Formal Verification

Follow this topic Ask about this topic

Latest papers 320

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

Aug 30, 2026

SkillForge: Compositional Skill Synthesis with Verification-in-the-Loop for Generating Formally Verified Dafny Programs

Generating formally verified programs from natural language remains challenging: existing approaches either produce code in a single pass without recourse when verification fails, or rely on open-ended agentic reasoning that is non-deterministic and opaque. We introduce SKILLFORGE, a framework that decomposes formal code synthesis into a library of atomic, reusable skills, each targeting a specific subtask such as specification inference, body synthesis, invariant generation, error diagnosis, or targeted repair, and defined by a prompt template, tool binding, and decidable success criterion. A verification-driven harness orchestrates these skills: it submits candidates to the Dafny verifier, diagnoses failures into structured categories, deterministically routes to the appropriate repair skill, and iterates until formal correctness is proved or a budget is exhausted. On a curated benchmark of natural language to Dafny specification pairs, SKILLFORGE substantially outperforms both state-of-the-art agentic approaches (including ReAct-style agents, MCTS-based repair, and RL-guided verification) and traditional iterative baselines, while requiring fewer tokens and lower latency. Ablation studies confirm that every skill contributes measurably, and the harness converges rapidly with the majority of programs verified on the first attempt.

Yanming Liu, Xinyue Peng, Jiannan Cao +2

Zhejiang University · Southeast University · MIT +2

LLM-Based Program Synthesis Program Synthesis Formal Verification

Aug 30, 2026

A Formal Analysis of Agent Payment Protocols

Agent payment protocols are emerging as a key transaction layer for autonomous commerce, enabling AI agents to purchase goods and services and execute payments on users' behalf. Unlike conventional payment flows, they distribute user intent, delegated authority, credential use, settlement, and fulfillment across multiple actors and stages, creating security dependencies that no single message or participant can enforce. Yet these guarantees remain largely implicit across evolving specifications, schemas, and reference implementations, with little systematic formal analysis. We formalize four representative agent payment protocols: x402, MPP, ACP, and AP2 in Tamarin. Using a common abstraction of the agent payment lifecycle, we construct source-grounded models that capture each protocol's roles, state, trust assumptions, and lifecycle transitions. Rather than assuming a complete property taxonomy, we use source-backed verification questions and counterexample traces to expose missing bindings, state constraints, and cross-stage correspondences, consolidating them into 18 shared security principles. Across 86 verification cases, our analysis reproduces 46 known or calibration cases and identifies 40 previously undocumented formal-consistency findings. For each retained violation, we isolate the missing protocol relation, construct a minimally strengthened reference model, and reverify the intended property. We further evaluate the new x402 findings across three implementations and validate ten representative findings through implementation PoCs, SDK/schema-level witnesses, and source-aligned executable traces spanning five security principles. Our results show that delegated authorization must remain consistent with its resulting economic and service effects across actors, states, and protocol stages.

Ke Jiang, Mohan Yu, Yuan Chang +4

Southern University of Science and Technology · Indian Institute of Technology · City University of Hong Kong

AI Agent Security Agentic Commerce Formal Verification

Aug 29, 2026

Explanations, Prompts, and Formalizations: Arguments for New Norms in LLM-Enabled Mathematical Research

As several mathematical conjectures have recently been settled using large language models (LLMs), the mathematical community has formulated norms and recommendations regarding the publishing of such results. These norms do not cover the disclosure of the prompts and precise software setup used to obtain those results, nor do they require that results be formalized in a manner that allows for machine verification. I argue that both of these are essential. In addition, since LLM-obtained results may be hard to understand, human authors have the responsibility to invent intuitive explanations.

Axel Boldt

LLM Mathematical Reasoning Formal Verification

Aug 29, 2026

Verification abundance, adjudication scarcity: what happens to mathematical knowledge when proof checking becomes free

In May 2026 an OpenAI model produced a counterexample to the Erdős unit distance conjecture. Five mathematicians published a human-verified version the same day, and the result entered the literature within weeks. In August 2026 the same laboratory published ten mathematical and theoretical computer science results, each accompanied by a machine-checkable Lean 4 certificate with no unproved steps. Four weeks later, one remained the subject of an unresolved dispute over whether its formalization meant what it claimed. We argue that this difference is structural. We distinguish three layers of verification: derivational validity, which a kernel checks; representational fidelity, whether the formal statement means the intended question; and epistemic significance. Only the first is mechanizable. Making it effectively free therefore does not eliminate verification work but shifts the burden to layers dependent on scarce expert attention. Measurements of the August corpus illustrate the shift. The kernel-checked proofs total 20.6 MB, while the statements requiring human audit total 55.6 KB, a ratio of 379 to 1. Yet those statements contain 218 bespoke definitions rather than relying on community-vetted ones. The audit surface is therefore small in volume but irreducibly expert. We argue that machine checking produces verification abundance while leaving adjudication scarce. We propose a six-category taxonomy of representational mismatch, a disclosure schema for machine-generated mathematical claims, and implications for software, cryptography, and regulated decision systems.

