Formal Verification

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

17 new papers

A weekly snapshot of new work published in Formal Verification.

Period ending 2026-09-14

18 new papers

A weekly snapshot of new work published in Formal Verification.

Period ending 2026-09-07

22 new papers

A weekly snapshot of new work published in Formal Verification.

Inside this field

Focused directions

Focused topic

Verifier

Within Formal Verification

330 papersExplore

Focused topic

Theorem

Within Formal Verification

134 papersExplore

Focused topic

Formalization

Within Formal Verification

71 papersExplore

Focused topic

Formal Verification

Within Formal Verification

67 papersExplore

Focused topic

Autoformalization

Within Formal Verification

45 papersExplore

Focused topic

Proof

Within Formal Verification

44 papersExplore

608 papers

Latest in Formal Verification

Browse all topics →

Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems
May 22, 2026Shubham Agarwal, Alexander Krentsel, Shu Liu +10Formal Verification Mock-Interface Synthesis
Advancing Mathematics Research with AI-Driven Formal Proof Search
May 21, 2026George Tsoukalas, Anton Kovsharov, Sergey Shirobokov +18Theorem Mathematics
GLeVE: Graph-Guided Lesion Grounding with Proposal Verification in 3D CT
May 21, 2026Shuo Jiang, Yuhao Hong, Chunbo Jiang +9Lesion Radiology Report Generation
VeriScale: Adversarial Test-Suite Scaling for Verifiable Code Generation
May 21, 2026Yifan Bai, Xiaoyang Liu, Zihao Mou +7Benchmarking Large Language Models Code Generation
What are the Right Symmetries for Formal Theorem Proving?
May 21, 2026Krzysztof Olejniczak, Radoslav Dimitrov, Xingyue Huang +3Theorem Symmetry
ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization
May 21, 2026Riyaz Ahuja, Tate Rowney, Jeremy Avigad +1Theorem Neuro-Symbolic Framework
Lean-GAP: A Dataset of Formalized Graduate Algebra Problems
May 20, 2026Seewoo Lee, Byung-Hak Hwang, Hyojae Lim +10Autoformalization Algebraic Structures
The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering
May 20, 2026Yefan Zhou, Yilun Zhou, Austin Xu +3Verifier Few-Step
Heartbeat-Bound Hierarchical Credentials: Cryptographic Revocation for AI Agent Swarms
May 20, 2026Saurabh DeochakeVerifier Swarms
RMA: an Agentic System for Research-Level Mathematical Problems
May 20, 2026Zelin Zhao, Bo Yuan, Jaemoo Choi +1Mathematics Agentic Systems
NeuroNL2LTL: A Neurosymbolic Framework for Natural Language Translation of Linear Temporal Logic
May 20, 2026Paapa Kwesi Quansah, Ernest BonnahLinear Temporal Logics Formal Verification
Lower Bounds for Advection-Diffusion Equations: An Exploration with AI-Generated Proofs
May 20, 2026Chenyang An, Xiaoqian XuAdvection-Reaction-Diffusion Lower Bounds
Pseudo-Formalization for Automatic Proof Verification
May 19, 2026Slim Barkallah, Luke Bailey, Kaiyue Wen +2Proof Formalization
Using Aristotle API for AI-Assisted Theorem Proving in Lean 4: A Formalisation Case Study of the Grasshopper Problem
May 19, 2026Gabriel Rongyang LauTheorem Proof
Pramana: A Protocol-Layer Treatment of Claim Verification in Autonomous Agent Networks
May 19, 2026Ravi Kiran KadaboinaVerifier Structural Inference
FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration
May 19, 2026Yaojie Zhang, Jianuo Huang, Junlong Ke +5Speculative Decoding LLM Inference Efficiency
Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection
May 19, 2026Bing Wang, Rui Miao, Ximing Li +6Misinformation Detection Misinformation
FormalASR: End-to-End Spoken Chinese to Formal Text
May 19, 2026Wanyi Ning, Yinshang Guo, Haitao Qian +3Accurate Transcription Autoformalization
Discoverable Agent Knowledge -- A Formal Framework for Agentic KG Affordances (Extended Version)
May 18, 2026Terry R. Payne, Valentina Tamma, Enrico DagaOntology Epistemic Actions
Progressive Autonomy as Preference Learning: A Formalization of Trust Calibration for Agentic Tool Use
May 18, 2026Changkun OuAgentic Tool Use Preference Learning
Verify-Gated Completion as Admission Control in a Governed Multi-Agent Runtime: A Bounded Architecture Case Study
May 18, 2026Hai-Duong Nguyen, Xuan-The TranAdmissibility Verifier
Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search
May 18, 2026Jialin Lu, Soonho Kong, Rodrigo Stehling +4Code Refactoring Theorem
Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification
May 17, 2026Shaddin Dughmi, Mahdi Haghifam, Yusuf Hakan KalayciInference-Time Verifier
Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps
May 17, 2026Tanmay Asthana, Aman Saksena, Divyansh SahuDeep Research Verifier
VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
May 17, 2026Hezhe Qiao, Hanghang Tong, Ee-Peng Lim +2Multi-Agent Systems Verifier
Compress the Context, Keep the Commitments: A Formal Framework for Verifiable LLM Context Compression
May 17, 2026Natalia Trukhina, Vadim VashkelisLarge Language Model Compression Context Compression
OProver: A Unified Framework for Agentic Formal Theorem Proving
May 17, 2026David Ma, Kaijing Ma, Shawn Guo +7Theorem Formalization
CAM-Bench: A Benchmark for Computational and Applied Mathematics in Lean
May 17, 2026Wentao Long, Yunfei Zhang, Chenyi Li +3Theorem Mathematics
Filter-then-Verify: A Multiphase GNN and ModernBERT Framework for Social Engineering Detection in Email Networks
