Copertina

Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kasprova, Vira, Parulekar, Amruta, AlRabah, Abdulrahman, Agaram, Krishna, Garg, Ritwik, Jha, Sagar, Bozdag, Nimet Beyza, Hakkani-Tur, Dilek
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence Multiagent Systems
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models
di: Bozdag, Nimet Beyza, et al.
Pubblicazione: (2025)

From Fact to Judgment: Investigating the Impact of Task Framing on LLM Conviction in Dialogue Systems
di: Rabbani, Parisa, et al.
Pubblicazione: (2025)

Language Specific Knowledge: Do Models Know Better in X than in English?
di: Agarwal, Ishika, et al.
Pubblicazione: (2025)

Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue
di: Dongre, Vardhan, et al.
Pubblicazione: (2026)

Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code Debugging
di: Kargupta, Priyanka, et al.
Pubblicazione: (2024)

Few-Shot Accent Synthesis for ASR with LLM-Guided Phoneme Editing
di: Halychanskyi, Yurii, et al.
Pubblicazione: (2026)

ATOD: An Evaluation Framework and Benchmark for Agentic Task-Oriented Dialogue Systems
di: Zhang, Yifei, et al.
Pubblicazione: (2026)

DialDefer: A Framework for Detecting and Mitigating LLM Dialogic Deference
di: Rabbani, Parisa, et al.
Pubblicazione: (2026)

AURA: A Diagnostic Framework for Tracking User Satisfaction of Interactive Planning Agents
di: Kim, Takyoung, et al.
Pubblicazione: (2025)

Must Read: A Comprehensive Survey of Computational Persuasion
di: Bozdag, Nimet Beyza, et al.
Pubblicazione: (2025)

FinCom: A Financial Multi-Agent Demo with Disagree-or-Commit Deliberation
di: Yang, Chao Peter, et al.
Pubblicazione: (2026)

When AI Agents Disagree Like Humans: Reasoning Trace Analysis for Human-AI Collaborative Moderation
di: Wawer, Michał, et al.
Pubblicazione: (2026)

Disagree and Commit: Degrees of Argumentation-based Agreements
di: Kampik, Timotheus, et al.
Pubblicazione: (2024)

Symmetric Policy Design for Multi-Agent Dispatch Coordination in Supply Chains
di: Sudhakara, Sagar
Pubblicazione: (2025)

Instructor-Aligned Knowledge Graphs for Personalized Learning
di: AlRabah, Abdulrahman, et al.
Pubblicazione: (2026)

Do LLMs Encode Functional Importance of Reasoning Tokens?
di: Singh, Janvijay, et al.
Pubblicazione: (2026)

Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data
di: Agarwal, Ishika, et al.
Pubblicazione: (2025)

Agent-Based Exploration of Recommendation Systems in Misinformation Propagation
di: Jakobsen, Lise, et al.
Pubblicazione: (2025)

When Agents Disagree: The Selection Bottleneck in Multi-Agent LLM Pipelines
di: Maryanskyy, Artem
Pubblicazione: (2026)

Coordinated Communication and Inventory Optimization in Multi-Retailer Supply Chains
di: Sudhakara, Sagar, et al.
Pubblicazione: (2025)

Enforcement Agents: Enhancing Accountability and Resilience in Multi-Agent AI Frameworks
di: Tamang, Sagar, et al.
Pubblicazione: (2025)

When the Universe is Too Big: Bounding Consideration Probabilities for Plackett-Luce Rankings
di: Aoki-Sherwood, Ben, et al.
Pubblicazione: (2024)

LASER: An LLM-based ASR Scoring and Evaluation Rubric
di: Parulekar, Amruta, et al.
Pubblicazione: (2025)

Too Many Specialists: Emergent Inefficiencies and Bottlenecks for Multi-agent Ad-hoc Collaboration
di: Panny, Benjamin, et al.
Pubblicazione: (2026)

Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems
di: Zhu, Jianing, et al.
Pubblicazione: (2026)

Distributed Simultaneous Localisation and Auto-Calibration using Gaussian Belief Propagation
di: Murai, Riku, et al.
Pubblicazione: (2024)

Socialized Learning and Emergent Behaviors in Multi-Agent Systems based on Multimodal Large Language Models
di: Akin, Sureyya, et al.
Pubblicazione: (2025)

Strategic Pseudo-Goal Perturbation for Deadlock-Free Multi-Agent Navigation in Social Mini-Games
di: Jha, Abhishek, et al.
Pubblicazione: (2024)

Simulating User Agents for Embodied Conversational-AI
di: Philipov, Daniel, et al.
Pubblicazione: (2024)

Plan Verification for LLM-Based Embodied Task Completion Agents
di: Hariharan, Ananth, et al.
Pubblicazione: (2025)

Multi-Agent Path Planning in Complex Environments using Gaussian Belief Propagation with Global Path Finding
di: Jensen, Jens Høigaard, et al.
Pubblicazione: (2025)

ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems
di: Liu, Jinnuo, et al.
Pubblicazione: (2026)

SIMU: Selective Influence Machine Unlearning
di: Agarwal, Anu, et al.
Pubblicazione: (2025)

Question Generation for Assessing Early Literacy Reading Comprehension
di: Yang, Xiaocheng, et al.
Pubblicazione: (2025)

The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems
di: Nguyen, Thi-Nhung, et al.
Pubblicazione: (2025)

Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems
di: Shen, Xu, et al.
Pubblicazione: (2025)

Adaptive Urban Planning: A Hybrid Framework for Balanced City Development
di: Singla, Pratham, et al.
Pubblicazione: (2024)

Too Noisy to Collude? Algorithmic Collusion Under Laplacian Noise
di: Zhang, Niuniu
Pubblicazione: (2025)

Too Human to Model:The Uncanny Valley of LLMs in Social Simulation -- When Generative Language Agents Misalign with Modelling Principles
di: Zeng, Yongchao, et al.
Pubblicazione: (2025)

Facilitating Trustworthy Human-Agent Collaboration in LLM-based Multi-Agent System oriented Software Engineering
di: Ronanki, Krishna
Pubblicazione: (2025)