Maher Kallel, Mohamed El Louadi

Institut Supérieur de Gestion, Université de Tunis 41 rue de la Liberté, Cité Bouchoucha, 2000 Le Bardo, Tunisia

Formal Verification Mathematical Reasoning Human-in-the-Loop Evaluation Automated Theorem Proving

Aug 28, 2026

An Enclosed Mode Is a Gauge Choice: Topology Relative to Reach in Certified Code World Models

A code world model accepted by a sampling gate can be exactly right on everything the gate can see and arbitrarily wrong beyond it. We characterize what a certified model can know, and what its errors can cost, when the omission is an annular freeze mode enclosing an unreachable interior. The gate quotient makes the question precise: acceptance-with-certainty determines the model exactly on the reachable query set; beyond reach is gauge. On a minimal ring instrument we prove the extreme case (a wrong-topology filled-disc artifact unfalsifiable by any sampling gate and bitwise harmless at play) and measure, with LLM synthesis across three model families, how one knob (a channel of width gamma) walks the same artifact through three regimes: unfalsifiable-and-harmless, falsifiable-and-costly, and instantly falsified. Three principles organize the empirics. First, danger is topology relative to reach: a channel the planner can use collapses the blind model's exploitation (play cost 1.09 to ~0 over a knee at gamma ~ 0.1), while a hidden channel with the same first Betti number keeps it at full strength (1.12). Second, repair is parameter-bound and sensor-bound: no family recovers the region from outside evidence; from inside, models pose the right topology but cannot pin its parameters, and the posed topology tracks the guiding persistent-homology summary's wrong beta_1 (a sensor with a measured geometric resolution limit), not the truth. Third, mitigation must match the error's dimension and direction: point fences fail against the one-dimensional boundary, a dimension-matched persisted fence collapses exploitation to a two-lesson transient (0.999 to 0.058), and the dual freedom certificate collapses the invented-mode failure symmetrically (1.769 to 0.029). In n dimensions the shell makes misidentification near-certain while the danger stays fully exploitable: the two axes are independent.

Javier Aguilar Martín

AGILabs

World Models World Model Evaluation Model Misspecification Formal Verification Reachability Analysis

Aug 26, 2026

Formal, Executable and Explainable Runtime Monitoring of Spoken Air Traffic Control Operational Procedures

Air traffic control procedures are executed through spoken exchanges between controllers and pilots. These interactions are essential to the safety of air transportation: failures in their execution can create severe operational hazards, as evidenced by past fatal accidents. Assessing whether an instruction has been followed requires relating what was said to the aircraft concerned, its state, and the obligations that pilots must meet. We present a runtime verification framework that monitors such procedures by checking controller-pilot exchanges, surveillance data, and onboard observations. The framework parses radio communications into events linked to the entities they concern and merges them with surveillance and onboard observations into a time-stamped trace. The ICAO-derived obligations as formalized as temporal formulas with explicit time bounds and evaluated over execution traces. Every violation is reported along with the breached obligations and the observations that support the verdict. With real traffic, the complete pipeline reaches an F1 of 0.85 against blind human-annotated violations; in 1,495 synthetic situations derived from two public corpora, the monitor logic returns the expected verdict in every case. In two historical accidents reconstructed from official investigation reports, the monitor identifies the same procedural deviations documented by the investigators.

Roberto Luvini, Giacomo Longo, Alessandro Armando +1

Department of Informatics, Bioengineering, Robotics, and Systems Engineering (DIBRIS), University of Genoa, Italy · CASD - University School of Advanced Defense Studies, Rome, Italy

Runtime Verification Air Traffic Management Formal Verification

Aug 25, 2026

FLARE: Verifying MILP Reformulations with LLM-Based Theorem Proving

Mixed-Integer Linear Programming (MILP) is a fundamental tool for combinatorial optimization with extensive real-world applications. A central challenge is designing computationally efficient MILP formulations. Large Language Models (LLMs) offer new opportunities to automate the modeling process, from deriving formulations to strengthening them. Reliable automation requires robust methods for verifying that proposed formulations preserve the underlying optimization problem. However, existing approaches evaluate formulations numerically and fail to reason about general problem instances. We resolve this limitation by introducing a constructive definition of MILP reformulation that can be formalized in Lean and machine-checked. We develop FLARE (Formulation-Level Automated Reformulation Evaluation), a method that uses an LLM-based agent and the Lean proof assistant to verify proposed reformulations against a reference formulation. To evaluate our approach, we introduce FormulationBench, a challenging dataset of 20 problems and 109 formulations. FLARE outperforms existing methods, with 100% accuracy on the NP-hard subset of FormulationBench. Furthermore, FLARE produces a machine-checkable certificate for every reformulation it accepts. For cases where formal guarantees are not necessary, we introduce FLARE-NL, a fast and cheap LLM proxy that matches FLARE's accuracy but produces no certificate. These methods enable reliable verification in automated optimization modeling.

Henry Robbins, Connor Lawless, Madeleine Udell +1

Stanford University

Mixed-Integer Linear Programming Formal Verification

Aug 21, 2026

AI with Authority, from Application to Silicon

For sixty years, machine verification has been a major cost overhead, affordable only for exceptional artifacts. Here we report that generative AI inverts this relationship: at AI speed, machine verification is not only economical but essential to productivity --- it is the incorruptible referee that lets one person safely direct autonomous machine work at scale. In five weeks, one researcher on consumer AI subscriptions directed a small fleet of AI agents from application code, through a verified compiler and executive, to a RISC-V processor taped out on a community silicon shuttle; no proof passed through human review, and no RTL was written by a human. The working discipline --- the Salt method --- rests on a proof kernel no hallucinated proof can pass: mathematical claims travel between agents as kernel-checked artifacts, and human attention is reserved for statements, designs, and rulings. Verification is stated link by link, from the Lean 4 kernel to SAT-checked equivalence at the silicon boundary. We publish the complete accounting: theorem provenance, a pre-registered token meter, floor-bounded human time, and an error ledger whose catch numbering runs to #256 --- a monotone counter over the mathematics campaign's append-only flags ledger, maintained 2026-07-07 to 2026-07-20 (one number, #79, was never assigned; later catches are recorded un-numbered) --- against zero incorrect proofs reaching the record.

