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.

This paper introduces CORE-Bench, a comprehensive benchmark for code retrieval in agentic coding.

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 introduces CodeGolf Bench, a novel multi-language benchmark using code golf to measure LLMs' ability to generate highly concise and efficient code, showing that reasoning models significantl…

This paper identifies the 'Format-Reliability Gap'—where LLMs know about code vulnerabilities but generate insecure code anyway—and proposes a localized, per-vulnerability steering vector fix that sig…

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 proposes and evaluates a novel embedding model for bidirectional function association between source code and decompiled/stripped code, significantly outperforming existing models.

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…

The paper introduces CodeScan, a novel black-box framework that detects data poisoning in code generation LLMs by analyzing structural similarities across multiple generations to identify recurring, v…

The paper investigates how AI coding assistants shift developers' security focus from proactive prevention to reactive review, finding that this structural change is reinforced by current tool interac…

The paper proposes CoDe-R, a two-stage framework that significantly improves the accuracy and re-executability of decompiled code generated by LLMs, achieving a new SOTA in the lightweight regime.

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…

Minor, single-character perturbations to prompts can significantly degrade the security of code generated by LLMs, suggesting that prompt fragility is a major security concern beyond simple prompt inj…

This systematic mapping survey reviews label-efficient approaches for code vulnerability detection, synthesizing five paradigm families and providing a decision guide to navigate trade-offs.

CRAFTQA introduces a novel adaptive, code-driven framework that significantly enhances complex structured data reasoning by dynamically generating custom code functions beyond predefined operations.

The paper analyzes LLM vulnerability detection using mechanistic interpretability, finding that models primarily rely on safety detectors rather than direct vulnerability signature recognition.

The paper proposes a general, compiler-integrated framework for secure content composition that minimizes the syntactic difference between secure and insecure coding practices.

The paper introduces LLM4CodeRE, a domain-adaptive LLM framework that significantly improves bidirectional code reverse engineering by unifying assembly-to-source and source-to-assembly translation.

The paper establishes an information-theoretic upper bound on the combined functional capacity and perturbation retention of code LLMs, quantifying the security budget available for code generation.

This paper analyzes various source-to-bytecode obfuscation techniques for Erlang, demonstrating that effective protection relies on exploiting the representational gaps between high-level semantics an…