The study found that while multi-agent LLM code generation architectures significantly affect code complexity, the added complexity does not translate into better functional correctness, suggesting ar…

The paper introduces a unified framework to fairly evaluate LLM agentic capabilities by standardizing diverse benchmarks and separating the effects of the LLM model from the surrounding framework and…

The paper experimentally evaluates 12 multi-agent LLM collaboration topologies for software design, finding that structural adversarial prompting and cross-model review are the most effective approach…

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 WebIGBench, a novel benchmark designed to rigorously evaluate multimodal LLMs' ability to generate code for complex, interactive webpages, addressing the limitations of existing s…

The paper presents a large-scale study demonstrating that tool cloning is a pervasive and severe source of hidden duplication in agent-tool ecosystems, necessitating changes in how tool diversity is m…

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-…

This paper empirically evaluates the security of code generated by seven popular LLMs and finds that all evaluated models generate code containing critical or high-severity vulnerabilities.

AgenticVM is a multi-agent framework that uses LLMs and specialized tools to automate and drastically reduce the volume of software vulnerabilities into actionable, prioritized queues.

The paper introduces Harness-Bench, a diagnostic benchmark that measures how different system 'harnesses' affect LLM agent performance in realistic workflows, showing that agent capability must be rep…

The paper introduces JAW, a novel framework that demonstrates how adversaries can hijack agentic workflows on automation platforms like GitHub Actions by manipulating inputs based on context-grounded…

The paper demonstrates that linking team bonus points to measurable security improvements significantly reduces code security issues in a controlled educational experiment.

This paper introduces Dependency Steering, a novel attack paradigm demonstrating that malicious agent skills can actively bias LLM coding agents to use attacker-controlled packages, posing a significa…

The paper proposes an automated, standardized framework to empirically compare the security quality of code generated through human-only, LLM-only, and hybrid collaboration methods.

FuzzAgent introduces a multi-agent, evolutionary system that significantly improves library fuzzing by iteratively refining the test suite based on runtime feedback, achieving superior coverage and bu…

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 proposes Meta-Team, an experience-driven framework that enables multi-agent systems (MAS) to collaboratively self-evolve by transforming complex execution experiences into reusable improveme…

The paper introduces VibeGuard, a pre-publish security gate framework designed to detect novel vulnerabilities—such as source map exposure and packaging drift—that arise from developers over-relying o…

The study extends cooperative bias testing across diverse, next-generation LLMs, finding that provider identity is a stronger predictor of cooperative equilibrium than model generation, and that noise…

The paper analyzes GitHub security advisories for LLM-integrated open-source systems, finding that while most vulnerabilities map to existing code-level weaknesses, the architectural risks like Supply…