May 17, 2026Barsat Khadka, Prasant Koirala, Kshitiz Neupane +1Phishing Attack Detection
Stress-Testing Neural Network Verifiers with Provably Robust Instances
May 16, 2026David Troxell, Yulia Alexandr, Sofia Hunt +2Neural Network Verification Verifier
CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning
May 15, 2026Fangzhou Lin, Shuo Xing, Peiran Li +6Reasoning Benchmark Verifier
From LLM-Generated Conjectures to Lean Formalizations: Automated Polynomial Inequality Proving via Sum-of-Squares Certificates
May 14, 2026Ruobing Zuo, Hanrui Zhao, Gaolei He +2Theorem Proof
Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Models
May 14, 2026Frederik Schmitt, Matthias Cosler, Niklas Metzger +4Constraint-Aware Synthesis Formal Verification
Orthologic for SAT Solving
May 14, 2026Vladislas de Haldat, Simon Guilloud, Viktor KunčakSatisfiability Propositions
Probabilistic Verification of Recurrent Neural Networks for Single and Multi-Agent Reinforcement Learning
May 14, 2026Luca Marzari, Enrico MarchesiniReinforcement Learning With Verifiable Reward Deep Reinforcement Learning
Contestable Multi-Agent Debate with Arena-based Argumentative Computation for Multimedia Verification
May 14, 2026Truong Thanh Hung Nguyen, Vo Thanh Khang Nguyen, Hoang-Loc Cao +3Multi-Agent Debate Verification-Triggered Multimodal
Precise Verification of Transformers through ReLU-Catalyzed Abstraction Refinement
May 14, 2026Hengjie Liu, Zhenya Zhang, Jianjun ZhaoNeural Network Verification Transformer Architectures
Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations
May 13, 2026Qisong He, Jinwei Hu, Xinmiao Huang +3Multi-Turn Large Language Model Conversations Verifier
MathAtlas: A Benchmark for Autoformalization in the Wild
May 13, 2026Nilay Patel, Noah Arias, Davit Babayan +7Autoformalization Mathematics
Neurosymbolic Auditing of Natural-Language Software Requirements
May 13, 2026Bethel Hall, William EiersFormal Verification Neuro-Symbolic Framework
LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving
May 13, 2026Guoxiong Gao, Zeming Sun, Jiedong Jiang +5Theorem Retrieval Strategies
NOVA: Fundamental Limits of Knowledge Discovery Through AI
May 12, 2026Salman Avestimehr, Ken Duffy, Muriel MédardEfficient Exploration Recursive Self-Improvement
Reward Hacking in Rubric-Based Reinforcement Learning
May 12, 2026Anas Mahmoud, MohammadHossein Rezaei, Zihao Wang +3Rubric-Based Reinforcement Learning Verifiable Rewards
Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers
May 12, 2026Haoyu Wang, Yuliang Song, Tao Li +5Classical Solvers Label Constraint Modeling
Information-Theoretic Generalization Bounds for Sequential Decision Making
May 12, 2026Futoshi Futami, Masahiro FujisawaGeneralization Bounds Information-Theoretic Limits
SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge Evaluation
May 12, 2026Xiaoyuan Li, Yuzhe Wang, Moxin Li +6Large Language Model Evaluation Verifier
Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem Proving
May 12, 2026Shuo Xu, Jiakun Zhang, Junyu Lai +2Theorem Step-Level Supervision
VERDI: Single-Call Confidence Estimation for Verification-Based LLM Judges via Decomposed Inference
May 11, 2026Jasmine Qi, Danylo Dantsev, Muyang SunLarge Language Model Judges Confidence Estimation
Natural Language based Specification and Verification
May 11, 2026Zhaorui Li, Chengyu SongLarge Language Model Safety Vulnerable Code
QUIVER: A Formal Framework for Quantifying Perturbation Propagation and Bifurcation in Compound AI Systems
May 11, 2026Prashanti Nilayam, Sankalp NayakLarge Language Model Pipelines Perturbation Propagation
Shields to Guarantee Probabilistic Safety in MDPs
May 11, 2026Linus Heck, Filip Macák, Roman Andriushchenko +2Shielding Safety Constraints
Verification Mirage: Mapping the Reliability Boundary of Self-Verification in Medical VQA
May 11, 2026Ruinan Jin, Beidi Zhao, Myeongkyun Kang +2Medical Visual Question Answering Verifier
LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
May 11, 2026Chiyu Zhang, Huiqin Yang, Bendong Jiang +8Large Language Model Safety Security Analysis
Hierarchical End-to-End Taylor Bounds for Complete Neural Network Verification
May 11, 2026Taha Entesari, Mahyar FazlyabNeural Network Verification Reachability
The Open-Box Fallacy: Why AI Deployment Needs a Calibrated Verification Regime
May 11, 2026Phongsakon Mark Konrad, Tim Lukas Adam, Ane Cathrine Holst Merrild +4Artificial Intelligence Governance Verifier
Coherency through formalisations of Structured Natural Language, A case study on FRETish
May 11, 2026Joost J. Joosten, Marina López Chamosa, Sofía Santiago FernándezFormalization Natural Language Queries
Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness
May 11, 2026Ivo Petrov, Jasper Dekoninck, Dimitar I. Dimitrov +1Mathematical Reasoning Proof
FormalRewardBench: A Benchmark for Formal Theorem Proving Reward Models
May 11, 2026Zeynel A. Uluşan, Burak S. Akbudak, Can S. Erer +1Theorem Reasoning Benchmark
FERA: Uncertainty-Aware Federated Reasoning for Large Language Models
May 11, 2026Ruhan Wang, Chengkai Huang, Zhiyong Wang +6Large Language Model Reasoning Reasoning Benchmark
CIVeX: Causal Intervention Verification for Language Agents
May 9, 2026Fabio RovaiCausal Intervention Causal Reasoning

