Cover Image

Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wynn, Andrea, Satija, Harsh, Hadfield, Gillian
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Multiagent Systems
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Voting or Consensus? Decision-Making in Multi-Agent Debate
by: Kaesberg, Lars Benedikt, et al.
Published: (2025)

Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation
by: Yao, Yiheng, et al.
Published: (2026)

AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
by: Zhang, Boxuan, et al.
Published: (2026)

iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference
by: Fan, Wei, et al.
Published: (2025)

Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification
by: Chowdhury, Masnun Nuha, et al.
Published: (2026)

Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs
by: Li, Yuxuan, et al.
Published: (2025)

MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate
by: Amayuelas, Alfonso, et al.
Published: (2024)

Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Games
by: Eckhaus, Niv, et al.
Published: (2025)

TopoDIM: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systems
by: Sun, Rui, et al.
Published: (2026)

MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems
by: Venkataramani, Vishal, et al.
Published: (2026)

Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems
by: Kasprova, Vira, et al.
Published: (2026)

Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation
by: Chen, Nuo, et al.
Published: (2026)

Talk to Right Specialists: Iterative Routing in Multi-agent Systems for Question Answering
by: Wu, Feijie, et al.
Published: (2025)

SafeTalkCoach: Diversity-Driven Multi-Agent Simulation for Parent-Teen Health Conversations
by: Tabarsi, Benyamin, et al.
Published: (2026)

MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks
by: Ke, Zixuan, et al.
Published: (2026)

DataSage: Multi-agent Collaboration for Insight Discovery with External Knowledge Retrieval, Multi-role Debating, and Multi-path Reasoning
by: Liu, Xiaochuan, et al.
Published: (2025)

An Economy of AI Agents
by: Hadfield, Gillian K., et al.
Published: (2025)

Unleashing Diverse Thinking Modes in LLMs through Multi-Agent Collaboration
by: He, Zhixuan, et al.
Published: (2025)

Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems
by: Jin, Haibo, et al.
Published: (2026)

QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents
by: Yuan, Ye, et al.
Published: (2026)

Grammar Search for Multi-Agent Systems
by: Singh, Mayank, et al.
Published: (2025)

SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning
by: Li, Xuchen, et al.
Published: (2025)

Multi-Agent Collaboration via Evolving Orchestration
by: Dang, Yufan, et al.
Published: (2025)

From Debate to Deliberation: Structured Collective Reasoning with Typed Epistemic Acts
by: Prakash, Sunil
Published: (2026)

GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives
by: Mercier, Alexandre Le, et al.
Published: (2026)

ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis
by: Zhao, Huiya, et al.
Published: (2025)

Achieving Unanimous Consensus Through Multi-Agent Deliberation
by: Pokharel, Apurba, et al.
Published: (2025)

Adaptive Multi-Agent Response Refinement in Conversational Systems
by: Jeong, Soyeong, et al.
Published: (2025)

Self-Resource Allocation in Multi-Agent LLM Systems
by: Amayuelas, Alfonso, et al.
Published: (2025)

HARBOR: Exploring Persona Dynamics in Multi-Agent Competition
by: Jiang, Kenan, et al.
Published: (2025)

An Empirical Study of Group Conformity in Multi-Agent Systems
by: Choi, Min, et al.
Published: (2025)

Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
by: Nakamura, Mason, et al.
Published: (2026)

Weak-Link Optimization for Multi-Agent Reasoning and Collaboration
by: Bian, Haoyu, et al.
Published: (2026)

Modeling Layered Consciousness with Multi-Agent Large Language Models
by: Kim, Sang Hun, et al.
Published: (2025)

Multi-Agent Language Models: Advancing Cooperation, Coordination, and Adaptation
by: Sudhakar, Arjun Vaithilingam
Published: (2025)

Learning Latency-Aware Orchestration for Parallel Multi-Agent Systems
by: Shi, Xi, et al.
Published: (2026)

Governed Memory: A Production Architecture for Multi-Agent Workflows
by: Taheri, Hamed
Published: (2026)

CONSCIENTIA: Can LLM Agents Learn to Strategize? Emergent Deception and Trust in a Multi-Agent NYC Simulation
by: Sinha, Aarush, et al.
Published: (2026)

Social Reasoning in Machines: Investigating Collective Truth-Seeking Dynamics in Large Language Model Debate
by: Pecher, Tom
Published: (2026)

CortexDebate: Debating Sparsely and Equally for Multi-Agent Debate
by: Sun, Yiliu, et al.
Published: (2025)