We propose an online agentic version for causal discovery, which aims to discover causal relations based on observational data. The platform is available at causallearn.com.</p>\n","updatedAt":"2026-06-23T03:56:40.411Z","author":{"_id":"6804a894ea0734d6b26f19c3","avatarUrl":"/avatars/b3f5321366bbbb2fd91624289fbea958.svg","fullname":"Yujia Zheng","name":"yujiazheng","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9275874495506287},"editors":["yujiazheng"],"editorAvatarUrls":["/avatars/b3f5321366bbbb2fd91624289fbea958.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.23608","authors":[{"_id":"6a3a0374fdcd3514343bb59b","name":"Yujia Zheng","hidden":false},{"_id":"6a3a0374fdcd3514343bb59c","name":"Vishal Verma","hidden":false},{"_id":"6a3a0374fdcd3514343bb59d","name":"Mantej Gill","hidden":false},{"_id":"6a3a0374fdcd3514343bb59e","name":"Haoyue Dai","hidden":false},{"_id":"6a3a0374fdcd3514343bb59f","name":"Peter Spirtes","hidden":false},{"_id":"6a3a0374fdcd3514343bb5a0","name":"Kun Zhang","hidden":false}],"publishedAt":"2026-06-22T00:00:00.000Z","submittedOnDailyAt":"2026-06-23T00:00:00.000Z","title":"Causal Discovery in the Era of Agents","submittedOnDailyBy":{"_id":"6804a894ea0734d6b26f19c3","avatarUrl":"/avatars/b3f5321366bbbb2fd91624289fbea958.svg","isPro":false,"fullname":"Yujia Zheng","user":"yujiazheng","type":"user","name":"yujiazheng"},"summary":"Recent attempts to combine large language models (LLMs) with causal discovery ask models to infer pairwise directions, propose graph structures, or inject language-model outputs as priors and constraints. These approaches promise faster analysis, but they also obscure whether a causal evidence is supported by data and assumptions or by textual associations, prompt artifacts and hallucinated mechanisms. We argue for a different role for agents in causal discovery. Agents should inspect data, retrieve context, explain method assumptions and clarify graph outputs, but they should not supply edges, orientations, priors, constraints or causal conclusions. We propose the principle that agents assist the workflow, while causal claims remain grounded in data, explicit assumptions, formal algorithms, diagnostics and user or domain-expert decisions. We instantiate this principle in causal-learn+, an online platform that coordinates data analysis, preprocessing, method recommendation, expert-knowledge incorporation, formal discovery and interpretation around the algorithmic ecosystem of causal-learn. A case study on Big Five personality data illustrates agent-assisted pipeline of causal discovery without turning language-model unreliability into causal evidence. The platform is available at causallearn.com.","upvotes":6,"discussionId":"6a3a0374fdcd3514343bb5a1","projectPage":"https://causallearn.com","githubRepo":"https://github.com/py-why/causal-learn","githubRepoAddedBy":"user","ai_summary":"Language models should assist causal discovery workflows by providing contextual support and explanations rather than generating causal conclusions, as demonstrated through a platform that integrates data analysis and expert knowledge.","ai_keywords":["causal discovery","large language models","causal claims","data analysis","expert-knowledge incorporation","formal algorithms","causal-learn"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","githubStars":1636,"organization":{"_id":"691d9a1012cc4d473e1c862f","name":"CarnegieMellonU","fullname":"Carnegie Mellon University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e396f2b5bb631e9b2fac9a/6I146aJvxxlRCEbYFFAeQ.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6804a894ea0734d6b26f19c3","avatarUrl":"/avatars/b3f5321366bbbb2fd91624289fbea958.svg","isPro":false,"fullname":"Yujia Zheng","user":"yujiazheng","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":"6270324ebecab9e2dcf245de","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6270324ebecab9e2dcf245de/cMbtWSasyNlYc9hvsEEzt.jpeg","isPro":false,"fullname":"Kye Gomez","user":"kye","type":"user"},{"_id":"697c8b15a7f796854ef333c4","avatarUrl":"/avatars/94de3a736fac914944f1b57609e3819a.svg","isPro":false,"fullname":"Joel Wang","user":"joelhenwang","type":"user"},{"_id":"6a2da6c8ca070ee12c6e396c","avatarUrl":"/avatars/0355287dcabaa67dbc7f0b10b87451f9.svg","isPro":false,"fullname":"Joe Mama","user":"JoeMama123123123","type":"user"},{"_id":"65d5b967eeb590ea7435ad07","avatarUrl":"/avatars/ca0a5e123d5da5aca97cfd8a2d07e60e.svg","isPro":true,"fullname":"Kaican Li","user":"m-Just","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"691d9a1012cc4d473e1c862f","name":"CarnegieMellonU","fullname":"Carnegie Mellon University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e396f2b5bb631e9b2fac9a/6I146aJvxxlRCEbYFFAeQ.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.23608.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2606.23608 in a model README.md to link it from this page.

Cite arxiv.org/abs/2606.23608 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2606.23608 in a Space README.md to link it from this page.