May 22, 2026 · cs.AIJ/K move · Enter open · S save

Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems

Shubham Agarwal, Alexander Krentsel, Shu Liu, Mert Cemri+9

1UC Berkeley · 2Google · 3UC Santa Cruz

AI agents increasingly excel at generating, testing, and refining code. However, they fall short on tasks requiring formal guarantees of full coverage that testing alone cannot provide. Distributed systems are a prime example: properties such as consistency between reads and writes must hold under every possible interleaving of events. Mechanized formal verification can guarantee such correctness, but typically demands months to years of expert effort. As evidence, even SOTA coding agents (Codex with GPT-5.4 and Claude Code with Opus 4.6) succeed on only 2/7 distributed key-value-store specifications. In this paper, we present the first effective approach to addressing this gap, Inductive Deductive Synthesis (IDS), which jointly and incrementally synthesizes implementation and proof, and learns from failed attempts to systematically try promising strategies. Built as an agentic LLM system, IDS achieves 7/7 in about 6.8 hours and $106 per spec on average, roughly 200x faster than expert effort and 17% cheaper than SOTA agents. IDS further incorporates performance feedback into the same loop, yielding implementations up to 3x faster than published verified systems.

Formal Verification Mock-Interface Synthesis Artificial Intelligence Agents Key-Value

Open paper Ask about it PDF