English
Related papers

Related papers: Talk Isn't Always Cheap: Understanding Failure Mod…

200 papers

Large language models (LLMs) excel in natural language generation but often confidently produce incorrect responses, especially in tasks like mathematical reasoning. Chain-of-thought prompting, self-verification, and multi-agent debate are…

Computation and Language · Computer Science 2026-03-30 Mahmood Hegazy

Multi-agent debate has been shown to improve reasoning in large language models (LLMs). However, it is compute-intensive, requiring generation of long transcripts before answering questions. To address this inefficiency, we develop a…

Artificial Intelligence · Computer Science 2026-04-29 John Seon Keun Yi , Aaron Mueller , Dokyun Lee

For some problems, humans may not be able to accurately judge the goodness of AI-proposed solutions. Irving et al. (2018) propose that in such cases, we may use a debate between two AI systems to amplify the problem-solving capabilities of…

Artificial Intelligence · Computer Science 2021-03-17 Vojtěch Kovařík , Ryan Carey

If AI systems match or exceed human capabilities on a wide range of tasks, it may become difficult for humans to efficiently judge their actions -- making it hard to use human feedback to steer them towards desirable traits. One proposed…

Artificial Intelligence · Computer Science 2025-05-26 Marie Davidsen Buhl , Jacob Pfau , Benjamin Hilton , Geoffrey Irving

Self-improvement, where models improve beyond their current performance without external supervision, remains a challenge. The core difficulty is sourcing a training signal stronger than what the model itself can currently produce. Majority…

Artificial Intelligence · Computer Science 2026-02-02 Ankur Samanta , Akshayaa Magesh , Runzhe Wu , Ayush Jain , Youliang Yu , Daniel Jiang , Boris Vidolov , Paul Sajda , Yonathan Efroni , Kaveh Hassani

Large Language Models (LLMs) have advanced autonomous agents' planning and decision-making, yet they struggle with complex tasks requiring diverse expertise and multi-step reasoning. Multi-Agent Debate (MAD) systems, introduced in NLP…

Software Engineering · Computer Science 2025-03-18 Jina Chun , Qihong Chen , Jiawei Li , Iftekhar Ahmed

Negotiation is a fundamental challenge for AI agents, as it requires an ability to reason strategically, model opponents, and balance cooperation with competition. We present the first comprehensive study that systematically evaluates how…

Computation and Language · Computer Science 2026-01-12 Sherzod Hakimov , Roland Bernard , Tim Leiber , Karl Osswald , Kristina Richert , Ruilin Yang , Raffaella Bernardi , David Schlangen

Large Language Models (LLMs) have shown remarkable reasoning capabilities in mathematical and scientific tasks. To enhance complex reasoning, multi-agent systems have been proposed to harness the collective intelligence of LLM agents.…

Artificial Intelligence · Computer Science 2025-10-22 Zhenyu Bi , Meng Lu , Yang Li , Swastik Roy , Weijie Guan , Morteza Ziyadi , Xuan Wang

The use of language-model-based question-answering systems to aid humans in completing difficult tasks is limited, in part, by the unreliability of the text these systems generate. Using hard multiple-choice reading comprehension questions…

Computation and Language · Computer Science 2022-10-21 Alicia Parrish , Harsh Trivedi , Nikita Nangia , Vishakh Padmakumar , Jason Phang , Amanpreet Singh Saimbhi , Samuel R. Bowman

Multi-Agent Debate has emerged as a promising framework for improving the reasoning quality of large language models through iterative inter-agent communication. However, broadcasting all agent messages at every round introduces noise and…

Computation and Language · Computer Science 2026-04-15 Manh Nguyen , Anh Nguyen , Dung Nguyen , Svetha Venkatesh , Hung Le

Recent progress in LLMs discussion suggests that multi-agent discussion improves the reasoning abilities of LLMs. In this work, we reevaluate this claim through systematic experiments, where we propose a novel group discussion framework to…

Computation and Language · Computer Science 2024-02-29 Qineng Wang , Zihao Wang , Ying Su , Hanghang Tong , Yangqiu Song

The core premise of AI debate as a scalable oversight technique is that it is harder to lie convincingly than to refute a lie, enabling the judge to identify the correct position. Yet, existing debate experiments have relied on datasets…

Multi-agent systems - systems with multiple independent AI agents working together to achieve a common goal - are becoming increasingly prevalent in daily life. Drawing inspiration from the phenomenon of human group social influence, we…

Artificial Intelligence · Computer Science 2025-09-25 Tianqi Song , Yugin Tan , Zicheng Zhu , Yibin Feng , Yi-Chieh Lee

Large language model (LLM) agents are increasingly acting as human delegates in multi-agent environments, where a representative agent integrates diverse peer perspectives to make a final decision. Drawing inspiration from social…

Computation and Language · Computer Science 2026-05-05 Changgeon Ko , Jisu Shin , Hoyun Song , Huije Lee , Eui Jun Hwang , Jong C. Park

Large Language Models (LLMs) have shown remarkable promise in communicating with humans. Their potential use as artificial partners with humans in sociological experiments involving conversation is an exciting prospect. But how viable is…

Artificial Intelligence · Computer Science 2025-02-04 James Flamino , Mohammed Shahid Modi , Boleslaw K. Szymanski , Brendan Cross , Colton Mikolajczyk

Current QA systems can generate reasonable-sounding yet false answers without explanation or evidence for the generated answer, which is especially problematic when humans cannot readily check the model's answers. This presents a challenge…

Computation and Language · Computer Science 2022-04-14 Alicia Parrish , Harsh Trivedi , Ethan Perez , Angelica Chen , Nikita Nangia , Jason Phang , Samuel R. Bowman

AI safety via debate and reinforcement learning from AI feedback (RLAIF) are both proposed methods for scalable oversight of advanced AI systems, yet no formal framework relates them or characterizes when debate offers an advantage. We…

Machine Learning · Computer Science 2026-03-06 Robin Young

Common methods for aligning large language models (LLMs) with desired behaviour heavily rely on human-labelled data. However, as models grow increasingly sophisticated, they will surpass human expertise, and the role of human evaluation…

Multi-agent debate (MAD) has gained significant attention as a promising line of research to improve the factual accuracy and reasoning capabilities of large language models (LLMs). Despite its conceptual appeal, current MAD research…

Computation and Language · Computer Science 2025-06-24 Hangfan Zhang , Zhiyao Cui , Jianhao Chen , Xinrun Wang , Qiaosheng Zhang , Zhen Wang , Dinghao Wu , Shuyue Hu

Grounding is the collaborative process of establishing mutual belief sufficient for a communicative goal. While static grounding maps language to a shared context, dynamic grounding requires agents to negotiate meaning across turns. Current…

Multiagent Systems · Computer Science 2026-05-14 Yiheng Yao , Chelsea Zou , Robert D. Hawkins