Dancing in Chains: Strategic Persuasion in Academic Rebuttal via Theory of Mind

2026-01-22

AI Summary

Academic rebuttals are often hindered by information asymmetry, and existing approaches merely mimic surface-level language without strategic persuasive reasoning. This work proposes RebuttalAgent, a novel framework that introduces Theory of Mind (ToM) into academic rebuttal generation for the first time, modeling reviewers’ mental states to unify strategic planning and response generation within an integrated TSR pipeline. We design a two-stage training paradigm based on self-reward mechanisms, combining supervised fine-tuning, reinforcement learning, and a novel critique-and-refine data synthesis method, alongside a dedicated evaluation model, Rebuttal-RM. Experiments demonstrate that our approach achieves an average improvement of 18.3% on automatic metrics, outperforming current baselines and advanced closed-source models, while Rebuttal-RM exhibits higher evaluation consistency than GPT-4.1.

Technology Category

• Knowledge Representation and Reasoning: Argumentation
• Multiagent Systems: Adversarial Agents
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Although artificial intelligence (AI) has become deeply integrated into various stages of the research workflow and achieved remarkable advancements, academic rebuttal remains a significant and underexplored challenge. This is because rebuttal is a complex process of strategic communication under severe information asymmetry rather than a simple technical debate. Consequently, current approaches struggle as they largely imitate surface-level linguistics, missing the essential element of perspective-taking required for effective persuasion. In this paper, we introduce RebuttalAgent, the first framework to ground academic rebuttal in Theory of Mind (ToM), operationalized through a ToM-Strategy-Response (TSR) pipeline that models reviewer mental state, formulates persuasion strategy, and generates strategy-grounded response. To train our agent, we construct RebuttalBench, a large-scale dataset synthesized via a novel critique-and-refine approach. Our training process consists of two stages, beginning with a supervised fine-tuning phase to equip the agent with ToM-based analysis and strategic planning capabilities, followed by a reinforcement learning phase leveraging the self-reward mechanism for scalable self-improvement. For reliable and efficient automated evaluation, we further develop Rebuttal-RM, a specialized evaluator trained on over 100K samples of multi-source rebuttal data, which achieves scoring consistency with human preferences surpassing powerful judge GPT-4.1. Extensive experiments show RebuttalAgent significantly outperforms the base model by an average of 18.3% on automated metrics, while also outperforming advanced proprietary models across both automated and human evaluations. Disclaimer: the generated rebuttal content is for reference only to inspire authors and assist in drafting. It is not intended to replace the author's own critical analysis and response.

Problem

• academic rebuttal
• strategic persuasion
• Theory of Mind
• information asymmetry
• perspective-taking

Innovation

• Theory of Mind
• Academic Rebuttal
• Strategic Persuasion
• RebuttalAgent
• Reinforcement Learning