Jason Hickey

Karyk

Formal Verification AI Agent Reliability Formal Hardware Verification

Aug 21, 2026

BeTaL-GBI: Admission-Aware Benchmark Tuning and Full-Stack Verification of Geometric Belief Interfaces

A verification substrate is more credible when exposing errors in its own claims, not just model outputs. GBI-DCSE v3 falsified an architectural claim: the reported Fisher value epsilon ~ 0.066 satisfies the kappa^2 <= 10^4 budget only on the slice [epsilon, 3, 4, 5], while the full box [epsilon, 20]^4 requires epsilon ~ 0.326472. This erratum highlights whether an enterprise verification architecture can isolate interface failure, task competence, policy admissibility, and control integrity while keeping claims auditable. BoundaryBench v0.1 established the baseline: Qwen3-4B-Instruct-2507 completed 768 frozen executions, but 0% cleared the contract (369 failed parsing, 399 failed validation), limiting downstream selectivity metrics. This companion study evaluates three successive improvements. First, BeTaL-GBI v0.2 applies Benchmark Tuning with an LLM-in-the-loop over 2,218,750,380 grid points, separating format admission from conditional performance (rho_adm = N_admitted/N; rho_task = N_verified/N_admitted). Following schema repair, a model-free feedback search achieves a 2.87% mean held-out target gap, outperforming non-feedback baselines (13.61%, 11.46%). Second, GBI v2 swaps static keys for a reference-independent witness state W and policy P. Across 512 synthetic tasks, a 16-gate policy detects all 116 injected severe contradictions and accepts all 99 clean records (broad denominator: 4.27%). Hallucinator and evidence-forger surrogates are blocked with zero silent promotions. Third, GBI-DCSE v3 maps 99 claims to machine-readable evidence: 95 of 96 testable claims pass, with 148 standalone checks executed without failure. The harness exercises signed ledgers, PBFT quorums, and enclave forgery across 62 configurations. Under synthetic conditions, GBI-DCSE is a selective, policy-versioned, self-auditing test and routing substrate.

Alvin Spivey, Yu Huang

Light Imaging Technologies, Inc.

Formal Verification Benchmark Auditing Benchmark Design Benchmark Validity AI Agent Auditing

Aug 20, 2026

Bounded Loops: Pre-Run Spend Bounds, Proved Termination, and Verified Completion for Agent Harnesses

In mainstream agent frameworks, a step ends when the agent's own output says it has finished. Durable-execution platforms bound retries and time, but their checker conventionally lives in the same codebase as the work: a discipline the deployment is trusted to keep, not a property the harness enforces. We state what an agent harness must guarantee, prove it, and build the instrument that measures whether a harness delivers it. A bounded loop is a worker, an independent gate the worker cannot write to, and a declared budget; a bounded-loop graph composes them with a repair relation that lets a downstream failure re-run a finished upstream node. Three guarantees follow. It finishes: termination holds under repair, with the worst-case attempt total in closed form, if the repair budget is global not per node. It does not drift: no node reaches DONE without a gate verdict in an append-only hash-chained ledger, proved from control flow, since repair leaves no topological order to induct along. It does not overspend: the ceiling is enforced inside an attempt, not between attempts. Gates are measured against a two-tier held-out mutant corpus. We characterise two classes that let a sound-looking check pass anything: vacuity, satisfied by the absence of the thing checked, and self-attestation, where the subject supplies the value the check is applied to. On a 69-loop catalogue the instrument found 47 vacuous gates in shipped, reviewed code. Against the repaired gates it reports no false accepts over 209 destroying mutants (

α\le 1.8\%

, Wilson 95%); that figure is saturation, not quality: freezing the gates and applying a fresh operator family recovers a 23.3% false-accept rate where the exhausted corpus reported none. A rate belongs to a specific gate; the apparatus, not our number, is the contribution. Engine, catalogue and corpus are Apache-2.0.

Varun Pratap Bhardwaj, Garima Singh, Arun Pratap Bhardwaj

Qualixar / Independent Researcher, India · Independent Researcher, India

LLM Agent Harnesses Runtime Enforcement for AI Agents Formal Verification

Aug 20, 2026

Escaping the Quicksand: A Call to Arms

Computing has been an astonishing success - but the accumulated technical debt exposes us all to huge costs in business and societal risk. For 75 years, we've built systems to prose specifications with test-and-debug development. That works well enough for industry to thrive, but it's an expensive and ineffective feedback loop, and leaves everyone relying on shaky foundations. Now, AI-enabled engineering is amplifying the success by reducing coding costs, but also amplifies the risks, by rapidly increasing technical debt, and by automating detection of the vulnerabilities therein. How can we do better? Research has long pursued mathematical proof of correctness, which, unlike testing, can cover all cases. This too has advanced massively, but it remains hard to apply, both technically and because of a deep-seated cultural disconnect. Instead, we argue for a pragmatic approach to flexible combinations of testing, specification, and proof, that provides more effective feedback loops for both AI and human development. Most simply, one can incrementally co-develop executable-as-test-oracle partial specifications alongside conventional prose descriptions, code, and tests. This clarifies design and makes testing much more discriminating. Developers can and should do it today. Or, even better, one can use specifications that support the full gamut of testing, property-based testing, symbolic execution, and proof. This enables a range of intertwined feedback loops, again both for AI and humans, from cheap testing to more expensive proof. However, making it really practical needs semantics infrastructure: specifications and tooling for the main programming languages and other abstractions, which we now more-or-less know how to build, but which is not yet in place. We call the community to arms to create and deploy it - to enable a future built on firmer ground.

