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

arXiv: https://arxiv.org/abs/2509.21054 · HTML: https://mlsanity.com/paper/2509.21054/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 12 of its 50 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 12 of 12)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [A Survey on Code Generation with LLM-based Agents](https://mlsanity.com/paper/2508.00083/) (2025)
- [Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2502.14321/) (2025)
- [Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate](https://mlsanity.com/paper/2402.07401/) (2024)
- [MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2505.16988/) (2025)
- [When Large Language Models are More PersuasiveThan Incentivized Humans, and Why](https://mlsanity.com/paper/2505.09662/) (2025)
- [Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment](https://mlsanity.com/paper/2411.11731/) (2024)
- [Exploring the Necessity of Reasoning in LLM-based Agent Scenarios](https://mlsanity.com/paper/2503.11074/) (2025)
- [LLMs are Biased Evaluators But Not Biased for Retrieval Augmented Generation](https://mlsanity.com/paper/2410.20833/) (2024)
- [When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements](https://mlsanity.com/paper/2502.15153/) (2025)

## Built on by (most cited first, 4 of 4)

- [Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems](https://mlsanity.com/paper/2602.15198/) (2026)
- [AgentCity: Constitutional Governance for Autonomous Agent Economies via Separation of Power](https://mlsanity.com/paper/2604.07007/) (2026)
- [Judge Before Answer: Can MLLM Discern the False Premise in Question?](https://mlsanity.com/paper/2510.10965/) (2025)
- [Assessing and Explaining the Persuadability of Large Language Models as Legal Decision Tools](https://mlsanity.com/paper/2604.26233/) (2026)

## Abstract (arXiv)

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.