Misalignment Bounty: Crowdsourcing AI Agent Misbehavior

Uncovering Code Insights: Leveraging GitHub Artifacts for Deeper Code Understanding

arXiv:2511.03549v1 Announce Type: cross Abstract: Understanding the purpose of source code is a critical task in software maintenance, onboarding, and modernization. While large language models

Visualization Biases MLLM’s Decision Making in Network Data Tasks

arXiv:2511.03617v1 Announce Type: cross Abstract: We evaluate how visualizations can influence the judgment of MLLMs about the presence or absence of bridges in a network.

Benchmarking the Thinking Mode of Multimodal Large Language Models in Clinical Tasks

arXiv:2511.03328v1 Announce Type: cross Abstract: A recent advancement in Multimodal Large Language Models (MLLMs) research is the emergence of “reasoning MLLMs” that offer explicit control

Light over Heavy: Automated Performance Requirements Quantification with Linguistic Inducement

arXiv:2511.03421v1 Announce Type: cross Abstract: Elicited performance requirements need to be quantified for compliance in different engineering tasks, e.g., configuration tuning and performance testing. Much

RefAgent: A Multi-agent LLM-based Framework for Automatic Software Refactoring

arXiv:2511.03153v1 Announce Type: cross Abstract: Large Language Models (LLMs) have substantially influenced various software engineering tasks. Indeed, in the case of software refactoring, traditional LLMs