In recursive self-evolving or discovery systems, diversity isn't just a nice-to-have, it's a key ingredient for unlocking sustained progress and continuous improvements. In our recent ICML2026 paper, \"Towards Diverse Scientific Hypothesis Search with Large Language Models\", we take a closer look at why diversity matters in discovery systems and introduce a simple but effective solution: EvoDiverse.</p>\n","updatedAt":"2026-06-11T17:33:20.757Z","author":{"_id":"6520621836008ecc88699622","avatarUrl":"/avatars/b08c00af00f1736a4f4938443e575b0e.svg","fullname":"Parshin Shojaee","name":"parshinsh","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":2,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8814035058021545},"editors":["parshinsh"],"editorAvatarUrls":["/avatars/b08c00af00f1736a4f4938443e575b0e.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.10587","authors":[{"_id":"6a2af0be4957fcdd3aac0446","name":"Haorui Wang","hidden":false},{"_id":"6a2af0be4957fcdd3aac0447","name":"Parshin Shojaee","hidden":false},{"_id":"6a2af0be4957fcdd3aac0448","name":"Kazem Meidani","hidden":false},{"_id":"6a2af0be4957fcdd3aac0449","name":"Kunyang Sun","hidden":false},{"_id":"6a2af0be4957fcdd3aac044a","name":"José Miguel Hernández-Lobato","hidden":false},{"_id":"6a2af0be4957fcdd3aac044b","name":"Teresa Head-Gordon","hidden":false},{"_id":"6a2af0be4957fcdd3aac044c","name":"Jiajun He","hidden":false},{"_id":"6a2af0be4957fcdd3aac044d","name":"Chandan K. Reddy","hidden":false},{"_id":"6a2af0be4957fcdd3aac044e","name":"Chao Zhang","hidden":false},{"_id":"6a2af0be4957fcdd3aac044f","name":"Yuanqi Du","hidden":false}],"publishedAt":"2026-06-09T08:52:49.000Z","submittedOnDailyAt":"2026-06-11T00:00:00.000Z","title":"Towards Diverse Scientific Hypothesis Search with Large Language Models","submittedOnDailyBy":{"_id":"6520621836008ecc88699622","avatarUrl":"/avatars/b08c00af00f1736a4f4938443e575b0e.svg","isPro":false,"fullname":"Parshin Shojaee","user":"parshinsh","type":"user","name":"parshinsh"},"summary":"Large language models (LLMs) are on the rise for accelerating scientific discovery, most recently in advanced tasks such as generating valid scientific hypotheses. Yet in many discovery settings, the goal is not to identify a single best hypothesis since validation can be noisy and expensive, and scientists benefit from a set of high-quality alternative hypotheses that hedge against downstream uncertainty for the best solutions. Nevertheless, commonly used evolutionary search recipes tend to prioritize optimization over exploration in hypothesis generation, and the resulting selection pressure during the search process leads to diversity collapse. Motivated by these limitations, we formulate hypothesis search as a sampling problem, where the objective is to efficiently produce diverse, high-quality hypotheses under a fixed validation budget. Building on this perspective, we propose \\ours, an evolutionary framework inspired by the classical parallel tempering algorithm that searches hypotheses at multiple temperature levels and enables principled information exchange across temperatures to improve exploration without disrupting convergence. Across domains including molecular discovery, equation discovery, and algorithm discovery, our approach consistently improves both hypothesis quality and diversity under the same validation budget, and produces candidates that remain robust under more expensive downstream computational validations.","upvotes":1,"discussionId":"6a2af0bf4957fcdd3aac0450","ai_summary":"Evolutionary framework for hypothesis generation that improves diversity and quality through multi-temperature sampling and information exchange across search levels.","ai_keywords":["evolutionary search","hypothesis generation","diversity collapse","parallel tempering","multi-temperature levels","sampling problem","validation budget","computational validation"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct"},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6520621836008ecc88699622","avatarUrl":"/avatars/b08c00af00f1736a4f4938443e575b0e.svg","isPro":false,"fullname":"Parshin Shojaee","user":"parshinsh","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.10587.md"}">
Towards Diverse Scientific Hypothesis Search with Large Language Models
Authors: ,
,
,
,
,
,
,
,
,
Abstract
Evolutionary framework for hypothesis generation that improves diversity and quality through multi-temperature sampling and information exchange across search levels.
Large language models (LLMs) are on the rise for accelerating scientific discovery, most recently in advanced tasks such as generating valid scientific hypotheses. Yet in many discovery settings, the goal is not to identify a single best hypothesis since validation can be noisy and expensive, and scientists benefit from a set of high-quality alternative hypotheses that hedge against downstream uncertainty for the best solutions. Nevertheless, commonly used evolutionary search recipes tend to prioritize optimization over exploration in hypothesis generation, and the resulting selection pressure during the search process leads to diversity collapse. Motivated by these limitations, we formulate hypothesis search as a sampling problem, where the objective is to efficiently produce diverse, high-quality hypotheses under a fixed validation budget. Building on this perspective, we propose \ours, an evolutionary framework inspired by the classical parallel tempering algorithm that searches hypotheses at multiple temperature levels and enables principled information exchange across temperatures to improve exploration without disrupting convergence. Across domains including molecular discovery, equation discovery, and algorithm discovery, our approach consistently improves both hypothesis quality and diversity under the same validation budget, and produces candidates that remain robust under more expensive downstream computational validations.
Community
In recursive self-evolving or discovery systems, diversity isn't just a nice-to-have, it's a key ingredient for unlocking sustained progress and continuous improvements. In our recent ICML2026 paper, "Towards Diverse Scientific Hypothesis Search with Large Language Models", we take a closer look at why diversity matters in discovery systems and introduce a simple but effective solution: EvoDiverse.
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/2606.10587 in a model README.md to link it from this page.
Cite arxiv.org/abs/2606.10587 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2606.10587 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.