ARGUS：基于心理理论（Theory-of-Mind）的论证生成，结合策略感知规划与知识接地

中文摘要 AI 辅助

有说服力的论证生成需要对受众信念、修辞策略和事实依据进行建模。尽管近年来取得了进展，但现有方法在很大程度上仍不关注受众，且未能整合策略选择以提升说服力。为弥合这一差距，我们提出了Argus，一个基于智能体的框架，将古典修辞学应用于说服性写作。其核心是一个心理理论（Theory-of-Mind，ToM）推理器，构建受众信念与价值观的显式双重心理模型，以指导下游决策。该表示为组件感知规划器提供条件，规划器将论证分解为子主题，分配细粒度修辞功能（logos诉诸逻辑、pathos诉诸情感、ethos诉诸信誉、kairos诉诸时机），并在规划时触发策略引导的证据检索。最后，一个优化模块迭代针对并解决多维度弱点，同时不降低质量。我们使用自动化配对Elo评分和LLM作为评判指标，在三个不同基准上评估Argus。结果显示，Argus在多个主干模型上始终优于强大的基线，取得最高排名和总体最高分数。针对性模拟实验进一步验证了其在改变持抗拒态度受众立场方面的有效性。

英文摘要

Persuasive argument generation requires modeling audience beliefs, rhetorical strategies, and factual grounding. Despite recent advancements, existing methods remain largely audience-agnostic and fail to integrate strategy selection to improve persuasiveness. To bridge this gap, we propose Argus, an agent-based framework that operationalizes classical rhetoric for persuasive writing. At its core, a Theory-of-Mind (ToM) Reasoner constructs an explicit dual mental model of the audience's beliefs and values to guide downstream decisions. This representation conditions a component-aware planner that decomposes the argument into subtopics, assigns fine-grained rhetorical functions (logos, pathos, ethos), and triggers strategy-guided evidence retrieval at planning time. Finally, a refinement module iteratively targets and resolves multi-dimensional weaknesses without quality regression. We evaluate Argus across three diverse benchmarks using both automated pairwise Elo and LLM-as-judge metrics. Results show that Argus consistently outperforms strong baselines across multiple backbone models, achieving top rankings and the highest overall scores. Targeted simulation experiments further validate its effectiveness in shifting resistant audience stances.

发表机构

• InspireOmni AI
• The Hong Kong Polytechnic University（香港理工大学）

机构由 AI 辅助整理，请以论文原文为准。