Agentic systems are increasingly expected to improve after deployment, yet single-entity self-evolution is often bounded by a static learning context, such as fixed tasks and feedback. This survey focuses on co-evolution in agentic systems, a multi-component form of self-evolution in which multiple agents and their environment impose adaptive pressure on one another. To organize existing papers, we propose a progressive three-stage taxonomy that traces how the system gradually sheds human-engineered constraints. Agent--Agent Co-Evolution studies how agents adapt through dynamic peers, including adversarial, collaborative, and organizational adaptation. Agent--Environment Co-Evolution extends this loop to adaptive tasks, feedback, and interaction spaces that change with the agents. Meta Co-Evolution further explores the possibility of making the evolution mechanism itself evolvable. We also discuss open challenges in evaluating such systems, scaling them across multiple components, and keeping increasingly autonomous evolutionary processes safe and controllable. This survey provides a unified foundation for building robust and open-ended agentic systems that can improve beyond fixed human-designed paths.</p>\n","updatedAt":"2026-08-12T03:08:44.284Z","author":{"_id":"687f853bb39262ba84f3eeff","avatarUrl":"/avatars/cdfc44fde8237f08f10192553fe5a075.svg","fullname":"Junhao Shen","name":"shenjunhao","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":5,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9268842339515686},"editors":["shenjunhao"],"editorAvatarUrls":["/avatars/cdfc44fde8237f08f10192553fe5a075.svg"],"reactions":[],"isReport":false}},{"id":"6a7c249487b2821da0c78d9c","author":{"_id":"6669a1c060f4fa80779898db","avatarUrl":"/avatars/6d5cabd61ae3d593400ff42f1f5a9fce.svg","fullname":"wuqimahei","name":"wqmh","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false},"createdAt":"2026-08-12T07:45:24.000Z","type":"comment","data":{"edited":true,"hidden":true,"hiddenBy":"","latest":{"raw":"This comment has been hidden","html":"This comment has been hidden","updatedAt":"2026-08-12T07:45:43.416Z","author":{"_id":"6669a1c060f4fa80779898db","avatarUrl":"/avatars/6d5cabd61ae3d593400ff42f1f5a9fce.svg","fullname":"wuqimahei","name":"wqmh","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false}},"numEdits":0,"editors":[],"editorAvatarUrls":[],"reactions":[]}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.10299","authors":[{"_id":"6a7be30d1653ef87c6af1c17","user":{"_id":"6587e349f8b453e1f54b1370","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6587e349f8b453e1f54b1370/K4I2G8v8MS6JC39GbKQlq.jpeg","isPro":false,"fullname":"zongqing","user":"zongqing0068","type":"user","name":"zongqing0068"},"name":"Qing Zong","status":"claimed_verified","statusLastChangedAt":"2026-08-12T08:45:05.083Z","hidden":false},{"_id":"6a7be30d1653ef87c6af1c18","name":"Jiayu Liu","hidden":false},{"_id":"6a7be30d1653ef87c6af1c19","user":{"_id":"687f853bb39262ba84f3eeff","avatarUrl":"/avatars/cdfc44fde8237f08f10192553fe5a075.svg","isPro":false,"fullname":"Junhao Shen","user":"shenjunhao","type":"user","name":"shenjunhao"},"name":"Junhao Shen","status":"claimed_verified","statusLastChangedAt":"2026-08-12T08:45:05.091Z","hidden":false},{"_id":"6a7be30d1653ef87c6af1c1a","name":"Zecong Tang","hidden":false},{"_id":"6a7be30d1653ef87c6af1c1b","name":"Linsi Wu","hidden":false},{"_id":"6a7be30d1653ef87c6af1c1c","name":"Yuxuan Liu","hidden":false},{"_id":"6a7be30d1653ef87c6af1c1d","name":"Rui Wang","hidden":false},{"_id":"6a7be30d1653ef87c6af1c1e","user":{"_id":"62281c11236b7b2eefa7f198","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62281c11236b7b2eefa7f198/O-LoLaDkIoWcP19mzkNgS.jpeg","isPro":false,"fullname":"Zhaowei Wang","user":"ZhaoweiWang","type":"user","name":"ZhaoweiWang"},"name":"Zhaowei