{"slug": "h1-a-taste-of-the-bitter-lesson-in-automated-theorem-proving", "title": "h1: A Taste of the Bitter Lesson in Automated Theorem Proving", "summary": "A 30 October 2026 arXiv paper by Skander Moalla and co-authors reports that h1, a simple agentic loop giving a language model an efficient interface to Lean 4 with verifier feedback and self-reflection, reaches state-of-the-art results on PutnamBench, FATE-X and FormalConjectures100-Solved and settles eight open problems in FormalConjectures. At matched models, h1 matches or outperforms specialized workflows such as Goedel-Architect and AlphaProof Nexus, with ablations against Claude Code and AxProverBase showing that an efficient Lean interface largely determines cost and solve rate. The authors recommend that future work evaluate frontier models with efficient execution feedback before prescribing human-designed workflows of planning, decomposition and prover orchestration.", "body_md": "# Computer Science > Machine Learning\n\n  [Submitted on 25 Oct 2026 (\n\n[v1](https://arxiv.org/abs/2610.35962v1)), last revised 30 Oct 2026 (this version, v2)]\n# Title:h1: A Taste of the Bitter Lesson in Automated Theorem Proving\n\n[View PDF](https://arxiv.org/pdf/2610.35962)\n\n[HTML (experimental)](https://arxiv.org/html/2610.35962v2)\n\nAbstract:While progress in informal mathematics has come largely from scaling the chain-of-thought and agentic reasoning of frontier language models, formal theorem proving has increasingly relied on human-designed workflows around these models, such as planning, decomposition, and orchestrating specialized provers. This raises a bitter-lesson question: can a simple agentic loop that scales test-time compute match these workflows? The answer matters as formal verification must scale to keep up with frontier models producing research mathematics, yet new workflows rarely settle it, as their gains are often confounded with stronger models or more compute. We study this question with h1, a simple harness that gives a model an efficient interface to Lean 4 and keeps it working through verifier feedback and self-reflection, without imposing a decomposition or search structure. h1 reaches state-of-the-art results on PutnamBench, FATE-X, and FormalConjectures100-Solved, settles eight open problems in FormalConjectures, and, at matched models, matches or outperforms specialized workflows such as Goedel-Architect and AlphaProof Nexus, surprisingly showing that a single attempt (pass@1) can often scale to solve open problems. Through ablations and matched-model comparisons with Claude Code and AxProverBase, we find that simplicity alone is not enough: an efficient Lean interface largely determines cost and solve rate. We thus recommend that future work evaluate frontier models with efficient execution feedback before prescribing workflows, at the risk of bitter lessons.\n    \n\n## Submission history\n\nFrom: Skander Moalla [\n[view email](https://arxiv.org/show-email/956eee7f/2610.35962)]\n\n**Sun, 25 Oct 2026 11:07:24 UTC (1,044 KB)**\n\n[\\[v1\\]](https://arxiv.org/abs/2610.35962v1)\n**[v2]** Fri, 30 Oct 2026 17:36:57 UTC (1,066 KB)\n\n### Additional Features\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/h1-a-taste-of-the-bitter-lesson-in-automated-theorem-proving", "canonical_source": "https://arxiv.org/abs/2610.35962", "published_at": "2026-11-02 22:34:47+00:00", "updated_at": "2026-11-02 22:51:09.764574+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-research", "ai-agents"], "entities": ["Skander Moalla", "h1", "Lean 4", "PutnamBench", "FATE-X", "FormalConjectures", "Goedel-Architect", "AlphaProof Nexus"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/h1-a-taste-of-the-bitter-lesson-in-automated-theorem-proving", "markdown": "https://wpnews.pro/news/h1-a-taste-of-the-bitter-lesson-in-automated-theorem-proving.md", "text": "https://wpnews.pro/news/h1-a-taste-of-the-bitter-lesson-in-automated-theorem-proving.txt", "jsonld": "https://wpnews.pro/news/h1-a-taste-of-the-bitter-lesson-in-automated-theorem-proving.jsonld"}}