{"slug": "theophyseval-assessing-ai-agents-at-autonomous-theoretical-physics-solving", "title": "TheoPhysEval: Assessing AI agents at autonomous theoretical physics solving", "summary": "A new arXiv paper, TheoPhysEval, reports that the best-performing off-the-shelf AI agent, GPT-6-Astra harnessed in Codex, solved 98% of 50 unpublished research-level theoretical physics problems autonomously at an average cost under USD 3 per problem. The benchmark problems, submitted 9 Oct 2026, would each take a world expert roughly a day or less, and agents showed only small accuracy changes when denied web search and background papers, suggesting significant memorization of the literature. The authors note the results indicate state-of-the-art agents can perform concrete theoretical physics calculations but still lack agent-led breakthroughs in the field.", "body_md": "# High Energy Physics - Theory\n\n  [Submitted on 9 Oct 2026]\n\n# Title:TheoPhysEval: Assessing AI agents at autonomous theoretical physics problem solving\n\n[View PDF](https://arxiv.org/pdf/2610.16733)\n\n[HTML (experimental)](https://arxiv.org/html/2610.16733v1)\n\nAbstract:We present a suite of 50 unpublished research-level theoretical physics problems with verifiable answers. Without AI assistance, a typical problem in our collection could be solved by a world expert in about a day or less but would take considerably longer for experts in adjacent specialties. We test the ability of off-the-shelf AI agents to tackle these problems autonomously, without human hints. When given access to tools available in a realistic setting, including the ability to search the literature and write scripts for numerical and symbolic work, the best-performing agent, GPT-6-Astra harnessed in Codex, obtains the final answers with a near-perfect accuracy of 98% at an average cost under USD 3 per problem. On average, agents show only small changes in accuracy when denied web search and access to background research papers, suggesting significant memorization of the literature. These results suggest that state-of-the-art agents can accurately perform concrete calculations required across theoretical physics research. We comment on the broader implications of these findings and discuss possible explanations for the current lack of agent-led breakthroughs in theoretical physics despite their outstanding problem-solving abilities.\n    \n\n### Current browse context:\n\nhep-th\n\n    Change to browse by:\n    \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))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))\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/theophyseval-assessing-ai-agents-at-autonomous-theoretical-physics-solving", "canonical_source": "https://arxiv.org/abs/2610.16733", "published_at": "2026-10-15 11:08:54+00:00", "updated_at": "2026-10-15 11:21:08.006341+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "large-language-models"], "entities": ["TheoPhysEval", "GPT-6-Astra", "Codex", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/theophyseval-assessing-ai-agents-at-autonomous-theoretical-physics-solving", "markdown": "https://wpnews.pro/news/theophyseval-assessing-ai-agents-at-autonomous-theoretical-physics-solving.md", "text": "https://wpnews.pro/news/theophyseval-assessing-ai-agents-at-autonomous-theoretical-physics-solving.txt", "jsonld": "https://wpnews.pro/news/theophyseval-assessing-ai-agents-at-autonomous-theoretical-physics-solving.jsonld"}}