Wang","status":"claimed_verified","statusLastChangedAt":"2026-08-12T16:45:05.162Z","hidden":false},{"_id":"6a7be30d1653ef87c6af1c1f","name":"Weiqi Wang","hidden":false},{"_id":"6a7be30d1653ef87c6af1c20","name":"Cheng Qian","hidden":false},{"_id":"6a7be30d1653ef87c6af1c21","name":"Xiusi Chen","hidden":false},{"_id":"6a7be30d1653ef87c6af1c22","name":"Yangqiu Song","hidden":false}],"publishedAt":"2026-08-10T00:00:00.000Z","submittedOnDailyAt":"2026-08-12T00:00:00.000Z","title":"Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design","submittedOnDailyBy":{"_id":"687f853bb39262ba84f3eeff","avatarUrl":"/avatars/cdfc44fde8237f08f10192553fe5a075.svg","isPro":false,"fullname":"Junhao Shen","user":"shenjunhao","type":"user","name":"shenjunhao"},"summary":"Agentic systems are increasingly expected to improve after deployment, yet single-entity self-evolution is often bounded by a static learning context, such as fixed tasks and feedback. This survey focuses on co-evolution in agentic systems, a multi-component form of self-evolution in which multiple agents and their environment impose adaptive pressure on one another. To organize existing papers, we propose a progressive three-stage taxonomy that traces how the system gradually sheds human-engineered constraints. Agent--Agent Co-Evolution studies how agents adapt through dynamic peers, including adversarial, collaborative, and organizational adaptation. Agent--Environment Co-Evolution extends this loop to adaptive tasks, feedback, and interaction spaces that change with the agents. Meta Co-Evolution further explores the possibility of making the evolution mechanism itself evolvable. We also discuss open challenges in evaluating such systems, scaling them across multiple components, and keeping increasingly autonomous evolutionary processes safe and controllable. This survey provides a unified foundation for building robust and open-ended agentic systems that can improve beyond fixed human-designed paths.","upvotes":107,"discussionId":"6a7be30d1653ef87c6af1c23","githubRepo":"https://github.com/zongqing0068/awesome-co-evolution","githubRepoAddedBy":"user","ai_summary":"Agentic systems can achieve open-ended improvement through multi-component co-evolution that progressively removes fixed human constraints across agents, environments, and evolution mechanisms.","ai_keywords":["agentic systems","co-evolution","self-evolution","adversarial adaptation","collaborative adaptation","organizational adaptation","agent-environment co-evolution","meta co-evolution","evolvable mechanisms"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":27},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"687f853bb39262ba84f3eeff","avatarUrl":"/avatars/cdfc44fde8237f08f10192553fe5a075.svg","isPro":false,"fullname":"Junhao Shen","user":"shenjunhao","type":"user"},{"_id":"6a5f29217ff099983483e767","avatarUrl":"/avatars/9c48d5e60a18acaf8ae048ef6e69f9cf.svg","isPro":false,"fullname":"Zecong Tang","user":"zecongtanghku","type":"user"},{"_id":"62d7bcbcf6e8ba66107b45bb","avatarUrl":"/avatars/89d0ae2d937b720eb5ece3f954430415.svg","isPro":false,"fullname":"zq","user":"zq27","type":"user"},{"_id":"69366520d3108f12cd6f6fb0","avatarUrl":"/avatars/ddbce09d436895ae1bdde1dc87bb0d85.svg","isPro":false,"fullname":"Zecong Tang","user":"Zecongloveai","type":"user"},{"_id":"6587e349f8b453e1f54b1370","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6587e349f8b453e1f54b1370/K4I2G8v8MS6JC39GbKQlq.jpeg","isPro":false,"fullname":"zongqing","user":"zongqing0068","type":"user"},{"_id":"66d8512c54209e9101811e8e","avatarUrl":"/avatars/62dfd8e6261108f2508efe678d5a2a57.svg","isPro":false,"fullname":"M Saad Salman","user":"MSS444","type":"user"},{"_id":"6996f56256426abbe6e6614a","avatarUrl":"/avatars/8a15d472223b6e538f823312566c2f6c.svg","isPro":false,"fullname":"Mue9rgobb4ay","user":"mue9rgobb4ay","type":"user"},{"_id":"66783baec3f824dde8f783ac","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66783baec3f824dde8f783ac/oqFYUrgs2vnGRhAMSrQpC.jpeg","isPro":false,"fullname":"Jeff","user":"JiayuJeff","type":"user"},{"_id":"6a3a1751122573bf1f98f4c3","avatarUrl":"/avatars/03f8f778cb4316e2880058ae67bfd6eb.svg","isPro":false,"fullname":"j185163","user":"j185163","type":"user"},{"_id":"6679a0e092e6bd0b961bfdb2","avatarUrl":"/avatars/0b7f66a25c1681d1984dc03552e8f42d.svg","isPro":false,"fullname":"LIU Jiayu","user":"JeffLiu2005","type":"user"},{"_id":"6a3a1559d566bf8f5224b8d5","avatarUrl":"/avatars/986316b772baf175989e32d2e4c23e0a.svg","isPro":false,"fullname":"jyjacademic","user":"jyjacademic","type":"user"},{"_id":"6a3a1621c69ee5aae6c8329d","avatarUrl":"/avatars/7907d753284e6ce7f62b2f211bbb32b2.svg","isPro":false,"fullname":"jyjgmail","user":"jyjgmail","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":2,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.10299.md","query":{}}">
Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design
Abstract
Agentic systems can achieve open-ended improvement through multi-component co-evolution that progressively removes fixed human constraints across agents, environments, and evolution mechanisms.
Agentic systems are increasingly expected to improve after deployment, yet single-entity self-evolution is often bounded by a static learning context, such as fixed tasks and feedback. This survey focuses on co-evolution in agentic systems, a multi-component form of self-evolution in which multiple agents and their environment impose adaptive pressure on one another. To organize existing papers, we propose a progressive three-stage taxonomy that traces how the system gradually sheds human-engineered constraints. Agent--Agent Co-Evolution studies how agents adapt through dynamic peers, including adversarial, collaborative, and organizational adaptation. Agent--Environment Co-Evolution extends this loop to adaptive tasks, feedback, and interaction spaces that change with the agents. Meta Co-Evolution further explores the possibility of making the evolution mechanism itself evolvable. We also discuss open challenges in evaluating such systems, scaling them across multiple components, and keeping increasingly autonomous evolutionary processes safe and controllable. This survey provides a unified foundation for building robust and open-ended agentic systems that can improve beyond fixed human-designed paths.
Community
Agentic systems are increasingly expected to improve after deployment, yet single-entity self-evolution is often bounded by a static learning context, such as fixed tasks and feedback. This survey focuses on co-evolution in agentic systems, a multi-component form of self-evolution in which multiple agents and their environment impose adaptive pressure on one another. To organize existing papers, we propose a progressive three-stage taxonomy that traces how the system gradually sheds human-engineered constraints. Agent--Agent Co-Evolution studies how agents adapt through dynamic peers, including adversarial, collaborative, and organizational adaptation. Agent--Environment Co-Evolution extends this loop to adaptive tasks, feedback, and interaction spaces that change with the agents. Meta Co-Evolution further explores the possibility of making the evolution mechanism itself evolvable. We also discuss open challenges in evaluating such systems, scaling them across multiple components, and keeping increasingly autonomous evolutionary processes safe and controllable. This survey provides a unified foundation for building robust and open-ended agentic systems that can improve beyond fixed human-designed paths.
This comment has been hidden 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/2608.10299 in a model README.md to link it from this page.
Cite arxiv.org/abs/2608.10299 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2608.10299 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.