# Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs

arXiv: https://arxiv.org/abs/2608.11624 · HTML: https://mlsanity.com/paper/2608.11624/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 48 references that are in the map.
- First posted on arXiv 12 Aug 2026.

## Builds on (most cited first, 14 of 14)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models](https://mlsanity.com/paper/2506.07468/) (2025)
- [Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models](https://mlsanity.com/paper/2503.01829/) (2025)
- [Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning](https://mlsanity.com/paper/2506.00782/) (2025)
- [Towards Strategic Persuasion with Language Models](https://mlsanity.com/paper/2509.22989/) (2025)
- [An Assessment of Model-On-Model Deception](https://mlsanity.com/paper/2405.12999/) (2024)
- [The Facade of Truth: Uncovering and Mitigating LLM Susceptibility to Deceptive Evidence](https://mlsanity.com/paper/2601.05478/) (2026)
- [Persuasion Propagation: Does Persuasion Change AI Agent Behavior?](https://mlsanity.com/paper/2602.00851/) (2026)
- [When Agents Persuade: Rhetoric Generation and Mitigation in LLMs](https://mlsanity.com/paper/2603.04636/) (2026)

## Built on by (most cited first, 2 of 2)

- [Black-Box Auditing of Epistemic Reliability in Multi-Agent Debate Distillation](https://mlsanity.com/paper/2609.32361/) (2026)
- [Understanding and Reducing Misalignment in Persuasion Optimization](https://mlsanity.com/paper/2610.16070/) (2026)

## Abstract (arXiv)

Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and reach decisions. As LLMs increasingly debate, advise, and think collaboratively with humans and each other, resistance to harmful persuasion becomes a core requirement for reliable behavior. Yet we show that this requirement is far from met: a single targeted persuasive argument is enough to collapse model accuracy to near zero, even when the argument is factually false. We formalize this threat as adversarial persuasion and introduce an adversarial reinforcement learning framework that trains persuader agents to change a target model's answer in a single interaction. First, we show that optimizing persuasion strategies through trial and error exposes vulnerabilities that static prompting misses: RL-trained persuaders raise persuasion success from approximately 24% to over 93% against the training-time persuadee. Second, we find that these learned strategies transfer to unseen models, achieving 83% attack success on Qwen-14B, 79% on Llama-3.1-8B, and 25% on GPT-4o-mini. Third, we demonstrate that a curriculum that bootstraps on more persuadable open-weight models before targeting harder models further increases GPT-4o-mini attack success from 25% to 38%. Moreover, our results reveal that optimized persuaders increasingly rely on credibility-based tactics, including fabricated citations and false authoritative evidence. Together, these findings expose a critical weakness in current LLM agents: even when they initially reason correctly, they can be steered toward false conclusions by optimized natural language influence. This positions persuasion robustness as a necessary safety criterion for multi-agent and human-AI decision-making systems.