Peter Sewell, Jean Pichon-Pharabod

University of Cambridge, UK · Aarhus University, Denmark

Software Engineering Formal Verification Automated Software Testing

Aug 19, 2026

Grading the Graders: Verification Autonomy Levels (L0-L5) for LLM Reasoning

Large language models (LLMs) are increasingly paired with verifiers (step checkers, self-consistency filters, tool-based fact checkers, formal proof assistants) that claim to detect the model's errors. Yet the verification literature uses the word "level" to mean at least five different things: verification granularity, concept abstraction, risk tier, system-stack layer, and the epistemic source of the ground truth. We propose Verification Autonomy Levels (VAL), a meta-standard that classifies any verification scheme along a single axis: where does the verification spec come from, and what does the verdict guarantee? VAL ranges from L0 (LLM self-declaration; no deterministic anchor) through L2 (objective ground truth; correctness only) to L3/L4 (decidable systems with single-property or domain-level completeness), with L5 impossible in the unrestricted case. Central to VAL is the completeness blind spot: substitution- and sampling-based verifiers can confirm that proposed candidates hold, but cannot prove that no candidate was missed. We further identify a dichotomy the literature has not stated: completeness is reachable only for formally specifiable properties, whereas empirical open-world verification (fact-checking, diagnosis) caps at anchored correctness (L2). We document this gap empirically across four domains (symbolic mathematics, behavior monitoring, medical diagnosis, code generation) and in the strongest formal-verification baseline in our survey. We show that granularity, concept hierarchy, risk, and system stack are orthogonal to VAL, resolving a conflation across 17 surveyed papers. Code and the full literature assessment are released on Zenodo (DOI: 10.5281/zenodo.23120985).

Yajie Yin

LLM Answer Verification LLM Evaluation Formal Verification LLM Auditing

Aug 19, 2026

Formal Verification of Romanov's Triplet Logic: A Verified Filter for Sliding-window 3-CNF with Application to Structured Formulas

We present the first mechanised formalisation of Romanov's Triplet Logic (TLS) in the Rocq proof assistant. TLS is a combinatorial framework originally motivated by Boolean satisfiability, based on triplet structures and a filter that we call Simple Vertex Intersection (SVI). We formalise the core of TLS, including its translation from 3-CNF, the clearing procedure, and the SVI algorithm. For the well-formed sliding-window fragment, we prove explicit polynomial-time bounds for the filter stages and verify the translation and intersection operations. Our main contribution is a precise correctness boundary: for general formulas, SVI non-emptiness is necessary but not sufficient for satisfiability; for aligned structures, we prove a full bi-implication, extended to systems of structures. We also formalise the grouped-window translation and provide a formal counterexample to its completeness. We introduce VFR (Verified Filter for Romanov's triplet logic), an extracted OCaml prototype that implements a verified decision procedure for the sliding-window fragment and a sound filter for general 3-CNF, with a Python runtime and Docker packaging. Benchmarks corroborate the predicted behaviour, and the complete toolchain is available as a curated Zenodo artifact. The Rocq development comprises over 23,000 lines of code, with 424 proved lemmas and no unproved assumptions.

Dmitry V. Alexandrov

HSE University, Moscow, Russia.

Constraint Satisfaction Formal Verification

Aug 16, 2026

$S^3$ : A Smooth Simulation Surrogate for Optimizing Discrete Abstractions of Dynamical Systems

Intelligent systems are increasingly deployed in safety-critical settings with black-box controllers, including neural networks. The properties and behaviors of these end-to-end systems can be studied with abstraction-based methods that replace them with simpler finite models. Constructing such abstractions requires balancing the soundness of over-approximating the dynamical system against conservatism, which manifests as spurious or excessive nondeterministic behaviors. Bi-simulation theory provides principled metrics for characterizing these relationships, but does not prescribe how to construct sound abstractions with minimal conservatism. We fill this gap with a smooth simulation surrogate (

S^3

) --- a differentiable objective that approximates the reverse simulation metric used to quantify conservatism. Combined with Taylor model-based reachability,

S^3

enables gradient-based optimization of abstraction parameters while preserving soundness by construction. We evaluate this optimization pipeline on three case studies. Our results show that

S^3

is strongly correlated with the reverse simulation metric, is computationally faster, and serves as an effective objective for reducing abstraction conservatism.

Jordan Peper, James Mathias Gast, Vignesh Nanduri +3

University of Florida

State Abstraction Surrogate Modeling Surrogate-Assisted Optimization Formal Verification

Aug 16, 2026

RDFdL: Integrating RDF with Differential Dynamic Logic

Knowledge graphs modeled in RDF are powerful for describing static knowledge, but they cannot capture or reason about the dynamic behavior of physical systems, e.g., systems described by differential equations, which is a critical gap for AI-driven cyber-physical systems. To solve this, we propose RDFdL, a framework that integrates RDF with Differential Dynamic Logic (dL) to represent and reason about both static knowledge and the continuous dynamics of physical systems. For the dynamic part, we syntactically represent differential equations and ranges in the state space in RDF and SHACL and provide semantics using a translation to dL. Linking RDF and dL through their shared foundation in first-order logic achieves a unique integration: verification results for safety and reachability properties in the dynamic logic domain become available as entailment to SPARQL queries over RDF data. We implement the pipeline using Apache Jena for ontology-driven RDF reasoning and KeYmaera X, the theorem prover for dL, and sketch its applicability in manufacturing.

Yuyang Li, Lukas Kubelka, Julia Butte +1

Institute AIFB, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany

Knowledge Graphs Formal Verification Cyber-Physical Systems

Aug 15, 2026

LLM-based Framework for Generating and Verifying Parallel DEVS Statecharts

The development of models demands sound modeling and simulation knowledge as well as domain knowledge. Every model should accurately represent a system's dynamics and be verifiable. Toward this objective, this research introduces an agentic PDEVS-LLM framework to assist human modelers in generating and verifying PDEVS statecharts for behavior modeling of atomic Parallel Discrete Event System Specification (PDEVS) models. The framework supports (re)generating plausible facts from a system description prompt using the agentic LLM used for generating plausible facts. Inconsistencies in plausible facts lead to incorrect PDEVS statecharts having logical structure and behavioral inaccuracies. A controlled-correction mechanism is developed to verify the logical consistency of the plausible facts. The agentic LLM is used to generate key behavioral conditions from the system description prompt. The plausible facts are then verified against the behavioral conditions using propositional logic entailment for a finite number of times. The verification results enable the generation of modification prompts that can reduce errors in generated plausible facts, resulting in more accurate PDEVS statecharts. To verify a statechart's logical correctness, its Timed Automata counterpart is manually created and verified for deadlock and reachability properties. The human modeler may regenerate plausible facts and PDEVS statecharts iteratively and incrementally. A basic correctness metric is introduced to quantify the completeness and accuracy of the expected behavioral traits of the PDEVS statechart models. A collection of example systems with varying levels of complexity is developed to demonstrate the capabilities and limitations of LLMs. The evaluation of the proposed verification mechanism shows a substantial improvement in the logical consistency of generated statecharts.

