10 papers
Unaccountable Delegation, Fading Skills: Mapping the Risks of Workplace AI Agents
Gabriele La Malfa, Lakmal Meegahapola, Edyta Bogucka +4
To anticipate socio-technical risks from AI agents, organizations need taxonomies to classify them. However, existing AI risk taxonomies focus on broad risks and do not capture job…
Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty
Tianjue Lin, Jianan Zhou, Jieyi Bi +4
Two-Stage Robust Optimization (2RO) with discrete uncertainty is challenging, often rendering exact solutions prohibitive. Scenario reduction alleviates this issue by selecting a s…
StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning
Hao Wang, Rui Li, Lei Sha +1
Existing code reasoning methods primarily supervise final code outputs, ignoring intermediate states, often leading to reward hacking where correct answers are obtained through inc…
The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play
Gabriele La Malfa, Emanuele La Malfa, Saar Cohen +4
Self-play red team is an established approach to improving AI safety in which different instances of the same model play attacker and defender roles in a zero-sum game, i.e., where…
A Study of Library Usage in Agent-Authored Pull Requests
Lukas Twist, Jie M. Zhang
Coding agents are becoming increasingly capable of completing end-to-end software engineering workflows that previously required a human developer, including raising pull requests…
Analyzing Message-Code Inconsistency in AI Coding Agent-Authored Pull Requests
Jingzhi Gong, Giovanni Pinna, Yixin Bian +1
Pull request (PR) descriptions generated by AI coding agents are the primary channel for communicating code changes to human reviewers. However, the alignment between these message…
SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints
Zhiyu Fan, Kirill Vasilevski, Dayi Lin +6
The advancement of large language models (LLMs) and code agents has demonstrated significant potential to assist software engineering (SWE) tasks, such as autonomous issue resoluti…
Large Language Models Miss the Multi-Agent Mark
Emanuele La Malfa, Gabriele La Malfa, Samuele Marro +5
Recent interest in Multi-Agent Systems of Large Language Models (MAS LLMs) has led to an increase in frameworks leveraging multiple LLMs to tackle complex tasks. However, much of t…
Fairness Aware Reinforcement Learning via Proximal Policy Optimization
Gabriele La Malfa, Jie M. Zhang, Michael Luck +1
Fairness in multi-agent systems (MAS) focuses on equitable reward distribution among agents in scenarios involving sensitive attributes such as race, gender, or socioeconomic statu…
Using Protected Attributes to Consider Fairness in Multi-Agent Systems
Gabriele La Malfa, Jie M. Zhang, Michael Luck +1
Fairness in Multi-Agent Systems (MAS) has been extensively studied, particularly in reward distribution among agents in scenarios such as goods allocation, resource division, lotte…