The paper introduces RePoT, a method that significantly improves Program-of-Thought (PoT) planning by deterministically verifying the initial plan prefix and using a single LLM call to resume planning…

The paper introduces ReproRepo, a scalable framework for evaluating the reproducibility of machine learning research using LLM agents and human-raised GitHub issues.

ACRFence introduces a framework-agnostic mitigation to prevent semantic rollback attacks in LLM agents by recording irreversible tool effects and enforcing strict replay-or-fork semantics upon checkpo…

The paper introduces Code-QA-Bench, a novel framework that rigorously separates genuine code reasoning from mere documentation memorization in repository-level code understanding benchmarks.

The paper evaluates code language model-based detection of vulnerability-fixing commits (VFCs) using a unified benchmark and concludes that code changes alone are insufficient for accurate detection,…

The paper proposes MAS-SZZ, a multi-agentic algorithm that significantly improves the identification of the earliest commit introducing a software vulnerability by combining root cause analysis with s…

SCRIBE is a novel framework that enables reliable source-level patching of binaries by performing 'binary-aware' recompilation, successfully resolving syntactic and semantic inaccuracies inherent in d…

This paper proposes CoHarden, a co-generation framework for automated program repair that uses a lax signal as an in-loop convergence criterion to prevent lax regressions.

The paper presents BigBag, an agentic framework that generates reusable fixing transformations for third-party library breaking API changes, achieving a compilable transformation rate of 94.3% and a f…

This paper characterizes oracle signals in test files of agent-authored pull requests and assesses their impact on merge outcomes.

The paper introduces CrossCommitVuln-Bench, a benchmark dataset demonstrating that many real-world Python vulnerabilities are introduced across multiple commits, making them invisible to standard per-…

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…

ContraFix is an agentic framework that improves automated vulnerability repair by using differential runtime evidence to pinpoint the root cause of bugs, achieving state-of-the-art performance on majo…

This study analyzes over 20,000 real-world coding sessions to show that AI coding agents frequently fail users through subtle misalignment, requiring constant manual correction even when major system…

Proposed ProjAgent, a repository-level code generation system using procedural similarity for retrieval and conservative static-analysis feedback.

The paper introduces SCDBench, a comprehensive benchmark dataset and methodology that rigorously evaluates LLM-based smart contract decompilers, finding that while frontier models can produce compilab…

The paper introduces SCDBench, a comprehensive benchmark dataset and methodology that rigorously evaluates LLM-based smart contract decompilers, finding that while frontier LLMs can generate compilabl…

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

This paper investigates the relationship between bug report features and repair success for automated program repair agents, finding that concrete, executable, and well-localized information is most b…