The paper proposes TraceDev, a multi-agent framework for automated software development grounded in use cases, achieving higher success rates than baseline approaches in repository-level code generati…

The paper proposes FedLAB, a traceable semantic codebook framework for federated multimodal graph foundation learning, which organizes multimodal graph knowledge into hierarchical codebooks and refine…

The paper introduces RefWalk, a novel framework designed to improve regulatory compliance question answering by ensuring rigorous citation traceability and explicit per-rule attribution across complex…

The paper introduces POLARIS, a novel framework that systematically generates comprehensive and verifiable safety tests for LLMs by formalizing natural language policies into First-Order Logic and exp…

Agentproof is a system that provides static, pre-deployment verification of safety properties in agent workflow graphs by automatically extracting a unified graph model and applying structural and tem…

This paper introduces StructureClaw, an artifact-centered workbench for evaluating structural-engineering agents, and presents StructureClaw-Bench, an executable benchmark for testing these agents.

TRIAGE is a framework for evaluating and diagnosing failures in document-grounded graph-RAG systems by attaching stage-specific metrics.

This paper settles the complexity of three sketching problems in graphs and distributions.

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 presents Weave, a deterministic method to convert SPICE netlists into LTspice schematics with guaranteed connectivity preservation.

The paper presents an end-to-end LLM pipeline and interactive dashboard designed to automatically extract and structure topics from massive volumes of regulatory consultation submissions, ensuring ful…

This paper introduces Path Consistency Scoring (PCS), a framework that evaluates router geolocation as a path-level consistency problem and produces a path consistency score based on a Hidden Markov M…

Kani is an open-source model checker for Rust that provides correctness guarantees for safety properties through compilation and a specification language.

The paper introduces CROP, a novel conformal procedure that provides rigorous statistical guarantees for certifying the longest safe prefix of a language model's reasoning trace, allowing for targeted…

Tool Forge is a validation-carrying toolchain that converts natural language capability intent into governed, sandbox-verified tool artifacts, significantly improving agent efficiency and reliability.