Formal Verification

Ask about this topic

Overview

Formal verification studies rigorous ways to show that systems satisfy properties such as safety, security, and correctness. It represents systems and requirements with logic, then uses theorem proving, model checking, SMT solving, static analysis, and runtime monitoring to prove properties or find counterexamples. These methods apply to software, hardware, protocols, neural networks, robotics, and AI agents, where failures can be costly and testing covers only selected executions. Current work combines automation and language models to reduce proof effort, but scalability and whether specifications faithfully capture intended behavior remain central challenges.

Latest papers 320

44 papers in the last four weeks, up 91% on the four weeks before. 0.3% of all new papers.

All topics
CardsList

  1. Mythos and the Unverified Cage: Z3-Based Pre-Deployment Verification for Frontier-Model Sandbox Infrastructure

    Apr 22, 2026Dominik BlainSoftware Vulnerability DetectionFormal Verification

    COBALT Formal Verification, QreativeLab Inc. Montr´eal, Qu´ebec, Canada

  2. Do LLMs Game Formalization? Evaluating Faithfulness in Logical Reasoning

    Apr 21, 2026Kyuhee Kim, Auguste Poiroux, Antoine BosselutFormal VerificationLean Theorem Proving

    EPFL

  3. Counting Worlds Branching Time Semantics for post-hoc Bias Mitigation in generative AI

    Apr 21, 2026Alessandro G. Buda, Giuseppe Primiero, Leonardo Ceragioli +1Algorithmic FairnessFormal Verification

  4. Formally Verified Patent Analysis via Dependent Type Theory: Machine-Checkable Certificates from a Hybrid AI + Lean 4 Pipeline

    Apr 20, 2026George KoomullilFormal VerificationLegal Document Analysis

    Ascendr, Inc.

  5. Symbolic Synthesis for LTLf+ Obligations

    Apr 20, 2026Giuseppe De Giacomo, Christian Hagemeier, Daniel Hausmann +1Program SynthesisFormal Verification

    University of Oxford, UK · University of Liverpool, UK · University of Gothenburg and Chalmers University of Technology, Sweden

  6. Logic-Based Verification of Task Allocation for LLM-Enabled Multi-Agent Manufacturing Systems

    Apr 18, 2026Jonghan Lim, Mostafa Tavakkoli Anbarani, Rômulo Meira-Góes +1Multi-Agent ControlFormal Verification

    Department of Industrial and Manufacturing Engineering, Pennsylvania State University, State College, USA · Department of Mechanical Engineering, Pennsylvania State University, State College, USA · Department of Electrical Engineering, Pennsylvania State University, State College, USA

  7. Certified Program Synthesis with a Multi-Modal Verifier

    Apr 17, 2026Yueyang Feng, Dipesh Kafle, Vladimir Gladshtein +5LLM-Based Program SynthesisProgram Synthesis

    National University of Singapore · Singapore · Neapolis University Pafos +2

  8. SpecPylot: Python Specification Generation using Large Language Models

    Apr 17, 2026Ragib Shahariar Ayon, Shibbir AhmedCounterexample-Guided RefinementFormal Verification

    Texas State University San Marcos, TX, USA

  9. Verification Modulo Tested Library Contracts

    Apr 16, 2026Abhishek Uppar, Omar Muhammad, Sumanth Prabhu +3Program SynthesisFormal Verification

    Indian Institute of Science, India · Relyance AI, India · University of Illinois Urbana-Champaign, Department of Computer Science, USA +1

  10. Vibe-Coding: Feedback-Based Automated Verification with no Human Code Inspection, a Feasibility Study

    Apr 16, 2026Michal Töpfer, František Plášil, Tomáš Bureš +1LLM Self-CorrectionFormal Verification

    Charles University Prague, Czech Republic

  11. FM-Agent: Scaling Formal Methods to Large Systems via LLM-Based Hoare-Style Reasoning

    Apr 13, 2026Haoran Ding, Zhaoguo Wang, Haibo ChenFormal VerificationSoftware Engineering Agents

    Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University

  12. Intent-aligned Formal Specification Synthesis via Traceable Refinement

    Apr 12, 2026Zhe Ye, Aidan Z. H. Yang, Huangyuan Su +6Formal VerificationLLM Self-Refinement

    UC Berkeley · Amazon Web Services · Harvard University

  13. Capture-Quiet Decomposition: A Verification Theorem for Chess Endgame Tablebases

    Apr 9, 2026Alexander PavlovChessFormal Verification

    ProofCodec

  14. Descent Before Hardness: Orbit-Gap Obstructions in Exact Certification

    Apr 8, 2026Tristan SimasFormal Verification

    McGill University, Montreal, Quebec, Canada

  15. Formally Guaranteed Control Adaptation for ODD-Resilient Autonomous Systems

    Apr 8, 2026Gricel Vázquez, Calum Imrie, Sepeedeh Shahbeigi +5Adaptive ControlRobust Control

