136 articles tagged with #formal-verification. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers introduce Agentic Redux, an LLM agent architecture that guarantees semantic correctness and auditability using typed lambda calculus, paired with a new Ontology-First Agent Design methodology. The framework is demonstrated in healthcare billing compliance and security vulnerability disclosure domains, offering production-grade implementations with provable safety guarantees.
Researchers prove mathematically that autonomous AI systems create structural accountability gaps that cannot be resolved through transparency or oversight alone. Once AI autonomy exceeds a specific threshold in human-agent collectives, no accountability framework can simultaneously satisfy four core principles: attributability, foreseeability, non-vacuity, and completeness—establishing the first formal impossibility result in AI governance.
Researchers introduce Symbolic Neural Generators (SNGs), a hybrid neurosymbolic model combining inductive logic programming with large language models to generate molecules meeting formal correctness criteria. The system demonstrates performance comparable to state-of-the-art drug discovery methods on benchmark problems and generates promising inhibitor candidates for poorly understood drug targets.
Researchers have created FVSpec, a benchmark dataset of 9,415 Lean 4 formal specifications derived from 2,772 real-world Python property-based tests, designed to evaluate AI models on automated formal software verification tasks. The work addresses a critical gap in AI-assisted code verification by providing open-source tools and data to advance AI's capability to formally prove software correctness.
Researchers introduce Ethical Hyper-Velocity (EHV), a hardware-enforced governance architecture that embeds real-time policy constraints directly into AI inference pipelines using trusted execution environments and formal verification. The system reduces policy enforcement latency from days to near-instant, addressing critical safety gaps in autonomous agentic systems operating in regulated industries like healthcare and finance.
Axiom Math, a $1.6B AI unicorn, is using formal verification to audit economic theorems and has discovered significant gaps in foundational antitrust law that economists have relied on for 50 years. This discovery highlights how AI can identify mathematical flaws in established economic theory that human experts overlooked.
Researchers introduce Hermes, an AI agent that combines informal reasoning with formally verified mathematical proofs in Lean, achieving up to 40% accuracy improvements on difficult math benchmarks while reducing computational costs by 80%. The system addresses a fundamental limitation in LLM reasoning by interleaving exploratory problem-solving with rigorous formal verification.
ProofWala is an open-source multilingual proof engineering framework that enables neural theorem proving across multiple interactive theorem provers like Lean 4 and Rocq through unified infrastructure. The framework demonstrates that cross-lingual training across different proof assistants improves performance on mathematical proof tasks, with significant gains shown in Lean Mathlib and domain-specific applications.
TamaSwap launches as the first decentralized exchange built with Verity, a smart contract language engineered for formal verification and provable security. This development represents a significant step toward eliminating smart contract vulnerabilities that have historically plagued DeFi platforms.
Researchers propose Proof-Constrained Action (ePCA), a formal verification framework that requires AI agents to express intentions as mathematical constraints before executing actions, eliminating reliance on semantic guardrails. The approach achieves zero attack success rates in testing and addresses critical security gaps as LLMs evolve from text generators into autonomous agents with real-world execution capabilities.
Researchers have developed AutoformBot, a multi-agent AI system that automatically translates informal mathematics textbooks into machine-verified formal proofs in Lean 4. The team successfully formalized 26 open-access textbooks into a library called Atlas containing over 45,000 declarations and 500,000 lines of verified code, demonstrating that large-scale automated mathematics formalization is now economically viable.
Researchers introduce proof-state snapshotting, a technique that accelerates automated theorem proving in Lean 4 by reusing elaborated proof states across parallel search branches instead of reconstructing them. The method achieves 5.6-50x speedups (averaging 14x) on benchmark problems, addressing a critical bottleneck where per-branch overhead from import loading and elaboration consumed over 99% of computation time.