Vamsi Krishna Vasa, Hessam S. Sarjoughian, Edward J. Yellig

Arizona State University, Tempe, Arizona, USA · Intel Corporation, Chandler, Arizona, USA

Formal Verification

Aug 14, 2026

MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement

Autoformalization is commonly framed as translating natural-language mathematical statements into machine-verifiable formal languages such as Lean 4. However, faithful formalization requires more than translation. Models must map mathematical concepts to the complex hierarchy of types and definitions in formal libraries such as Mathlib, while ensuring that generated statements preserve the meaning of the source propositions. Existing approaches struggle because they rely heavily on the model's parametric memory for library-specific knowledge, while common data construction pipelines often resort to filtering single-pass outputs and lack mechanisms for feedback-driven revision. To address these challenges, we introduce MathForm, an autoformalization framework for constructing verified training data through Mathlib knowledge retrieval and verification-guided iterative refinement. Before generation, a retrieval planner gathers relevant definitions and existing formalizations from Mathlib to guide the formalization generator. Generated statements are then revised using compiler diagnostics and semantic-consistency feedback. Using this framework, we construct FormalVerse, a Lean 4 dataset containing approximately 367K verified examples across diverse mathematical domains and sources. We then train MathForm-8B through supervised fine-tuning followed by reinforcement learning. Across six benchmarks, MathForm-8B achieves average Pass@8 rates of 88.06% under Syntax Check (SC) and 72.37% under Consistency Check (CC), outperforming multiple specialized 32B autoformalizers. On the challenging FATE-H and FATE-X subsets, it attains CC pass rates of 63% and 37%, exceeding the strongest specialized baselines in both cases.

Lushi Pu, Weiming Zhang, Xinheng Xie +7

ModelBest Inc. · Tsinghua University

Autoformalization Formal Verification Knowledge Augmentation for Language Models LLM Self-Refinement

Aug 13, 2026

Vero: Can AI Agents Build Formally Verified Software Repositories?

AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an agent produces both an implementation and a machine-checked proof of its specification, offers a stronger path toward trustworthy AI-generated software. Existing benchmarks in this direction either focus on individual functions or only evaluate proof generation with provided implementations. It is still an open question whether agents can make coherent implementation and proof choices across real multi-module codebases. To bridge this gap, we introduce Vero, the first benchmark to evaluate joint implementation and proof synthesis at the repository level. Vero contains 43 multi-module instances sourced from real-world repositories spanning Python, Dafny, Verus, and Coq, and covering diverse domains from cryptographic protocols to distributed systems. Each instance consists of a multi-module Lean 4 repository with predetermined API interfaces, manually curated formal specifications, and reference implementations, supporting both proof-only and code-and-proof evaluation modes. To improve benchmark reliability, Vero also includes an audit mechanism where agents are allowed to formally prove unsatisfiability of provided specification or incorrectness of reference code, which surfaces and corrects latent code and specification errors during curation. We evaluate frontier coding-agent configurations with Lean toolchain access. The strongest agent fully solves only 27 of 43 instances and closes no specifications on the hardest repositories. Vero provides a concrete testbed for measuring progress toward repository-scale verified software synthesis, where current agents still fall short. We release the benchmark, curation pipeline, and evaluation harness at https://github.com/sunblaze-ucb/vero.

Zhe Ye, Hantao Lou, Yuechun Sun +8

1UC Berkeley · University of Chicago · 3California Institute of Technology +3

Code Generation Formal Verification AI Agent Benchmarks Repository-Level Code Generation Code Generation Benchmarks

Aug 13, 2026

A Contract-Grade Verifier for LLM-Generated GPU Kernels, and a Native Blackwell Backward for the Gated-Linear-Recurrence Family

Systems that generate GPU kernels with language models report high correctness rates. Those rates come from a single loose test: run the kernel on a few random inputs at one fixed shape and accept it if the output is close to a reference. A kernel can pass that test and still be silently wrong. It can return an ordinary number where the true answer is a NaN or an infinity, differ from run to run, break when the shape changes, or accumulate in fp16 where the reference keeps an fp32 total. We build the instrument that checks correctness properly: a contract-grade verifier of twelve adversarial gates, each a property a correct kernel must satisfy, several of them tolerance-free, so no choice of threshold can explain a failure away. Aimed outward, the verifier audits 2,638 machine-generated kernels that a public system's own harness had already accepted as correct. It finds 39.5% broken beyond any tolerance argument and 62.1% carrying at least one violation. The field's standard test accepts 1,487 kernels the verifier rejects, against only 14 the other way. We defend the finding four independent ways: a 7/7 positive control, a threshold-calibration sweep, 98.5% agreement with the reference benchmark's own correctness code, and a stratified hand-audit. Aimed inward, the verifier judges a kernel of our own: the first native Blackwell tcgen05 training backward for the gated-linear-recurrence (GDN) family, including the reverse-state stage the field still runs on a fallback. We establish its correctness independently, against a double-precision oracle, and train five family members through it. The correctness signal behind reported progress in kernel generation is far weaker than the numbers suggest, and a set of tolerance-free contracts would close most of the gap.