    Department of Computer Science, University of York, UK · Cyprus University of Technology, Limassol, Cyprus

  16. Generating Local Shields for Decentralised Partially Observable Markov Decision Processes

    Apr 8, 2026Haoran Yang, Nobuko YoshidaPartially Observable Markov Decision ProcessesFormal Verification

    University of Oxford

  17. ProofSketcher: Hybrid LLM + Lightweight Proof Checker for Reliable Math/Logic Reasoning

    Apr 7, 2026Kranthi Kommuru, Kunal Khanvilkar, Gaurav ParekhAutomated Theorem ProvingLLM Mathematical Reasoning

    Automatic Data Processing, Inc Atlanta, USA · Amazon Web Services, Inc Banglore, India

  18. A Formal Security Framework for MCP-Based AI Agents: Threat Taxonomy, Verification Models, and Defense Mechanisms

    Apr 7, 2026Nirajan Acharya, Gaurav Kumar GuptaMCP SecurityAI Agent Security

    University of the Cumberlands · Youngstown State University

  19. Differentiable Invariant Sets for Hybrid Limit Cycles with Application to Legged Robots

    Apr 6, 2026Varun Madabushi, Akash Harapanahalli, Samuel Coogan +1Dynamical SystemsReachability Analysis

    School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, 30332, USA.

  20. Incompleteness of AI Safety Verification via Kolmogorov Complexity

    Apr 6, 2026Munawar HasanFormal VerificationAI Safety

    Mechanical and Aerospace Engineering, Michigan Technological University, Houghton, MI, USA

  21. Automated Conjecture Resolution with Formal Verification

    Apr 4, 2026Haocheng Ju, Guoxiong Gao, Jiedong Jiang +13Automated Theorem ProvingLLM Mathematical Reasoning

    School of Mathematical Sciences, Peking University · IQuest Research · Westlake Institute for Advanced Study, Westlake University +8

  22. AutoReSpec: A Framework for Generating Specification using Large Language Models

    Apr 4, 2026Ragib Shahariar Ayon, Shibbir AhmedAutoformalizationFormal Verification

    Texas State University, San Marcos, TX, USA

  23. SentinelAgent: Intent-Verified Delegation Chains for Securing Federal Multi-Agent AI Systems

    Apr 3, 2026KrishnaSaiReddy PatilAI Agent GovernanceMulti-Agent System Security

  24. From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems

    Apr 2, 2026Thomas Stefani, Johann Maximilian Christensen, Elena Hoemann +2AI SafetyFormal Verification

    Institute for AI Safety and Security, German Aerospace Center (DLR), Sankt Augustin and Ulm, Germany

  25. Type-Checked Compliance: Deterministic Guardrails for Agentic Financial Systems Using Lean 4 Theorem Proving

    Apr 1, 2026Devakh Rashie, Veda RashiLLM GuardrailsRuntime Enforcement for AI Agents

    Independent Researcher Centreville, Virginia, USA · Thomas Jefferson High School for Science and Technology Alexandria, VA, USA

  26. Spec-Harness: Assessing and Guiding LLM-Synthesized Formal Specifications Beyond Verifiability

    Mar 31, 2026Md Rakib Hossain Misu, Cristina V. Lopes, Iris Ma +2Software Engineering AgentsLLM-Based Program Synthesis

    Department of Informatics, University of California, Irvine

  27. WybeCoder: Verified Imperative Code Generation

    Mar 31, 2026Fabian Gloeckle, Mantas Baksys, Darius Feher +5Formal VerificationCode Generation

    FAIR, Meta · CERMICS, ENPC, Institut Polytechnique de Paris, CNRS · Computer Lab, University of Cambridge +3

  28. From Inference Routing to Agent Orchestration: Declarative Policy Compilation with Cross-Layer Verification

    Mar 28, 2026Huamin Chen, Xunzhuo Liu, Bowei He +1LLM RoutingLLM Agent Orchestration

    vLLM Semantic Router Project · MBZUAI · McGill University +1

  29. FormalProofBench: Can Models Write Graduate Level Math Proofs That Are Formally Verified?

    Mar 27, 2026Nikil Ravi, Kexing Ying, Vasilii Nesterov +5Mathematical Reasoning BenchmarksFormal Verification

    Vals AI · École Polytechnique Fédérale de Lausanne (EPFL) · Moscow Institute of Physics and Technology +2

  30. ExVerus: Verus Proof Repair via Counterexample Reasoning

    Mar 26, 2026Jun Yang, Yuechun Sun, Yi Wu +5Formal Verification

    The University of Chicago · Purdue University · The University of Toronto +1