TLAPS-Bench: Formally Proving Correctness with TLA+ Proof System

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%.

Computer Science Artificial Intelligence Submitted on 2 Nov 2026 Title:TLAPS-Bench: Formally Proving Correctness of Real-World System Specifications with TLA+ Proof System View PDF https://arxiv.org/pdf/2611.02849 HTML experimental https://arxiv.org/html/2611.02849v1 Abstract: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. Additional Features Current browse context: cs.AI References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both 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. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .