Deprecated: The each() function is deprecated. This message will be suppressed on further calls in /home/zhenxiangba/zhenxiangba.com/public_html/phproxy-improved-master/index.php on line 456 Paper page - SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue
\n","updatedAt":"2026-02-09T15:14:12.137Z","author":{"_id":"65243980050781c16f234f1f","avatarUrl":"/avatars/743a009681d5d554c27e04300db9f267.svg","fullname":"Avi","name":"avahal","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":3,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7133000493049622},"editors":["avahal"],"editorAvatarUrls":["/avatars/743a009681d5d554c27e04300db9f267.svg"],"reactions":[],"isReport":false}},{"id":"698a8cfe9d03ad21c16fa805","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false},"createdAt":"2026-02-10T01:42:22.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning](https://huggingface.co/papers/2601.09215) (2026)\n* [SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection](https://huggingface.co/papers/2601.02871) (2026)\n* [SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning](https://huggingface.co/papers/2512.13159) (2025)\n* [From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents](https://huggingface.co/papers/2601.22607) (2026)\n* [User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale](https://huggingface.co/papers/2601.08225) (2026)\n* [Adversarial Training for Failure-Sensitive User Simulation in Mental Health Dialogue Optimization](https://huggingface.co/papers/2512.20773) (2025)\n* [ATOD: An Evaluation Framework and Benchmark for Agentic Task-Oriented Dialogue Systems](https://huggingface.co/papers/2601.11854) (2026)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
\n
The following papers were recommended by the Semantic Scholar API
Please give a thumbs up to this comment if you found it helpful!
\n
If you want recommendations for any Paper on Hugging Face checkout this Space
\n
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
\n","updatedAt":"2026-02-10T01:42:22.202Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7661312818527222},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2602.03548","authors":[{"_id":"6986d4b52d626112378ad65f","user":{"_id":"668547e921e9f68a7a2a6d18","avatarUrl":"/avatars/5251e5c52993c7e5fb23cb4afba03f50.svg","isPro":false,"fullname":"Yuqin Dai","user":"dayll","type":"user"},"name":"Yuqin Dai","status":"claimed_verified","statusLastChangedAt":"2026-02-09T08:34:30.731Z","hidden":false},{"_id":"6986d4b52d626112378ad660","user":{"_id":"64dad2dc00b80a024c5277e4","avatarUrl":"/avatars/10be4a8f9a9d36e231b427a4946de38a.svg","isPro":false,"fullname":"高宁","user":"Aoyama7Hai","type":"user"},"name":"Ning Gao","status":"claimed_verified","statusLastChangedAt":"2026-02-09T08:34:26.859Z","hidden":false},{"_id":"6986d4b52d626112378ad661","name":"Wei Zhang","hidden":false},{"_id":"6986d4b52d626112378ad662","name":"Jie Wang","hidden":false},{"_id":"6986d4b52d626112378ad663","name":"Zichen Luo","hidden":false},{"_id":"6986d4b52d626112378ad664","name":"Jinpeng Wang","hidden":false},{"_id":"6986d4b52d626112378ad665","name":"Yujie Wang","hidden":false},{"_id":"6986d4b52d626112378ad666","name":"Ruiyuan Wu","hidden":false},{"_id":"6986d4b52d626112378ad667","name":"Chaozheng Wang","hidden":false}],"publishedAt":"2026-02-03T14:01:11.000Z","submittedOnDailyAt":"2026-02-09T08:24:20.104Z","title":"SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue","submittedOnDailyBy":{"_id":"668547e921e9f68a7a2a6d18","avatarUrl":"/avatars/5251e5c52993c7e5fb23cb4afba03f50.svg","isPro":false,"fullname":"Yuqin Dai","user":"dayll","type":"user"},"summary":"Large Language Models have demonstrated remarkable capabilities in open-domain dialogues. However, current methods exhibit suboptimal performance in service dialogues, as they rely on noisy, low-quality human conversation data. This limitation arises from data scarcity and the difficulty of simulating authentic, goal-oriented user behaviors. To address these issues, we propose SEAD (Self-Evolving Agent for Service Dialogue), a framework that enables agents to learn effective strategies without large-scale human annotations. SEAD decouples user modeling into two components: a Profile Controller that generates diverse user states to manage training curriculum, and a User Role-play Model that focuses on realistic role-playing. This design ensures the environment provides adaptive training scenarios rather than acting as an unfair adversary. Experiments demonstrate that SEAD significantly outperforms Open-source Foundation Models and Closed-source Commercial Models, improving task completion rate by 17.6% and dialogue efficiency by 11.1%. Code is available at: https://github.com/Da1yuqin/SEAD.","upvotes":4,"discussionId":"6986d4b52d626112378ad668","githubRepo":"https://github.com/Da1yuqin/SEAD","githubRepoAddedBy":"user","ai_summary":"SEAD framework enables service dialogue agents to learn effective strategies through self-evolving user modeling components, achieving superior task completion and dialogue efficiency compared to existing foundation and commercial models.","ai_keywords":["large language models","service dialogues","user modeling","profile controller","user role-play model","task completion rate","dialogue efficiency"],"githubStars":18,"organization":{"_id":"6282108b1c4fdf630c7943a4","name":"meituan","fullname":"meituan","avatar":"https://cdn-uploads.huggingface.co/production/uploads/61ac8f8a00d01045fca0ad2f/4TJKRXMsRyZsyi4H3rWsh.jpeg"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"64dad2dc00b80a024c5277e4","avatarUrl":"/avatars/10be4a8f9a9d36e231b427a4946de38a.svg","isPro":false,"fullname":"高宁","user":"Aoyama7Hai","type":"user"},{"_id":"668547e921e9f68a7a2a6d18","avatarUrl":"/avatars/5251e5c52993c7e5fb23cb4afba03f50.svg","isPro":false,"fullname":"Yuqin Dai","user":"dayll","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":"684d57f26e04c265777ead3f","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/cuOj-bQqukSZreXgUJlfm.png","isPro":false,"fullname":"Joakim Lee","user":"Reinforcement4All","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0,"organization":{"_id":"6282108b1c4fdf630c7943a4","name":"meituan","fullname":"meituan","avatar":"https://cdn-uploads.huggingface.co/production/uploads/61ac8f8a00d01045fca0ad2f/4TJKRXMsRyZsyi4H3rWsh.jpeg"}}">
SEAD framework enables service dialogue agents to learn effective strategies through self-evolving user modeling components, achieving superior task completion and dialogue efficiency compared to existing foundation and commercial models.
AI-generated summary
Large Language Models have demonstrated remarkable capabilities in open-domain dialogues. However, current methods exhibit suboptimal performance in service dialogues, as they rely on noisy, low-quality human conversation data. This limitation arises from data scarcity and the difficulty of simulating authentic, goal-oriented user behaviors. To address these issues, we propose SEAD (Self-Evolving Agent for Service Dialogue), a framework that enables agents to learn effective strategies without large-scale human annotations. SEAD decouples user modeling into two components: a Profile Controller that generates diverse user states to manage training curriculum, and a User Role-play Model that focuses on realistic role-playing. This design ensures the environment provides adaptive training scenarios rather than acting as an unfair adversary. Experiments demonstrate that SEAD significantly outperforms Open-source Foundation Models and Closed-source Commercial Models, improving task completion rate by 17.6% and dialogue efficiency by 11.1%. Code is available at: https://github.com/Da1yuqin/SEAD.
We propose SEAD (Self-Evolving Agent for Service Dialogue), a framework that enables agents to learn effective strategies without large-scale human annotations.