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

v1v2 (latest)

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

5 September 2025

Gillian Hadfield

ArXiv (abs)PDF HTML

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

4 / 4 papers shown

Title
Natural Language Tools: A Natural Language Approach to Tool Calling In Large Language Agents Reid T. Johnson Michelle D. Pain Jordan D. West LLMAG LM&MA ELM 152 0 0 16 Oct 2025
AgentAsk: Multi-Agent Systems Need to Ask Bohan Lin Kuo Yang Yingchuan Lai Yudong Zhang Chen Zhang G. Zhang Xinlei Yu Miao Yu Xu Wang Yang-Feng Wang 98 0 0 08 Oct 2025
Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate Binwei Yao Chao Shang Wanyu Du Jianfeng He Ruixue Lian Yi Zhang Hang Su Sandesh Swamy Yanjun Qi LLMAG 112 1 0 27 Sep 2025
Graph of Agents: Principled Long Context Modeling by Emergent Multi-Agent Collaboration Taejong Joo Shu Ishida Ivan Sosnovik Bryan Lim Sahand Rezaei-Shoshtari Adam Gaier Robert Giaquinto LLMAG 105 0 0 26 Sep 2025