Rishi Shah, Rishav Shrestha

E3A Healthcare

Automated Software Testing Formal Verification GPU Kernel Generation

Aug 11, 2026

Self-evolving network verifiers

Symbolic network verifiers can reason about correctness across vast spaces of routing inputs and failures, but only for the protocols and features an expert has encoded by hand. Creating and maintaining a faithful model of the control plane is both difficult and never-ending, since no written source specifies perfectly what a network does: vendor implementations deviate from the RFCs, and behaviour shifts with releases. The burden of constant upkeep ultimately keeps verification out of many networks that need it. We argue that the model should instead evolve automatically to faithfully capture the actual network behaviour. To achieve that, we leverage the only source that specifies it unambiguously: the router software itself. In a counterexample-guided loop, a coding agent proposes extensions to the verifier's symbolic encoding, while a trusted oracle (e.g., emulated routers) supplies the ground-truth routing state. The agent iteratively refines the network model using each disagreement with the oracle. As early evidence, a prototype of this system taught a 3,000-line SMT-based verifier three features it did not support: OSPF areas, BGP route reflection, and L3VPN over EVPN, converging autonomously on models that match the oracle, even noticing vendor-specific behaviour. Automating model growth shifts the hard problem from writing verification systems to systematically testing them; we propose a research agenda for trusting and harnessing automatically evolved verifiers.

Ioannis Protogeros, Tibor Schneider, Laurent Vanbever

ETH Zürich Zürich, Switzerland

Counterexample-Guided Refinement Formal Verification Self-Evolving Agents

Aug 11, 2026

Reward-Oracle MCTS for Formal Theorem Proving: Sample-Efficient Search and the Need for Kernel-Level Proof Auditing

Formal theorem proving with large language models remains challenging due to the difficulty of navigating large proof search spaces efficiently. Existing tree search approaches either feed verbose compiler error messages directly into the generation context, increasing context usage during search, or employ non-standard evaluation protocols that prevent direct comparison with established baselines. We propose a three-role Monte Carlo Tree Search (MCTS) framework that treats the Lean 4 compiler purely as a reward oracle using compiler output as a scalar signal for UCB-guided tree updates without feeding error content into the generation context. Our framework decomposes proof search into three roles: a generator for proof attempts, a decomposer for subgoal decomposition, and a critic for subgoal quality evaluation. We evaluate across 4 benchmarks spanning competition mathematics and physics (MiniF2F, PutnamBench, LeanPhysBench, PhysLeandata) with three prover models at standard proof attempt budgets (PAB@16 to PAB@256). Our method achieves 87.1% on MiniF2F with Goedel-Prover-V2-8B at PAB@256 and solves 26/659 PutnamBench problems at PAB@32 surpassing base sampling 18/659 at same proof attempt budget. Through an exhaustive axiom-level audit of every compiled proof, we further identify reward hacking in search-based theorem proving: DeepSeek-Prover-V2-7B produces proofs on PutnamBench that pass compilation and the standard sorry-token scan while depending on sorryAx. The audit removes 4 and 8 such proofs from whole-proof sampling at PAB@32 and PAB@128, and 11 and 19 from MCTS. We do not attribute these counts to the search procedure; we report them to establish that kernel-level auditing is necessary for compiler-verified evaluation.

Bodla Krishna Vamshi, Haizhao Yang

University of Maryland, College Park

Lean Theorem Proving Formal Verification Monte Carlo Tree Search Reward Hacking

Aug 10, 2026

P $^{3}$ : Joint Program-and-Proof Planning for Verified Code Generation

Verified code generation asks a large language model (LLM) to generate both an executable program and a machine-checkable proof that the program meets a formal specification, promising software that is correct by construction. The de facto workflow decouples the two halves of the problem: first synthesize a program, then attempt to prove it correct. We observe that this sequential pipeline can be both ineffective and inefficient in practice. A program generated without anticipating its proof can be subtly incorrect or structurally difficult to verify, forcing the LLM into brittle repair loops that alternate between patching the code and patching the proof. Inspired by Dijkstra's view that a program and its correctness argument should be developed hand in hand, we propose

P^3

, an LLM-based agentic workflow that first derives a unified program-and-proof plan from the specification, then elaborates the implementation and proof scaffold under this shared plan. To evaluate verified code generation in realistic settings, we further introduce Lean4Commit0, a repository-derived, library-level benchmark built by extracting core APIs from real-world software repositories and translating their requirements, including relational specifications across APIs, into Lean tasks. Using four frontier LLM backends, we evaluate

P^3

on Verina, AlgoVeri, and our Lean4Commit0 benchmark, where it achieves the highest solve rate in every benchmark--model setting. Compared with the stronger baseline, it improves solve rates by 4.6--11.2 percentage points and reduces per-task API cost by up to roughly 40% and wall-clock time by up to roughly 37% on the difficult subset of each benchmark. A targeted ablation further shows gains of 3.3--8.3 points over implementation-only planning, isolating the benefit of planning the program and proof jointly.

Zenan Li, Ziran Yang, Peiyang Song +2

1Apodex · 2Princeton University · 3Caltech +1

Code Generation Formal Verification Agentic Code Generation Code Generation Benchmarks

Aug 8, 2026

Directed Neuro-Symbolic Stochastic Execution for Verification of Distributed Parallel AI Programs

Distributed parallel Artificial Intelligence (AI) programs expose reliability gaps that conventional testing cannot close: parallel executions are non-deterministic, and AI workloads bring high-dimensional inputs and non-linear operations that defeat fuzzing and symbolic execution in isolation. We present Directed Neuro-Symbolic Stochastic Execution (DNSSE), a hybrid testing framework that couples schedule prediction guided by a Large Language Model (LLM) with symbolic constraint solving and coverage-guided stochastic mutation. We model distributed AI executions as non-deterministic transition systems, specify correctness in linear temporal logic, and prove soundness, bounded completeness, and probabilistic completeness of the hybrid solver, together with an expected-cost analysis of LLM-guided schedule exploration. A scalable implementation on PyTorch and Ray detects 2.9% more concurrency bugs than the strongest baseline and raises average branch coverage from 68.6 % to 91.6 % across five realistic distributed AI benchmarks.

