# AREG: Adversarial Resource Extraction Game for Evaluating Persuasion and Resistance in Large Language Models

arXiv: https://arxiv.org/abs/2602.16639 · HTML: https://mlsanity.com/paper/2602.16639/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Builds on (most cited first, 7 of 7)

- [Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good](https://mlsanity.com/paper/1906.06725/) (2019)
- [Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models](https://mlsanity.com/paper/2503.01829/) (2025)
- [When AIs Judge AIs: The Rise of Agent-as-a-Judge Evaluation for LLMs](https://mlsanity.com/paper/2508.02994/) (2025)
- [Multiagent Evaluation under Incomplete Information](https://mlsanity.com/paper/1909.09849/) (2019)
- [Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD](https://mlsanity.com/paper/2508.17450/) (2025)
- [Evaluating and Modeling Social Intelligence: A Comparative Study of Human and AI Capabilities](https://mlsanity.com/paper/2405.11841/) (2024)
- [Elo Ratings for Large Tournaments of Software Agents in Asymmetric Games](https://mlsanity.com/paper/2105.00839/) (2021)

## Built on by (most cited first, 1 of 1)

- [Receiver Decides Agent-to-Agent Negotiations](https://mlsanity.com/paper/2610.18424/) (2026)

## Abstract (arXiv)

Evaluating the social intelligence of Large Language Models (LLMs) increasingly requires moving beyond static text generation toward dynamic, adversarial interaction. We introduce the Adversarial Resource Extraction Game (AREG), a benchmark that operationalizes persuasion and resistance as a multi-turn, zero-sum negotiation over financial resources. Using a round-robin tournament across frontier models, AREG enables joint evaluation of offensive (persuasion) and defensive (resistance) capabilities within a single interactional framework. Our analysis provides evidence that these capabilities are weakly correlated (ρ = 0.33) and empirically dissociated: strong persuasive performance does not reliably predict strong resistance, and vice versa. Across all evaluated models, resistance scores exceed persuasion scores, indicating a systematic defensive advantage in adversarial dialogue settings. Further linguistic analysis suggests that interaction structure plays a central role in these outcomes. Incremental commitment-seeking strategies are associated with higher extraction success, while verification-seeking responses are more prevalent in successful defenses than explicit refusal. Together, these findings indicate that social influence in LLMs is not a monolithic capability and that evaluation frameworks focusing on persuasion alone may overlook asymmetric behavioral vulnerabilities.