Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasion
cs.AI, cs.CL
Submitted: 2025-09-25
Updated: 2026-08-31
Comments: Accepted as EMNLP 2026 Findings
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models
- Must Read: A Comprehensive Survey of Computational Persuasion
- Seeing Things from a Different Angle: Discovering Diverse Perspectives about Claims
- An Empirical Study of Group Conformity in Multi-Agent Systems
- A Survey on Code Generation with LLM-based Agents
- A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Red-Teaming LLM Multi-Agent Systems via Communication Attacks
- Measuring Massive Multitask Language Understanding
- Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment
- Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models
- Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities
- When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements
- Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate
- Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
- Towards Simulating Social Influence Dynamics with LLM-based Multi-agents
- Evaluating the Performance of Large Language Models via Debates
- When Large Language Models are More PersuasiveThan Incentivized Humans, and Why
- Measuring and Improving Persuasiveness of Large Language Models
- Literature Review Of Multi-Agent Debate For Problem-Solving
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