Gautham Koorma, Vikas Sharma, George Edwards +1

Quandary Peak Research, Los Angeles, CA, USA

Automated Software Testing Formal Verification Neuro-Symbolic AI

Aug 6, 2026

Runtime Observability for Heterogeneous Attention Memory

Modern models no longer keep a plain KV cache: latent caches, learned sparse selectors and recurrent states each carry the model's memory in a different form, and each fails differently under compression. We give a runtime observability contract that covers all four memory classes with three operators, instantiate it on six model configurations across five architecture families, and compose the per-stage bounds into an executable request-level risk ledger. Contracts carry their error metric as a type -- composition is only defined when metrics match, and this check rejected our own first composed chain; the repaired chain crosses metrics through two proved bridges, and whatever no formal system can certify is measured instead, dropping the composed tier to empirical automatically: every claim is certified, partially certified, or empirical, composition inherits the weakest tier, and the tier is decided by the machine. Replayed over

12.4

M entry reads and run under eight-way concurrency with per-request budgets and fail-closed identity attribution, the ledger quantifies the honest trade-off on today's witness and holds its risk budget with zero violations. A fused always-on probe observes a declared one-layer subset under CUDA graphs inside the serving noise floor. Applied to a served DeepSeek-V4 stack with a packed compressed-KV prototype, the same machinery localizes a silent corruption to a precise structural boundary -- exact in the eviction-free, identity-isolated regime, with every observed failure in an eviction or slot-reuse regime -- through a machine-adjudicated discrimination campaign whose calculus rejected two of our own confounded inferences along the way. All artifacts, guards, and the Lean development are released at https://github.com/metask-ai/witprobe-attention-memory; every number in this paper regenerates from the shipped artifacts by one command.

Fanzhe Wei, Li Liu, Ziyang Wang +1

Metask Lab

KV Caching LLM Auditing LLM Memory Formal Verification KV-Cache Compression Runtime Verification

Aug 4, 2026

Resume Means Resume: A Machine-Checked Conformance Contract for Checkpoint, Interrupt, and Resume Semantics in Workflow Persistence Layers

A framework that persists execution state so a run can be interrupted, survive a crash, and continue must decide what a resume means for effects that already happened. Five widely deployed agent workflow frameworks answer differently, none exposes a machine-checkable contract, and measured behavior violates even the fragments they state. The RESUME CONTRACT states six properties over the persistence API (prefix continuation, effect exactly-once, fork determinism, checkpoint validity, consume-once, recovery determinism), plus fork-intent and liveness obligations. A TLA+ model checks a reference semantics exhaustively, unchanged at scaled bounds (7.4 million states), and the reference conjunction is additionally TLAPS-proved unbounded (196 obligations); a 39-cell fault matrix and two companion modules yield the separating models independence requires. A deterministic, LLM-free harness measures them at pinned releases. LangGraph 1.2.9 durably records a second resume value and never consults it, persists schema-invalid state silently, and re-executes durably recorded work after a real SIGKILL: exactly-once across interrupts, at-least-once across crashes, on one API. CrewAI 1.15.2 re-executes completed effect-bearing methods against its written claim; pydantic-graph 1.x cannot resume after a mid-node crash; no two probed frameworks share a conformance profile. Consume-once holds sequentially and fails under concurrent delivery: k processes resuming one parked interrupt fire the gated effect k times, saturation 1.0 in 36 of 40 cells, and the failure crosses hosts. REMIT, a reference sequencer whose Verus-verified recovery core is line-identical to the shipped executable, repairs the fork and validity cells. The cross-process cell is repaired at the read path: an opt-in gate claims consumption in the shared store, serving one racer and refusing the rest before any node executes.

Sajjad Khan

independent researcher, London, UK

Formal Verification LLM Agent Reliability

Aug 4, 2026

Formal Verification of Agentic Systems over Operational Data

Agentic systems driven by large language models (LLMs) are increasingly deployed in real-world workflows where they act on persistent operational data. Before deployment, these systems need to be verified against business requirements that govern workflow execution and data evolution. However, existing approaches do not provide such system-level guarantees, as they mainly constrain or analyse behaviour at the agent's interface level. We study here the verification of agentic systems comprising a single LLM and a tool orchestration harness over relational operational data. We formalise them as Stateful Tool-Enabled Agentic Deployments (STEADs), give their semantics, define the problem of verifying them against First-Order Computation Tree Logic (FO-CTL) specifications, and show that it is undecidable. We identify sufficient conditions for exact preservation of FO-CTL specifications under a finite-domain restriction, over which verification is PSPACE-complete. The key requirement is that renaming opaque identifiers in the data must correspondingly rename the selected tool calls. We show that LLM-driven agents can violate this condition and introduce a canonical deployment wrapper that guarantees it for arbitrary base agents while preserving already-equivariant behaviour. We prove that computing canonical representations required by this construction is graph-isomorphism-hard. Finally, we illustrate our framework on an LLM agent orchestrating a case-management workflow.

