A step toward exponentiating mathematical discovery</p>\n","updatedAt":"2026-08-19T20:28:13.911Z","author":{"_id":"67cffe31d6f5c181e523610c","avatarUrl":"/avatars/8706e09fc4397456baeddb8942c8b0ee.svg","fullname":"Zeyu Zheng","name":"zeyu-zheng","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6099374294281006},"editors":["zeyu-zheng"],"editorAvatarUrls":["/avatars/8706e09fc4397456baeddb8942c8b0ee.svg"],"reactions":[],"isReport":false}},{"id":"6a8659eee1736a86643cc21e","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":378,"isUserFollowing":false},"createdAt":"2026-08-20T01:35:42.000Z","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* [ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System](https://huggingface.co/papers/2607.14178) (2026)\n* [From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier](https://huggingface.co/papers/2607.07779) (2026)\n* [Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems](https://huggingface.co/papers/2607.09025) (2026)\n* [The Past and Future of AI Scientists](https://huggingface.co/papers/2608.14407) (2026)\n* [Towards Automating Scientific Review with Google's Paper Assistant Tool](https://huggingface.co/papers/2606.28277) (2026)\n* [SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematics](https://huggingface.co/papers/2606.29894) (2026)\n* [Personalized Auto-Research: Towards a True AI Co-Scientist](https://huggingface.co/papers/2608.14881) (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":"<p>This is an automated message from the <a href=\"https://huggingface.co/librarian-bots\">Librarian Bot</a>. I found the following papers similar to this paper. </p>\n<p>The following papers were recommended by the Semantic Scholar API </p>\n<ul>\n<li><a href=\"https://huggingface.co/papers/2607.14178\">ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2607.07779\">From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2607.09025\">Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2608.14407\">The Past and Future of AI Scientists</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.28277\">Towards Automating Scientific Review with Google's Paper Assistant Tool</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.29894\">SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematics</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2608.14881\">Personalized Auto-Research: Towards a True AI Co-Scientist</a> (2026)</li>\n</ul>\n<p> Please give a thumbs up to this comment if you found it helpful!</p>\n<p> If you want recommendations for any Paper on Hugging Face checkout <a href=\"https://huggingface.co/spaces/librarian-bots/recommend_similar_papers\">this</a> Space</p>\n<p> You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: <code>@librarian-bot recommend</code></p>\n","updatedAt":"2026-08-20T01:35:42.192Z","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":378,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7209100723266602},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.16977","authors":[{"_id":"6a861139db13816030683dea","name":"Zeyu Zheng","hidden":false},{"_id":"6a861139db13816030683deb","name":"Shengtong Zhang","hidden":false},{"_id":"6a861139db13816030683dec","name":"Jeremy Avigad","hidden":false},{"_id":"6a861139db13816030683ded","name":"Prasad Tetali","hidden":false},{"_id":"6a861139db13816030683dee","name":"Sean Welleck","hidden":false}],"publishedAt":"2026-08-17T00:00:00.000Z","submittedOnDailyAt":"2026-08-19T00:00:00.000Z","title":"The Problem Is the Problem: Towards Scalable Mathematical Discovery","submittedOnDailyBy":{"_id":"67cffe31d6f5c181e523610c","avatarUrl":"/avatars/8706e09fc4397456baeddb8942c8b0ee.svg","isPro":false,"fullname":"Zeyu Zheng","user":"zeyu-zheng","type":"user","name":"zeyu-zheng"},"summary":"AI systems are increasingly capable of contributing to mathematical research. In research practice, frontier-model reasoning is a limited resource, and expert mathematical review is even more sharply constrained. Allocating these scarce resources well is therefore central to making AI-assisted mathematical discovery efficient. In most current AI-for-math workflows, human effort is concentrated at the beginning and end, in selecting suitable research problems and later reviewing the resulting artifacts. These two stages are becoming bottlenecks for research-level mathematics. We address them by proposing a new human-AI discovery paradigm. The human input is no longer a single problem selected in advance, but a research direction in which the experts have interest and expertise. The system then searches a broad literature corpus for candidate problems in that direction. Inspired by search and recommender systems, we build Find, Attempt, and Recommend (FAR), a literature-to-review cascade that automates the search for suitable problems and focuses human attention on artifacts that have passed several stages of filtering. In a combinatorics pilot, the pipeline starts from 5,245 combinatorics papers, recovers 6,453 candidate conjectures or open problems, and filters them to 4,717 apparently well-posed and still-open conjectures. Subsequent reasoning and automated triage stages surface 598 potential resolutions and select 77 items for author-team review. Among them, we identify many interesting discoveries, including results on conjectures and questions of Davies--Jenssen--Perkins--Roberts, Erdős--Straus, Ikenmeyer--Pak--Panova, and Lund--Saraf--Wolf. These results demonstrate the effectiveness of this new mode of human-AI collaboration for mathematical discovery.","upvotes":2,"discussionId":"6a861139db13816030683def","projectPage":"https://probxiv.com","githubRepo":"https://github.com/zeyu-zheng/FAR","githubRepoAddedBy":"user","ai_summary":"A literature-to-review pipeline automates problem discovery and triage to focus expert review on promising mathematical conjectures within a chosen research direction.","ai_keywords":["FAR","literature-to-review cascade","candidate conjectures","automated triage","reasoning stages","human-AI collaboration"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":7,"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":"67cffe31d6f5c181e523610c","avatarUrl":"/avatars/8706e09fc4397456baeddb8942c8b0ee.svg","isPro":false,"fullname":"Zeyu Zheng","user":"zeyu-zheng","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":"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/2608/2608.16977.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2608.16977 in a model README.md to link it from this page.

Cite arxiv.org/abs/2608.16977 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2608.16977 in a Space README.md to link it from this page.

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