English
Related papers

Related papers: When Agents Disagree: The Selection Bottleneck in …

200 papers

Many of the world's most pressing issues, such as climate change and global peace, require complex collective problem-solving skills. Recent studies indicate that diversity in individuals' behaviors is key to developing such skills and…

Artificial Intelligence · Computer Science 2025-01-30 Matteo Bettini , Ryan Kortvelesy , Amanda Prorok

Mixture-of-Agents (MoA) improves LLM performance through layered collaboration, but its dense topology raises costs and latency. Existing methods employ LLM judges to filter responses, yet still require all models to perform inference…

Artificial Intelligence · Computer Science 2026-01-27 Jize Wang , Han Wu , Zhiyuan You , Yiming Song , Yijun Wang , Zifei Shan , Yining Li , Songyang Zhang , Xinyi Le , Cailian Chen , Xinping Guan , Dacheng Tao

Agentic retrieval-augmented reasoning pipelines are increasingly used to structure how large language models (LLMs) incorporate external evidence in clinical decision support. These systems iteratively retrieve curated domain knowledge and…

Computational models of collaboration without prior coordination often overlook how heterogeneous agent traits and complex task structures jointly produce systemic bottlenecks, inefficiencies, and contribution inequalities. We address this…

Multiagent Systems · Computer Science 2026-05-12 Benjamin Panny , Shashank Mehrotra , Zahra Zahedi , Teruhisa Misu , Kumar Akash

A multi-agent pipeline with N agents typically issues N LLM calls per run. Merging agents into fewer calls (compound execution) promises token savings, but naively merged calls silently degrade quality through tool loss and prompt…

Computation and Language · Computer Science 2026-05-04 Aninda Ray

With advancements in reasoning capabilities, Large Language Models (LLMs) are increasingly employed for automated judgment tasks. While LLMs-as-Judges offer promise in automating evaluations, current approaches often rely on simplistic…

Artificial Intelligence · Computer Science 2025-10-15 Tianyu Hu , Zhen Tan , Song Wang , Huaizhi Qu , Tianlong Chen

Consensus formation is pivotal in multi-agent systems (MAS), balancing collective coherence with individual diversity. Conventional LLM-based MAS primarily rely on explicit coordination, e.g., prompts or voting, risking premature…

Multiagent Systems · Computer Science 2025-05-20 Zengqing Wu , Takayuki Ito

Building helpful and harmless large language models (LLMs) requires effective model alignment approach based on human instructions and feedback, which necessitates high-quality human-labeled data. Constructing such datasets is often…

Computation and Language · Computer Science 2025-05-07 Junlin Wang , Roy Xie , Shang Zhu , Jue Wang , Ben Athiwaratkun , Bhuwan Dhingra , Shuaiwen Leon Song , Ce Zhang , James Zou

Effectively leveraging diversity has been shown to improve performance for various machine learning models, including large language models (LLMs). However, determining the most effective way of using diversity remains a challenge. In this…

Computation and Language · Computer Science 2026-05-21 Rafael Rosales , Santiago Miret

Much of the success of multi-agent debates depends on carefully choosing the right parameters. The decision-making protocol stands out as it can highly impact final model answers, depending on how decisions are reached. Systematic…

Multiagent Systems · Computer Science 2025-10-01 Lars Benedikt Kaesberg , Jonas Becker , Jan Philip Wahle , Terry Ruas , Bela Gipp

Multi-agent systems (MAS) have emerged as a prominent paradigm for leveraging large language models (LLMs) to tackle complex tasks. However, the mechanisms governing the effectiveness of MAS built upon publicly available LLMs, specifically…

Multiagent Systems · Computer Science 2026-05-11 Yuxuan Zhao , Sijia Chen , Ningxin Su

Existing work in fairness auditing assumes that each audit is performed independently. In this paper, we consider multiple agents working together, each auditing the same platform for different tasks. Agents have two levers: their…

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,…

Human-Computer Interaction · Computer Science 2026-04-06 Harsh Kumar , Zi Kang , Mu , Jonathan Vincentius , Ashton Anderson

Today's pursuit of a single Large Language Model (LMM) for all software engineering tasks is resource-intensive and overlooks the potential benefits of complementarity, where different models contribute unique strengths. However, the degree…

Software Engineering · Computer Science 2025-10-31 Fernando Vallecillos-Ruiz , Max Hort , Leon Moonen

We seek to understand when heterogeneity in user preferences yields improved outcomes in terms of overall cost. That this might be hoped for is based on the common belief that diversity is advantageous in many settings. We investigate this…

Computer Science and Game Theory · Computer Science 2018-06-29 Richard Cole , Thanasis Lianeas , Evdokia Nikolova

We consider the problem of subset selection where one is given multiple rankings of items and the goal is to select the highest ``quality'' subset. Score functions from the multiwinner voting literature have been used to aggregate rankings…

Computers and Society · Computer Science 2023-06-19 Niclas Boehmer , L. Elisa Celis , Lingxiao Huang , Anay Mehrotra , Nisheeth K. Vishnoi

Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol to invoke, which agent role should perform a subtask, which model to bind to each role, how…

Multiagent Systems · Computer Science 2026-05-28 Nicole Koenigstein

LLM-as-Judge has emerged as a scalable alternative to human evaluation, enabling large language models (LLMs) to provide reward signals in trainings. While recent work has explored multi-agent extensions such as multi-agent debate and…

Artificial Intelligence · Computer Science 2025-09-19 Chiyu Ma , Enpei Zhang , Yilun Zhao , Wenjun Liu , Yaning Jia , Peijun Qing , Lin Shi , Arman Cohan , Yujun Yan , Soroush Vosoughi

LLMs often underperform on complex reasoning tasks when relying on a single generation-and-selection pipeline. Inference-time ensemble methods can improve performance by sampling diverse reasoning paths or aggregating multiple candidate…

Machine Learning · Computer Science 2026-02-03 Tong Zhu , Baiting Chen , Jin Zhou , Hua Zhou , Sriram Sankararaman , Xiaowu Dai

High-quality labeled datasets are fundamental for training and evaluating machine learning models, yet domains such as healthcare and Requirements Engineering (RE) face persistent barriers due to data scarcity, privacy constraints, or…

Software Engineering · Computer Science 2026-03-31 Abdelkarim El-Hajjami , Camille Salinesi