia","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3aac","name":"Shichun Liu","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3aad","name":"Feng Chen","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3aae","name":"Chenhao Huang","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3aaf","name":"Yujiong Shen","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3ab0","name":"Shaofan Liu","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3ab1","name":"Jiayi Chen","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3ab2","name":"Jiahang Lin","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3ab3","name":"Honglin Guo","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3ab4","name":"Qianyu He","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3ab5","name":"Minghao Guo","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3ab6","name":"Ziyi Ye","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3ab7","name":"Pluto Zhou","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3ab8","name":"Tao Gui","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3ab9","name":"Qi Zhang","hidden":false},{"_id":"6a97ad0dfe3c2f89286c3aba","name":"Xuanjing Huang","hidden":false}],"publishedAt":"2026-08-31T00:00:00.000Z","submittedOnDailyAt":"2026-09-02T00:00:00.000Z","title":"Agents in the Large: Perception-Centered Architecture for Persistent Agents","submittedOnDailyBy":{"_id":"65435cad429b80b14922ab8d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/N8oWq4ZZn3dRxmXi18FrA.jpeg","isPro":false,"fullname":"Shichun Liu","user":"Liusc2020","type":"user","name":"Liusc2020"},"summary":"Cognitive language agents have achieved substantial progress by equipping language models with memory, tools, and decision-making procedures, enabling agents to reason and act in interactive environments. Existing frameworks largely cast these agents as systems for solving user-specified, bounded tasks. An increasingly important goal is for language agents to provide persistent assistance in long-lived settings where user needs, context, and service procedures persist and change, and to remain useful across the broad range of tasks that arise over time. Yet we still lack a framework to characterize persistent AI agents, organize existing work, and guide future development. To this end, we propose a Perception-Centered Architecture for Persistent Agents (Pera). Pera describes a persistent agent organized around perception and control components that continually perceive service-relevant signals from episodic task executions, internal context, and changes in the surrounding environment, and use these signals to construct lifecycle tasks. These tasks drive the ongoing operation and adaptation of the agent's service procedures. We use Pera to retrospectively organize recent work, examine a detailed case study, and offer forward-looking insights for building more capable persistent agents. Just as software engineering moved from programming in the small to programming in the large, Pera frames the evolution of language agents as an analogous architectural transition toward long-lived, adaptive intelligence systems.","upvotes":3,"discussionId":"6a97ad0efe3c2f89286c3abb","ai_summary":"The paper proposes a perception-centered architecture for persistent language agents that continuously adapt service procedures by perceiving signals from tasks, context, and environmental changes.","ai_keywords":["language models","perception-centered architecture","persistent agents","lifecycle tasks"],"ai_summary_model":"thinkingmachines/Inkling-Small","organization":{"_id":"643cb0625fcffe09fb6ca688","name":"Fudan-University","fullname":"Fudan University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6437eca0819f3ab20d162e14/kWv0cGlAhAG3iNWVxowkJ.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":"65435cad429b80b14922ab8d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/N8oWq4ZZn3dRxmXi18FrA.jpeg","isPro":false,"fullname":"Shichun Liu","user":"Liusc2020","type":"user"},{"_id":"63ac5701c21e60a3e9b58aa7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63ac5701c21e60a3e9b58aa7/g6EX7diOpuA94R2ab-rZC.png","isPro":true,"fullname":"Dipankar Sarkar","user":"dipankarsarkar","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"643cb0625fcffe09fb6ca688","name":"Fudan-University","fullname":"Fudan University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6437eca0819f3ab20d162e14/kWv0cGlAhAG3iNWVxowkJ.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.30478.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2608.30478 in a model README.md to link it from this page.

Cite arxiv.org/abs/2608.30478 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2608.30478 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.