Alejandro J. Mercado, Alessio Lomuscio

Imperial College London · Safe Intelligence

Formal Verification LLM Agent Harnesses LLM Agent Reliability

Aug 4, 2026

GenOS: Compositional Certificates for Semantic Robustness in AI Code Generation

AI coding agents are stochastic workflows: prompts are interpreted, artifacts are sampled, validators produce observations, and orchestrators commit or repair. Small prompt or specification changes can therefore alter program-behavior distributions even when the texts appear synonymous. Existing systems evaluate correctness, but lack a compositional criterion for safely replacing a prompt, contract, generator, or program inside a complete agentic workflow. We introduce GenOS, a probabilistic operational semantics for this replacement problem. Each layer is modeled as a Markov kernel, and each interface carries an observer-relative equivalence. We prove that equivalence-compatible kernels descend to quotient classes and that quotienting commutes with distributional extension and sequential composition. Hence, equivalent prompts induce equal probabilities for all downstream equivalence-closed events, including verified commit. We also establish workflow bisimulation, guarded-commit safety under sound validation, total-variation non-expansiveness, and an additive robustness bound that attributes approximation error to individual pipeline layers. An executable insertion-sort audit instantiates the theory with natural-language paraphrases, a formal contract, six programs, two observers, and exhaustive execution on 121 inputs. Equivalent prompts yield identical code-class and commit distributions; a prompt assigning 5% probability to an in-place contract is distinguished by a mutation observer, while downstream distances remain within the predicted bound. Across 20,000 randomized finite-kernel trials, no exact or approximate law is violated. GenOS is model-parametric: compatibility is a measurable property to test, not an assumption about language-model behavior.

Corrado Priami

Dipartimento di Informatica, Università di Pisa and Fondazione Start Attractor

Code Generation Formal Verification Agentic Code Generation

Aug 4, 2026

Leveraging System-Level Observations to Inform Bayesian Learning of Model Parameters for Quantitative Verification

Combining Bayesian learning and quantitative verification is a powerful toolset for analysing key quantitative properties of software systems, like reliability and response time. However, the accuracy and robustness of verification results strongly depend on the prior knowledge (PK) underlying Bayesian inference. This knowledge reflects original beliefs about the probability of events and typically depends on domain expertise. Using inaccurate or uninformative PK can negatively affect quantitative analysis, yielding incorrect verification results. Our EPIK approach tackles this important challenge by eliciting and embedding PK in quantitative verification equipped with Bayesian estimators. Unlike existing approaches that require PK on formal model transition parameters, EPIK leverages system-level properties that are directly observable and are linked to real-world semantics. EPIK formulates a twofold optimisation problem to derive the distributions of unknown transition parameters and then embeds these distributions to verify new or difficult-to-measure (elusive) properties. The detailed experimental evaluation using multiple variants of real-world case studies and diverse EPIK instantiations shows its effectiveness, flexibility and generality.

Simos Gerasimou, Xingyu Zhao

Cyprus University of Technology, Cyprus · Wuhan University, China

Bayesian Inference Formal Verification

Aug 3, 2026

Infinite Trace Objectives with Finite Trace Techniques: Translating LTL to LTLf+

Linear Temporal Logic (LTL) is one of the most widely adopted languages for specifying temporal extended objectives in AI, with applications ranging from reactive synthesis to stochastic planning in Markov decision processes and reinforcement learning. Traditionally, solving any of these problems requires translating the LTL specification to a nondeterministic automata on infinite words and then determinizing it, a step that is notoriously difficult in theory and in practice. Recent work has introduced LTLf+, which lifts the finite-trace logic LTLf to infinite traces. LTLf+ has the same expressive power as LTL, yet it retains most of the crucial advantages of its base logic LTLf. Most reasoning in LTLf+ rests on finite automata on finite words, for which we have not only a canonical minimal representation but also an efficient determinization procedure. In this work we present the first translation from LTL to LTLf+. We first normalize an LTL formula into the syntactic reactivity fragment of the Manna-Pnueli hierarchy, to create the general fragment-based shape of LTLf+. We then present linear translations for each individual component of that fragment. As a consequence of this translation, the expanding body of techniques developed for LTLf+ now becomes available to many AI problems currently formulated in LTL. We further show that this comes at no asymptotic cost, as the pipeline from LTL to automaton via LTLf+ remains doubly exponential.

Christoph Weinhuber, Maximilian Prokop, Giuseppe De Giacomo +1

University of Oxford · 2Technical University of Munich · 3Masaryk University Brno +1

Temporal Reasoning Formal Verification Linear Temporal Logic

Aug 3, 2026

PAC Approximation and DIRECT Optimization for Parametric Markov Models

In this paper, we consider the parameter synthesis and optimization problem for parametric Markov decision processes (pMDPs), the extension of classical MDPs where exact probability values are replaced by parametric expressions. Computing the rational function

f_{\lsf}

that maps parameter valuations to the satisfaction value of a PRCTL property

\lsf

is a computationally expensive task, particularly for pMDPs where the optimal policy may vary across the parameter space. We adopt the scenario approach to efficiently synthesize a probably approximately correct (PAC) approximation

\ApproxFunOfProperty{f}

of

f_{\lsf}

: by sampling parameter configurations and solving a linear program, we obtain a polynomial approximation whose error margin

\margin

is guaranteed, with prescribed confidence, for all but an

\errorRate

-fraction of the parameter domain under the sampling distribution. We further show how this PAC framework can be combined with statistical model checking (SMC), enabling the analysis of black-box parametric models. Building on the PAC approximation, we integrate the DIRECT (DIviding RECTangles) algorithm for derivative-free global optimization over the parameter space. We establish conditional optimality-gap guarantees: under explicit Lipschitz and PAC-good-set assumptions, the difference between the true optimum

f_{\lsf}(\parameters^{*})

and the value found by DIRECT is bounded by a partition-diameter term and, in the PAC case, an additional approximation-error term. An empirical evaluation on 2997 benchmarks focuses on the new DIRECT-based optimization component. The results show that DIRECT variants solve fewer instances than the scenario optimizer, but on their common successful instances they often return slightly better objective values and usually run faster, while remaining close to the scenario values within the PAC margin.

Zhiming Chi, Ying Liu, Andrea Turrini +2

Key Laboratory of System Software (Chinese Academy of Sciences), Beijing, China · Institute of Software, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China +2

Robust Markov Decision Processes Markov Decision Processes Markov Models Formal Verification