Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasion

arXiv:2509.21054v2 Announce Type: replace-cross Abstract: Understanding persuasion is critical for the safety and reliability of multi-agent systems built on large language models (LLMs). This paper studies persuasion dynamics by contrasting general LLMs with Large Reasoning Models (LRMs) that employ explicit ``thinking'' processes. Through large-scale experiments on objective (MMLU) and subjective (PersuasionBench and Perspectrum) tasks, we identify Persuasion Duality: reasoning enhances an agent's persuasive power while simultaneously increasing its resistance to persuasion. For LRMs, adding thinking content increases persuasion rates by 21 pp on average, yet reduces susceptibility to incorrect persuasion by up to 10 pp on objective tasks. Despite these gains, we uncover a critical vulnerability: persuasiveness often stems from superficial cues such as response length and repetition rather than logical validity. Non-semantic padding or repeated conclusions can match or exceed the persuasive effect of coherent reasoning, revealing a strong length bias in agents' judgments. We further show that persuasion propagates non-linearly in multi-hop agent chains, where intermediate agents may amplify or attenuate influence depending on task subjectivity. Finally, guided by attention analysis, we propose a prompt-level adversarial argument detection method that consistently improves agent robustness.

Related

• Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning
• Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization
• Thinking About Thinking: Evaluating Reasoning in Post-Trained Language Models

Source: arXiv cs.CL | 2026-08-27