136 articles tagged with #formal-verification. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers have developed an agentic AI-driven workflow using Large Language Models to automate coverage analysis for formal verification in integrated chip development. The approach systematically identifies coverage gaps and generates required formal properties, demonstrating measurable improvements in coverage metrics that correlate with design complexity.
VeriStruct is a new AI framework that automates formal verification of complex data structure modules in the Verus programming language. The system achieved a 99.2% success rate in verifying 128 out of 129 functions across eleven Rust data structure modules, representing significant progress in AI-assisted formal verification.
Researchers have developed a framework that allows neural network verification tools to accept natural language specifications instead of low-level technical constraints. The system automatically translates human-readable requirements into formal verification queries, significantly expanding the practical applicability of neural network verification across diverse domains.
Researchers introduce IoUCert, a new formal verification framework that enables robustness verification for anchor-based object detection models like SSD, YOLOv2, and YOLOv3. The breakthrough uses novel coordinate transformations and Interval Bound Propagation to overcome previous limitations in verifying object detection systems against input perturbations.
Researchers have enhanced the Saarthi AI framework for formal verification, achieving 70% better accuracy in generating SystemVerilog assertions and 50% fewer iterations to reach coverage closure. The framework uses multi-agent collaboration and improved RAG techniques to move toward domain-specific AI intelligence for verification tasks.
Researchers introduce Agent Behavioral Contracts (ABC), a formal framework for specifying and enforcing reliable behavior in autonomous AI agents. The system addresses critical issues of drift and governance failures in AI deployments by implementing runtime-enforceable contracts that achieve 88-100% compliance rates and significantly improve violation detection.
Researchers introduced LeanCat, a benchmark comprising 100 category-theory tasks in Lean to test AI's formal theorem proving capabilities. State-of-the-art models achieved only 12% success rates, revealing significant limitations in abstract mathematical reasoning, while a new retrieval-augmented approach doubled performance to 24%.
Researchers have developed a neural theorem prover for Lean that successfully solved challenging high-school mathematics olympiad problems, including those from AMC12, AIME competitions, and two problems adapted from the International Mathematical Olympiad (IMO). This represents a significant advancement in AI's ability to handle formal mathematical reasoning and proof generation.
Researchers introduce conformal recovery-deadline certificates, a new runtime assurance mechanism that allows adaptive controllers to safely recover from faults without premature shutdown. The method uses statistical bounds to distinguish between controllers capable of self-correction and those that will fail, applying a verified backstop only when necessary.
Researchers present a unified mathematical framework for understanding how behavioral structures in reinforcement learning systems are preserved when models are simplified through state abstraction. The work establishes compositional principles for transferring behavioral guarantees between abstract and concrete systems, providing theoretical foundations for scaling RL to complex structured environments.
Researchers present AMPLE-GNC, an autonomous spacecraft control system that combines learned AI models with formal verification to achieve both capability and safety. The system successfully demonstrates fault-adaptive control recovering from 97.8% of actuator faults while maintaining 94.5% autonomous operation under a verified safety shield.
Researchers have developed a multi-agent AI system in Lean 4 that formalizes asymptotic statistical theory, a mathematically complex domain combining convergence statements, functional analysis, and regularity conditions. The hypothesis-disciplined approach ensures every formalization claim is anchored to source mathematics, producing axiom-clean and human-audited proofs for parametric and semi-parametric statistical models.
Researchers introduce CogSpike, a formal verification tool for probabilistic spiking neural networks that addresses the state space explosion problem through weight-discretized quotient abstractions. The innovation enables verification of previously intractable neural network models by reducing computational complexity exponentially while maintaining mathematical fidelity guarantees.
Researchers present an LLM-powered code synthesis system that automatically generates formally verified translations between medical device data formats and healthcare interoperability standards. The system integrates formal verification into its pipeline to guarantee generated code meets predefined requirements, demonstrated through integrating a pulse oximeter into an existing Medical IoT network.
Researchers have developed a machine learning approach to automatically generate splitting heuristics for parallel string constraint solvers, replacing manual design methods. The technique was implemented in Z3seq and Z3str4, demonstrating improved performance in solving complex string constraints across multiple processor cores.
Researchers propose a design-time verification framework for agentic AI workflows that models them as composable building blocks and validates structural compatibility through twelve rules. The approach detects design flaws in LLM-based agent systems before runtime, addressing a significant gap in current AI platform safeguards.
Researchers introduce ForEx, a framework that translates LLM-generated explanations into formal logic (Lean4) to verify whether reasoning actually supports predicted labels on logical fallacy detection tasks. The study reveals a critical gap: while 90% of LLM outputs can be formally verified as logically sound, agreement with human annotations remains around 20%, exposing that formal correctness differs fundamentally from label accuracy.
Researchers introduce REBA (Revealed Belief Automaton), a new framework for online planning in continuous partially observable environments that dynamically certifies belief states rather than relying on predefined discrete abstractions. The method achieves 17-47% performance improvements over existing approaches in patrolling and navigation tasks by combining information-theoretic analysis with formal symbolic planning.
Researchers propose a domain-specific language for specifying AI-SDLC (Software Development Lifecycle) processes that formalizes human-agent collaboration boundaries, approval gates, and governance constraints. The language distinguishes policy from enforcement mechanism and demonstrates that structural controls can bound system failure rates, while providing a theoretical framework for AI agent integration in software development teams.
Researchers present Geometric Information Flow (GIF), a new framework for detecting and controlling information leakage in large language models by tracking how input tokens influence outputs through the model's Jacobian and local geometry. GIF achieves superior performance on prompt injection and privacy breach detection benchmarks while using significantly lower computational costs than existing approaches, with detection patterns transferable across different model sizes and families.
Researchers propose a new framework combining large language models with formal methods to generate hardware designs (RTL code) with guaranteed correctness, addressing the critical issue of LLM hallucinations in chip design where errors have severe consequences.
Pythagoras-Prover introduces a family of efficient Lean theorem provers that achieve state-of-the-art performance with significantly fewer parameters than existing models, using novel training techniques including curriculum learning and augmented data generation. The 4B-parameter model outperforms DeepSeek-Prover-V2-671B by 167x parameter efficiency, while the 32B model sets new benchmarks on formal mathematics tasks.
Researchers propose a bridge-database system connecting bibliographic mathematical literature with formal proof libraries, introducing a formalization score to measure publication coverage in machine-verifiable systems like Lean mathlib. This framework aims to unify fragmented mathematical knowledge across informal publications and formal verification ecosystems.
Researchers introduce a neuro-symbolic framework that integrates Linear Temporal Logic constraints into transformer-based reinforcement learning policies, enabling AI systems to satisfy high-level temporal requirements while maintaining competitive performance. The method compiles logical specifications into deterministic finite automata and uses differentiable signals to regularize training, demonstrating improved constraint satisfaction in navigation tasks.
Researchers introduce RTL-BenchLS, a large-scale benchmark containing over 10,000 formally verified Verilog designs for evaluating large language models on hardware design tasks. The benchmark addresses limitations of existing datasets through three novel self-supervised tasks beyond specification-to-RTL generation, with top models achieving only 12-28% accuracy, demonstrating substantial room for improvement in LLM-based hardware automation.