Researchers propose the SMARt framework, a four-layer autonomous AI system architecture that manages failures through formal escalation protocols rather than relying solely on model improvements. The framework enables AI agents to detect uncertainty, suspend operations, attempt recovery, and surrender control when reliability diminishes, addressing the fundamental architectural vulnerability of unbounded autonomy in deployed agentic systems.
Researchers present alpha-beta-CROWN, a neural network verification framework that enables formal verification of learning-based controllers in safety-critical systems. The tool addresses scalability challenges in verifying controller properties like stability and safety by computing certified bounds on nonlinear functions and using GPU parallelization for complex verification tasks.
Vitalik Buterin advocates for AI-powered formal verification as a security advancement for cryptocurrency systems. The Ethereum co-founder believes integrating AI-assisted verification tools can strengthen cryptographic security and reduce vulnerabilities in blockchain infrastructure.
Shepherd is a new runtime substrate that enables meta-agents to supervise and optimize other agents through formalized execution traces, achieving 5x faster forking than Docker and demonstrating measurable improvements in coding assistance, optimization, and reinforcement learning tasks. The open-source system mechanizes core operations in Lean and enables replay, branching, and counterfactual exploration of agent behaviors.
Researchers introduce containment verification, a formal verification approach that embeds safety guarantees directly into agentic AI frameworks rather than relying on model alignment. The team demonstrated the paradigm by verifying PocketFlow, an LLM framework, using Dafny formal methods—marking the first deductive verification of an agentic framework with safety properties independent of model capabilities.
Researchers prove a fundamental mathematical incompatibility between accuracy, trust, and human-level reasoning in AI systems, demonstrating that systems designed to never make false claims cannot solve certain problems that humans can easily solve. The findings parallel Gödel's incompleteness theorems and establish formal limitations on what AI systems can achieve regardless of computational power.
Researchers introduce LAWS, a self-certifying caching architecture for neural inference that builds a library of expert functions with formal error bounds, enabling efficient deployment across LLMs, robotics, and edge devices. The system generalizes both Mixture-of-Experts and KV prefix caching while providing mathematically verifiable performance guarantees without requiring ground truth validation.
Researchers present a formal framework proving that AI governance systems structurally fail when expressiveness boundaries (what AI can do) and governance boundaries (what's regulated) are defined independently, creating inevitable gaps. The paper proposes 'coterminous governance'—aligning these boundaries through architectural separation of computation from effects—as the only viable solution, with proofs mechanized in Coq.
Researchers introduce ANCORA, a self-play framework enabling language models to generate verifiable problems, solve them, and improve without human supervision. The method achieves 81.5% pass rate on Dafny2Verus tasks, significantly outperforming baseline approaches and demonstrating advances in autonomous AI reasoning capabilities.
Researchers introduce SafeAdapt, a novel framework for updating reinforcement learning policies while maintaining provable safety guarantees across changing environments. The approach uses a 'Rashomon set' to identify safe parameter regions and projects policy updates onto this certified space, addressing the critical challenge of deploying RL agents in safety-critical applications where dynamics and objectives evolve over time.
ClawLess introduces a formally verified security framework that enforces policies on AI agents operating with code execution and information retrieval capabilities, addressing risks that existing training-based approaches cannot adequately mitigate. The system uses BPF-based syscall interception and a user-space kernel to prevent adversarial AI agents from violating security boundaries, regardless of their internal design.
Researchers prove mathematically that no continuous input-preprocessing defense can simultaneously maintain utility, preserve model functionality, and guarantee safety against prompt injection attacks in language models with connected prompt spaces. The findings establish a fundamental trilemma showing that defenses must inevitably fail at some threshold inputs, with results verified in Lean 4 and validated empirically across three LLMs.
Researchers have developed LeanTutor, a proof-of-concept AI system that combines Large Language Models with theorem provers to create a mathematically verified proof tutor. The system features three modules for autoformalization, proof-checking, and natural language feedback, evaluated using PeanoBench, a new dataset of 371 Peano Arithmetic proofs.
