Related papers: Fairness Auditing with Multi-Agent Collaboration
Removing an agent from a cooperative team to measure its contribution seems natural, yet in multi-agent LLM systems this evaluation distorts the result it claims to measure. This failure is not isolated: learned critics, trajectory-level…
Typically, fair machine learning research focuses on a single decisionmaker and assumes that the underlying population is stationary. However, many of the critical domains motivating this work are characterized by competitive marketplaces…
Existing approaches to algorithmic fairness aim to ensure equitable outcomes if human decision-makers comply perfectly with algorithmic decisions. However, perfect compliance with the algorithm is rarely a reality or even a desirable…
Algorithmic tools are increasingly used in hiring to improve fairness and diversity, often by enforcing constraints such as gender-balanced candidate shortlists. However, we show theoretically and empirically that enforcing equal…
Recent progress in language modeling has largely relied on scaling model size, yet larger models do not reliably improve performance on tasks requiring multi-step reasoning and tool use. Multi-agent collaboration offers a potential…
Joint attention - the ability to purposefully coordinate attention with another agent, and mutually attend to the same thing -- is a critical component of human social cognition. In this paper, we ask whether joint attention can be useful…
Recent breakthroughs in large language model-driven autonomous agents have revealed that multi-agent collaboration often surpasses each individual through collective reasoning. Inspired by the neural scaling law--increasing neurons enhances…
Mitigating algorithmic bias is a critical task in the development and deployment of machine learning models. While several toolkits exist to aid machine learning practitioners in addressing fairness issues, little is known about the…
Agents in dynamic multi-agent environments must monitor their peers to execute individual and group plans. A key open question is how much monitoring of other agents' states is required to be effective: The Monitoring Selectivity Problem.…
In fairness audits, a standard objective is to detect whether a given algorithm performs substantially differently between subgroups. Properly powering the statistical analysis of such audits is crucial for obtaining informative fairness…
Multi-agent LLM pipelines produce contradictory evidence on whether team diversity improves output quality: heterogeneous Mixture-of-Agents teams outperform single models, yet homogeneous Self-MoA teams consistently win under…
Large Language Models (LLMs) have shown impressive capabilities in various applications, but they still face various inconsistency issues. Existing works primarily focus on the inconsistency issues within a single LLM, while we…
While Multi-Agent Systems (MAS) are increasingly deployed for complex workflows, their emergent properties-particularly the accumulation of bias-remain poorly understood. Because real-world MAS are too complex to analyze entirely,…
The Multi-Agent Path Finding (MAPF) problem aims at finding non-conflicting paths for multiple agents from their respective sources to destinations. This problem arises in multiple real-life situations, including robot motion planning and…
Multi-Agent Systems (MAS) with Large Language Model (LLM)-powered agents are gaining attention, yet fewer studies explore their team dynamics. Inspired by human team science, we propose a multi-agent framework to examine core aspects of…
Most AI-based educational tools today adopt a one-on-one tutoring paradigm, pairing a single LLM with a single learner. Yet decades of learning science research suggest that multi-party interaction -- through peer modeling, co-construction,…
Large Language Models (LLMs) have increasingly been utilized in social simulations, where they are often guided by carefully crafted instructions to stably exhibit human-like behaviors during simulations. Nevertheless, we doubt the…
Existing research mostly improves the fairness of Machine Learning (ML) software regarding a single protected attribute at a time, but this is unrealistic given that many users have multiple protected attributes. This paper conducts an…
Despite rapid technological progress, effective human-machine cooperation remains a significant challenge. Humans tend to cooperate less with machines than with fellow humans, a phenomenon known as the machine penalty. Here, we show that…
To improve the reasoning and question-answering capabilities of Large Language Models (LLMs), several multi-agent approaches have been introduced. While these methods enhance performance, the application of collective intelligence-based…