{"slug": "tlaps-bench-formally-proving-correctness-with-tla-proof-system", "title": "TLAPS-Bench: Formally Proving Correctness with TLA+ Proof System", "summary": "A paper submitted on 2 Nov 2026 introduces TLAPS-Bench, a benchmark and execution harness for building machine-checked proofs of real-world system specifications in TLA+ using agentic AI atop the TLA+ Proof System (TLAPS), with safeguards against reward hacking. TLAPS-Bench contains 265 proof targets from 95 TLA+ specifications of real-world systems spanning cache coherence, Byzantine consensus, and write-ahead logs, including properties not previously proved. On a subset of 70 proof targets across 12 specifications, the highest-scoring model, GPT-6.1 Sol (max) run through Codex, proved 31 targets, or 44.3%.", "body_md": "# Computer Science > Artificial Intelligence\n\n  [Submitted on 2 Nov 2026]\n\n# Title:TLAPS-Bench: Formally Proving Correctness of Real-World System Specifications with TLA+ Proof System\n\n[View PDF](https://arxiv.org/pdf/2611.02849)\n\n[HTML (experimental)](https://arxiv.org/html/2611.02849v1)\n\nAbstract:TLAPS-Bench is a benchmark and execution harness for constructing machine-checked proofs for real-world system specifications in TLA+ with agentic AI. Proving correctness of complex system specifications requires discovering inductive invariants, reasoning about intricate state transitions, and decomposing proofs into tractable obligations. TLAPS-Bench provides a proof harness that supports iterative proof development atop the TLA+ Proof System (TLAPS), where agents are equipped with proof tools and libraries, with safeguards against reward hacking. Using the harness, we have employed AI agents to prove desired properties for important system specifications that were not proved before, spanning cache coherence, Byzantine consensus, and write-ahead logs. TLAPS-Bench contains 265 proof targets (each encodes a property to prove) from 95 TLA+ specifications of real-world systems. We evaluated frontier AI agents, represented by Codex with GPT models, on a subset of 70 proof targets across 12 specifications. The highest-scoring model, GPT-6.1 Sol (max), proved 31 (44.3%) proof targets. The results show challenges and opportunities in end-to-end proof development.\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/tlaps-bench-formally-proving-correctness-with-tla-proof-system", "canonical_source": "https://arxiv.org/abs/2611.02849", "published_at": "2026-11-03 23:31:40+00:00", "updated_at": "2026-11-03 23:50:24.964301+00:00", "lang": "en", "topics": ["ai-research", "artificial-intelligence", "ai-agents", "machine-learning"], "entities": ["TLAPS-Bench", "TLA+ Proof System", "TLA+", "Codex", "GPT-6.1 Sol", "OpenAI", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/tlaps-bench-formally-proving-correctness-with-tla-proof-system", "markdown": "https://wpnews.pro/news/tlaps-bench-formally-proving-correctness-with-tla-proof-system.md", "text": "https://wpnews.pro/news/tlaps-bench-formally-proving-correctness-with-tla-proof-system.txt", "jsonld": "https://wpnews.pro/news/tlaps-bench-formally-proving-correctness-with-tla-proof-system.jsonld"}}