6 papers
ToMAS: A Pilot Failure-Grounded Theory-of-Mind Benchmark from Multi-Agent LLM Failures
Muhammad Ashar Ishfaq, Glaucia Melo
LLM-based multi-agent systems can fail even when communication succeeds because agents do not correctly track their peers' roles, knowledge, or intentions. We investigate whether s…
Beyond Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitive and LLM-Generated Python Code
Jessica Pourleyli, Maitreyee Das Urmi, Glaucia Melo
Advances in large language models (LLMs) fuel the quest for scalable methods to assess the security of generated and security-sensitive software. Static analysis is widely adopted…
Evaluating Tiny Recursive Models Across Training for Code Generation
Anjani Sirivella, Aanisha Newaz, Glaucia Melo
Code generation increasingly relies on large transformer models, whose capability advances with scale. Yet such a scale is costly, creating demand for small models, especially wher…
Prompt Structure Redistributes, Not Reduces: An Empirical Analysis of Security-Weaknesses in LLM-Generated Python Code
Maitreyee Das Urmi, Jessica Pourleyli, Fabio Santos +1
Large Language Models (LLMs) increasingly generate code from natural-language prompts, making prompt engineering a key mechanism for shaping the security of generated software. Str…
Reformulate, Retrieve, Localize: Agents for Repository-Level Bug Localization
Genevieve Caumartin, Glaucia Melo
Bug localization remains a critical yet time-consuming challenge in large-scale software repositories. Traditional information retrieval-based bug localization (IRBL) methods rely…
Is LLM-Generated Code More Maintainable \& Reliable than Human-Written Code?
Alfred Santa Molison, Marcia Moraes, Glaucia Melo +2
Background: The rise of Large Language Models (LLMs) in software development has opened new possibilities for code generation. Despite the widespread use of this technology, it rem…