This paper presents a novel approach for constructing information flow paths from RTL trace data for automated property generation and validation in hardware design.

The paper introduces FVSpec, a large-scale benchmark that translates thousands of real-world Python property-based tests into formal Lean 4 specifications to evaluate AI models for formal software ver…

This paper proposes using large language models (LLMs) to generate and compositionally verify software implementations directly from natural language specifications, showing promising preliminary resu…

SEMBridge is a tagless-final framework that allows a single executable object program to generate multiple program semantics, including weakest-precondition and bounded-checking interpretations, ensur…

The paper introduces TRAILS~, a novel method that improves code correctness validation by grounding LLM reasoning in concrete (input, output) pairs derived from specifications, achieving state-of-the-…

The paper introduces KindHML, an automated formal verification approach that uses Hennessy-Milner Logic and the Kind 2 model checker to verify complex temporal properties of smart contracts, detecting…

The paper proposes GRiD, a novel framework that uses a two-phase training strategy (supervised pre-training and RL fine-tuning) to discover complex, graph-like rules for knowledge graph reasoning, ove…

SpecDB is a novel system that uses LLMs to synthesize highly customized, purpose-built relational databases, achieving performance comparable to commercial systems while significantly reducing code si…

The paper introduces prefix filters and an algorithm (Palla) to systematically learn and apply specific error patterns in Large Language Models, significantly improving constrained generation tasks li…

The paper introduces CHECKMATE, a novel framework that uses code evolution to automatically generate and optimize algorithms for complex combinatorial problems, outperforming state-of-the-art solvers.

The paper introduces Neuroforger, a system that combines a new formal specification language with LLMs and type checking to reliably generate and validate concrete violation witnesses (counterexamples…

The paper introduces SecGoal, a benchmark dataset and framework, demonstrating that fine-tuning smaller LLMs on this dataset significantly improves the precision of extracting formalizable security go…

This paper provides the first longitudinal analysis of log-based detection rule evolution in public repositories, finding that rule changes reflect ongoing operational trade-offs rather than steady co…

FuzzPilot is a controller for AFL++ that validates candidate mutation recipes by running short micro-campaigns, demonstrating a mechanism to manage fuzzing plateaus, though initial results on a satura…

pcbGPT is a grounded system that automatically generates editable KiCad PCB schematics from natural language requirements, achieving high accuracy on complex embedded design tasks.

This paper studies AI development frameworks for software engineering and proposes a six-dimension process taxonomy.

The paper proposes UniRule, a novel agentic RAG framework that unifies the detection rule generation process by mapping context and language to rules, significantly outperforming pure LLM generation.

The paper introduces a novel pipeline integrating formal verification and process mining to systematically identify and analyze root causes of security property invalidations in complex automotive net…

The paper develops a novel, sound, and complete deductive proof system for proving contract satisfaction, which is crucial for verifying CPU security against side-channel attacks.

The paper proposes a federated formal verification architecture that treats verification as a polyglot proof system, successfully validating it on complex production subsystems like a Raft consensus m…