{"slug": "contrastive-discovery-open-ended-scientific-discovery-over-competing", "title": "Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations", "summary": "A November 10, 2026 arXiv paper introduces Contrastive Discovery, a method that replaces single-hypothesis testing in LLM discovery agents with contrast sets of mutually exclusive, collectively exhaustive competing explanations. Across six domains, 89% of pointwise candidates with the largest belief shifts were rejections, while contrast sets resolved 73% of those same candidates to a specific alternative, and contrast sets guiding search resolved 67% more questions than pointwise surprisal under the same experiment budget. In a blinded study, 38 human experts chose the same explanation on 78% of resolved questions and on 82% of questions where the pointwise agent rejected its hypothesis and stopped.", "body_md": "# Computer Science > Artificial Intelligence\n\n  [Submitted on 10 Nov 2026]\n\n# Title:Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations\n\n[View PDF](http://arxiv.org/pdf/2611.14514v1)\n\n[HTML (experimental)](https://arxiv.org/html/2611.14514v1)\n\nAbstract:LLM agents are increasingly used for open-ended, data-driven scientific discovery, yet most of them evaluate hypotheses pointwise, testing an empirical claim $h$ only against its complement $\\neg h$. When evidence rejects $h$, the agent learns that one explanation is unlikely but not which alternative the evidence supports. To recover that alternative, we introduce Contrastive Discovery, which replaces the single hypothesis with a contrast set, a scientific question paired with mutually exclusive and collectively exhaustive competing explanations. Each experiment is scored by how its evidence redistributes belief across the set, and the question is resolved when belief concentrates on one explanation. Because contrast sets change only the unit an agent proposes and scores, an existing agent can use them to re-evaluate evidence it has already collected or to guide its search. Across six domains, $89\\%$ of the pointwise candidates with the largest belief shifts are rejections. On the same evidence, contrast sets resolve $73\\%$ of these candidates to a specific alternative. When contrast sets guide search, the agent resolves $67\\%$ more questions than pointwise surprisal under the same experiment budget. In a blinded study, $38$ human experts chose the same explanation on $78\\%$ of resolved questions and on $82\\%$ of questions where the pointwise agent rejected its hypothesis and stopped. Together, these results support explicit competing explanations as a way for discovery agents to resolve more scientific questions from the same evidence and validation budget.\n    \n\n### Additional Features\n\n### Current browse context:\n\ncs.AI\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/contrastive-discovery-open-ended-scientific-discovery-over-competing", "canonical_source": "http://arxiv.org/abs/2611.14514v1", "published_at": "2026-11-11 16:49:50+00:00", "updated_at": "2026-11-11 17:21:04.679313+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-research", "ai-agents", "large-language-models", "ai-safety"], "entities": ["arXiv", "Contrastive Discovery"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/contrastive-discovery-open-ended-scientific-discovery-over-competing", "markdown": "https://wpnews.pro/news/contrastive-discovery-open-ended-scientific-discovery-over-competing.md", "text": "https://wpnews.pro/news/contrastive-discovery-open-ended-scientific-discovery-over-competing.txt", "jsonld": "https://wpnews.pro/news/contrastive-discovery-open-ended-scientific-discovery-over-competing.jsonld"}}