PersuaRL: Reinforcement Learning-Driven Multi-Expert Selection for Persuasive Dialogue Generation in Insurance

• URL: http://arxiv.org/abs/2609.01188v1
• Date: Tue, 01 Sep 2026 13:02:09 GMT
• Title: PersuaRL: Reinforcement Learning-Driven Multi-Expert Selection for Persuasive Dialogue Generation in Insurance
• Abstract summary: Large Language Models (LLMs) are revolutionizing digital communication by powering conversational agents deployed across domains such as customer service, digital sales, and insurance.<n>While they excel at factual communication, they often lack the ability to engage in truly persuasive, context-sensitive dialogue.<n>We introduce PersuaRL, a reinforcement learning-based framework that equips LLM-driven dialogue agents with the ability to adaptively explore, select, and coordinate strategies to achieve more effective persuasion.
• Score: 14.699506824596419
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are revolutionizing digital communication by powering conversational agents deployed across domains such as customer service, digital sales, and insurance. These agents, built on LLMs, can understand user input, retrieve relevant information, and generate coherent responses. However, while they excel at factual communication, they often lack the ability to engage in truly persuasive, context-sensitive dialogue, especially in domains like insurance, where trust and clarity are critical. Building on this need within the insurance domain, our work focuses on improving the persuasiveness of digital agents, aka LLMs. To support this, we introduce InsureDial, a Persuasive Insurance Dialogue dataset, designed to capture the nuances of persuasive communication specific to motor insurance interactions. We introduce PersuaRL, a reinforcement learning-based framework that equips LLM-driven dialogue agents with the ability to adaptively explore, select, and coordinate strategies across multiple expert modules, guided by the evolving dialogue context, to achieve more effective persuasion. We conduct extensive automatic human and qualitative evaluations on two benchmark persuasion dialogue datasets, including our InsureDial. Our evaluations consistently demonstrate that PersuaRL outperforms baseline, generating contextually appropriate and highly persuasive responses.

Related papers

• Enhancing Persuasive Dialogue Agents by Synthesizing Cross-Disciplinary Communication Strategies [5.729038915697267]
  We develop a framework for designing persuasive dialogue agents that draws on proven strategies from social psychology, behavioral economics, and communication theory.<n>We validated our proposed framework through experiments on two distinct datasets.
  arXiv  Detail & Related papers  (2026-02-26T07:18:45Z)
• Affective Multimodal Agents with Proactive Knowledge Grounding for Emotionally Aligned Marketing Dialogue [3.780355670921318]
  AffectMind is a multimodal affective dialogue agent that performs proactive reasoning and dynamic knowledge grounding to sustain emotionally aligned and persuasive interactions.<n>Experiments show that AffectMind outperforms strong LLM-based baselines in emotional consistency, persuasive success rate, and long-term user engagement.
  arXiv  Detail & Related papers  (2025-11-21T04:16:45Z)
• MMPersuade: A Dataset and Evaluation Framework for Multimodal Persuasion [73.99171322670772]
  Large Vision-Language Models (LVLMs) are increasingly deployed in domains such as shopping, health, and news.<n> MMPersuade provides a unified framework for systematically studying multimodal persuasion dynamics in LVLMs.
  arXiv  Detail & Related papers  (2025-10-26T17:39:21Z)
• Persuasion Should be Double-Blind: A Multi-Domain Dialogue Dataset With Faithfulness Based on Causal Theory of Mind [21.022976907694265]
  Recent persuasive dialogue datasets often fail to align with real-world interpersonal interactions.<n>We introduce ToMMA, a novel multi-agent framework for dialogue generation guided by causal Theory of Mind.<n>We present CToMPersu, a multi-domain, multi-turn persuasive dialogue dataset.
  arXiv  Detail & Related papers  (2025-02-28T18:28:16Z)
• Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations [58.65755268815283]
  Many real dialogues are interactive, meaning an agent's utterances will influence their conversational partner, elicit information, or change their opinion. We use this fact to rewrite and augment existing suboptimal data, and train via offline reinforcement learning (RL) an agent that outperforms both prompting and learning from unaltered human demonstrations. Our results in a user study with real humans show that our approach greatly outperforms existing state-of-the-art dialogue agents.
  arXiv  Detail & Related papers  (2024-11-07T21:37:51Z)
• Persuasion Games using Large Language Models [0.0]
  Large Language Models (LLMs) have emerged as formidable instruments capable of comprehending and producing human-like text. This paper explores the potential of LLMs, to shape user perspectives and subsequently influence their decisions on particular tasks. This capability finds applications in diverse domains such as Investment, Credit cards and Insurance.
  arXiv  Detail & Related papers  (2024-08-28T15:50:41Z)
• Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models [52.24756457516834]
  We propose a novel "Self-Explanation" prompting strategy to enhance the comprehension abilities of Large Language Models (LLMs) This task-agnostic approach requires the model to analyze each dialogue utterance before task execution, thereby improving performance across various dialogue-centric tasks. Experimental results from six benchmark datasets confirm that our method consistently outperforms other zero-shot prompts and matches or exceeds the efficacy of few-shot prompts.
  arXiv  Detail & Related papers  (2023-09-22T15:41:34Z)
• Controllable Mixed-Initiative Dialogue Generation through Prompting [50.03458333265885]
  Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy planner. Standard approach has been fine-tuning pre-trained language models to perform generation conditioned on these intents. We instead prompt large language models as a drop-in replacement to fine-tuning on conditional generation.
  arXiv  Detail & Related papers  (2023-05-06T23:11:25Z)
• A Mixture-of-Expert Approach to RL-based Dialogue Management [56.08449336469477]
  We use reinforcement learning to develop a dialogue agent that avoids being short-sighted (outputting generic utterances) and maximizes overall user satisfaction. Most existing RL approaches to DM train the agent at the word-level, and thus, have to deal with aly complex action space even for a medium-size vocabulary. We develop a RL-based DM using a novel mixture of expert language model (MoE-LM) that consists of (i) a LM capable of learning diverse semantics for conversation histories, (ii) a number of specialized LMs (or experts) capable of generating utterances corresponding to a
  arXiv  Detail & Related papers  (2022-05-31T19:00:41Z)
• Structural Pre-training for Dialogue Comprehension [51.215629336320305]
  We present SPIDER, Structural Pre-traIned DialoguE Reader, to capture dialogue exclusive features. To simulate the dialogue-like features, we propose two training objectives in addition to the original LM objectives. Experimental results on widely used dialogue benchmarks verify the effectiveness of the newly introduced self-supervised tasks.
  arXiv  Detail & Related papers  (2021-05-23T15:16:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.