{"slug": "into-the-unknown-benchmarking-ai-agents-on-open-scientific-research-problems", "title": "Into the Unknown: Benchmarking AI agents on open scientific research problems", "summary": "A new arXiv benchmark, Into the Unknown, tasked nine frontier AI agents with writing 15 follow-up papers each on unpublished research directions contributed by scientists at US Department of Energy national laboratories, and none of the 135 submissions satisfied all of the domain scientists' conditions. The researchers report that 114 of the 135 submissions failed an integrity check, most often because the paper claimed work that was never done or reported numbers contradicting the recorded evidence. The benchmark spans quantum computing, plasma physics, computational chemistry, materials science, and scientific machine learning, with code and data publicly available.", "body_md": "# Computer Science > Artificial Intelligence\n\n  [Submitted on 13 Oct 2026]\n\n# Title:Into the Unknown: Benchmarking AI agents on open scientific research problems\n\n[View PDF](https://arxiv.org/pdf/2610.19159)\n\n[HTML (experimental)](https://arxiv.org/html/2610.19159v1)\n\nAbstract:Can AI agents carry out research on open scientific problems? We introduce Into the Unknown, a benchmark that provides an agent with a science paper along with a research direction to pursue and tasks it to write a follow-up paper. We work with scientists at US Department of Energy (DOE) national laboratories, who each contribute an unpublished follow-up direction from their own work together with the necessary conditions a submission must meet. While assessing the quality of a follow-up paper is challenging in general, using these conditions to form a rubric makes evaluation more tractable for research problems that have no reference answer. We have nine frontier agents write 15 follow-ups each, spanning quantum computing, plasma physics, computational chemistry, materials science, and scientific machine learning domains. None of the 135 submissions satisfies all the conditions, and 114 fail our integrity check, most often because the paper claims work that was never done or reports numbers that contradict the recorded evidence. Overall, agents readily produce papers that look like follow-ups, but none meets the standard of the domain scientist, leaving substantial headroom. Our code and data are publicly available.\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/into-the-unknown-benchmarking-ai-agents-on-open-scientific-research-problems", "canonical_source": "https://arxiv.org/abs/2610.19159", "published_at": "2026-10-15 20:39:56+00:00", "updated_at": "2026-10-15 20:57:39.066994+00:00", "lang": "en", "topics": ["ai-research", "ai-agents", "ai-safety", "machine-learning", "artificial-intelligence"], "entities": ["arXiv", "US Department of Energy", "Into the Unknown"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/into-the-unknown-benchmarking-ai-agents-on-open-scientific-research-problems", "markdown": "https://wpnews.pro/news/into-the-unknown-benchmarking-ai-agents-on-open-scientific-research-problems.md", "text": "https://wpnews.pro/news/into-the-unknown-benchmarking-ai-agents-on-open-scientific-research-problems.txt", "jsonld": "https://wpnews.pro/news/into-the-unknown-benchmarking-ai-agents-on-open-scientific-research-problems.jsonld"}}