When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Sources
- Misinformation Propagation in Benign Multi-Agent Systems
- AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
- Reasoning Models Don't Always Say What They Think
- Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systems
- Hallucination Cascade: Analyzing Error Propagation in Multi-Agent LLM Systems
- Measuring Faithfulness in Chain-of-Thought Reasoning
- Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity
- The Bystander Effect in Multi-Agent Reasoning: Quantifying Cognitive Loafing in Collaborative Interactions
- The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation
- Simple synthetic data reduces sycophancy in large language models
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems