Prog. Synthesis

This paper introduces decode-time grammars to ensure grammatical and semantic correctness of code generated by large language models, particularly for low-resource programming surfaces.

The paper presents a new approach to verifying quantum programs using classical automated verifiers.

ARCHER is a test-driven, multi-agent program-synthesis harness that generates auditable verification code from regulatory Codes of Practice for transparent, adaptable, and scalable compliance checking…

The paper introduces Atomic Decomposition and Recombination (ADR), a novel framework that generates genuinely novel and challenging verifiable code tasks, significantly improving the scalability of Re…

This paper evaluates the effectiveness of coding agents in solving generalized task and motion planning problems.

The authors propose nomp, a framework for building domain-specific compilers to improve programmer productivity without sacrificing performance and portability.

The paper introduces Vero, the first benchmark for evaluating joint implementation and proof synthesis at the repository level for AI-generated software.

The paper empirically evaluates the security quality of LLM-generated code across various prompting methods, finding that while prompting alters the structure of weaknesses, it is insufficient to reli…

The paper proposes a visual program synthesis framework using a VLM to generate accurate training data for semiconductor inspection, mitigating the sim-to-real gap by applying input binarization to st…

The paper introduces methods to compare agents procedurally in different contexts and develop a framework for auditing and evaluating agent behavior.

ALPS is an automated, vendor-agnostic framework that enforces least privilege in serverless functions by analyzing code and generating precise security policies, achieving high coverage and significan…

The paper introduces False Security Confidence (FSC), a new metric to measure the inherent prevalence of security vulnerabilities in code generated by LLMs that are otherwise functionally correct, eve…

AutoACSL is a framework that uses Code Property Graphs and large language models to generate formal specifications for C programs with improved success ratio and full proof ratio.

The paper introduces lazy Streett supermartingales and their lexicographic extension to certify almost-sure satisfaction of omega-regular properties with polynomial templates under a broad class of sa…

This paper explores the use of AI agents in robotic engineering and their impact on productivity.

Proposed method, KBSpec, uses external and internal knowledge to improve formal specification generation by LLMs, increasing verification pass rates and producing more high-completeness specifications…

MOSAIC introduces a structured agentic framework that treats automated data science as a staged, context-grounded model selection problem, improving performance and traceability over traditional AutoM…

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 Calf, a dependent type theory for cost verification, which synthesizes the physicist's and banker's views on amortized analysis using potential functions and credit annotations.

This paper introduces gradient inference, a new approach to developing sound and efficient gradient estimators for probabilistic programs by reducing gradient estimation to a related probabilistic inf…