Cover Image

Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yao, Binwei, Shang, Chao, Du, Wanyu, He, Jianfeng, Lian, Ruixue, Zhang, Yi, Su, Hang, Swamy, Sandesh, Qi, Yanjun
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systems
by: Kulshreshtha, Devang, et al.
Published: (2025)

STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents
by: Li, Jing-Jing, et al.
Published: (2025)

Cross-Modal Content Optimization for Steering Web Agent Preferences
by: Jiang, Tanqiu, et al.
Published: (2025)

Angelic Troublemakers
by: Wiley, A. Terrance
Published: (2022)

Interactive Peacemaking
by: Allen, Susan H.
Published: (2022)

Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluation
by: Koupaee, Mahnaz, et al.
Published: (2025)

Be Friendly, Not Friends: How LLM Sycophancy Shapes User Trust
by: Sun, Yuan, et al.
Published: (2025)

MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarization
by: Liu, Yinhong, et al.
Published: (2025)

Troublemaker Learning for Low-Light Image Enhancement
by: Song, Yinghao, et al.
Published: (2024)

Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System
by: Wang, Haotian, et al.
Published: (2023)

Towards Improved Preference Optimization Pipeline: from Data Generation to Budget-Controlled Regularization
by: Chen, Zhuotong, et al.
Published: (2024)

How RLHF Amplifies Sycophancy
by: Shapira, Itai, et al.
Published: (2026)

Peacemaking past & present: A syllabus
by: Michael Clinton
Published: (2024)

A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns
by: Men, Tianyi, et al.
Published: (2024)

DFlow: Diverse Dialogue Flow Simulation with Large Language Models
by: Du, Wanyu, et al.
Published: (2024)

Intersectional Sycophancy: How Perceived User Demographics Shape False Validation in Large Language Models
by: Maltbie, Benjamin, et al.
Published: (2026)

DebFlow: Automating Agent Creation via Agent Debate
by: Su, Jinwei, et al.
Published: (2025)

SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution
by: Li, Han, et al.
Published: (2025)

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

Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate
by: Liu, Yiqing, et al.
Published: (2026)

Free-MAD: Consensus-Free Multi-Agent Debate
by: Cui, Yu, et al.
Published: (2025)

RUMAD: Reinforcement-Unifying Multi-Agent Debate
by: Wang, Chao, et al.
Published: (2026)

Journey Before Destination: On the importance of Visual Faithfulness in Slow Thinking
by: Uppaal, Rheeya, et al.
Published: (2025)

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy
by: Kumarappan, Adarsh, et al.
Published: (2026)

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

Augmented Reinforcement Learning Framework For Enhancing Decision-Making In Machine Learning Models Using External Agents
by: Singh, Sandesh Kumar
Published: (2025)

Improving Multi-Agent Debate with Sparse Communication Topology
by: Li, Yunxuan, et al.
Published: (2024)

Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection
by: Tang, Yixuan, et al.
Published: (2026)

Not Your Typical Sycophant: The Elusive Nature of Sycophancy in Large Language Models
by: Natan, Shahar Ben, et al.
Published: (2026)

Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation
by: Dong, Jiangwen, et al.
Published: (2026)

Measuring Sycophancy of Language Models in Multi-turn Dialogues
by: Hong, Jiseung, et al.
Published: (2025)

Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate
by: Yi, John Seon Keun, et al.
Published: (2026)

Dialectic-Med: Mitigating Diagnostic Hallucinations via Counterfactual Adversarial Multi-Agent Debate
by: Lu, Zhixiang, et al.
Published: (2026)

DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection
by: Qi, Hongyuan, et al.
Published: (2026)

Unlocking Democratic Efficiency: How Coordinated Outcome-Contingent Promises Shape Decisions
by: Lazrak, Ali, et al.
Published: (2023)

Dynamic Model Merging Made Slim
by: Du, Guodong, et al.
Published: (2026)

Sycophancy is an Educational Safety Risk: Why LLM Tutors Need Sycophancy Benchmarks
by: Kasneci, Enkelejda, et al.
Published: (2026)

The Silicon Mirror: Dynamic Behavioral Gating for Anti-Sycophancy in LLM Agents
by: Shah, Harshee Jignesh
Published: (2026)

MAD-Spear: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems
by: Cui, Yu, et al.
Published: (2025)

Honoring repression: the award of the Peacemaker’s Medal to state agents involved in security (1964-1985)
by: Mariana Joffily
Published: (2014)