Dual-Agent Co-Training for Health Coaching via Implicit Adversarial Preference Optimization

• URL: http://arxiv.org/abs/2605.07011v1
• Date: Thu, 07 May 2026 22:49:41 GMT
• Title: Dual-Agent Co-Training for Health Coaching via Implicit Adversarial Preference Optimization
• Abstract summary: Motivational-interviewing-based health coaching is an effective approach for improving mental health and promoting healthy behavior change.<n>The scarcity of trained human coaches and the high cost of coaching services make such support inaccessible to many people.<n>We propose a dual-agent framework that interactively co-trains both the health coach agent and the client simulator.
• Score: 13.546847868345369
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Motivational-interviewing-based health coaching is an effective approach for improving mental health and promoting healthy behavior change. However, the scarcity of trained human coaches and the high cost of coaching services make such support inaccessible to many people who could benefit from it. This motivates the development of AI health coaches that can provide scalable and affordable support. Existing methods typically optimize only one side of the interaction: they either train a dialogue agent against a fixed client environment or train a client simulator against a fixed assistant. This one-sided setup can limit exploration of the interaction space and may be inefficient at developing the capabilities required by the target agent and pushing its performance boundaries. In this paper, we propose a dual-agent framework that interactively co-trains both the health coach agent and the client simulator. The coach is optimized with DPO using Pareto-dominant response pairs identified by a multi-dimensional LLM judge. In turn, the client is trained adversarially by reversing these preferences, inducing an implicit adversarial training dynamic. We further show that this co-training process admits a natural stochastic-game interpretation. Extensive experiments demonstrate that our method effectively improves coaching quality across several important dimensions.

Related papers

• AI Coaching for Accelerating Human Skill Development with Reinforcement Learning [13.06179791485747]
  AI copilots can substantially boost human performance through shared control, but excessive assistance can induce over-reliance and skill atrophy.<n>This paper studies how an embodied AI agent can act as a coach that accelerates human motor-skill development.
  arXiv  Detail & Related papers  (2026-06-24T03:05:22Z)
• PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological Counselor [27.91498114470285]
  We propose an Experience-Driven Lifelong Learning Agent (textttPsychAgent) for psychological counseling.<n>First, we establish a Memory-Augmented Planning Engine tailored for longitudinal multi-session interactions.<n>Second, we design a Skill Evolution Engine that extracts new practice-grounded skills from historical counseling trajectories.<n>Third, we introduce a Reinforced Internalization Engine that integrates the evolved skills into the model.
  arXiv  Detail & Related papers  (2026-04-01T14:08:49Z)
• Nested Training for Mutual Adaptation in Human-AI Teaming [30.247046563601202]
  Existing approaches aim to improve diversity in training partners to approximate human behavior, but these partners are static and fail to capture adaptive behavior of humans.<n>We model the human-robot teaming scenario as an Interactive Partially Observable Markov Decision Process (I-POMDP), explicitly modeling human adaptation as part of the state.<n>We train our method in a multi-episode, required cooperation setup in the Overcooked domain, comparing it against several baseline agents designed for human-robot teaming.
  arXiv  Detail & Related papers  (2026-02-18T23:07:48Z)
• AutoCBT: An Autonomous Multi-agent Framework for Cognitive Behavioral Therapy in Psychological Counseling [57.054489290192535]
  Traditional in-person psychological counseling remains primarily niche, often chosen by individuals with psychological issues.<n>Online automated counseling offers a potential solution for those hesitant to seek help due to feelings of shame.
  arXiv  Detail & Related papers  (2025-01-16T09:57:12Z)
• 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)
• Coaching Copilot: Blended Form of an LLM-Powered Chatbot and a Human Coach to Effectively Support Self-Reflection for Leadership Growth [40.30407535831779]
  This paper explores the potential of such a chatbots powered by recent Large Language Models (LLMs) in collaboration with professional coaches in the field of executive coaching. Through a design workshop with them and two weeks of user study involving ten coach-client pairs, we explored the feasibility and nuances of integrating chatbots to complement human coaches.
  arXiv  Detail & Related papers  (2024-05-24T06:20:56Z)
• ProAgent: Building Proactive Cooperative Agents with Large Language Models [89.53040828210945]
  ProAgent is a novel framework that harnesses large language models to create proactive agents. ProAgent can analyze the present state, and infer the intentions of teammates from observations. ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various coordination scenarios.
  arXiv  Detail & Related papers  (2023-08-22T10:36:56Z)
• Multi-trainer Interactive Reinforcement Learning System [7.3072544716528345]
  We propose a more effective interactive reinforcement learning system by introducing multiple trainers. In particular, our trainer feedback aggregation experiments show that our aggregation method has the best accuracy. Finally, we conduct a grid-world experiment to show that the policy trained by the MTIRL with the review model is closer to the optimal policy than that without a review model.
  arXiv  Detail & Related papers  (2022-10-14T18:32:59Z)
• Safe adaptation in multiagent competition [48.02377041620857]
  In multiagent competitive scenarios, ego-agents may have to adapt to new opponents with previously unseen behaviors. As the ego-agent updates its own behavior to exploit the opponent, its own behavior could become more exploitable. We develop a safe adaptation approach in which the ego-agent is trained against a regularized opponent model.
  arXiv  Detail & Related papers  (2022-03-14T23:53:59Z)
• Enabling AI and Robotic Coaches for Physical Rehabilitation Therapy: Iterative Design and Evaluation with Therapists and Post-Stroke Survivors [66.07833535962762]
  Artificial intelligence (AI) and robotic coaches promise the improved engagement of patients on rehabilitation exercises through social interaction. Previous work explored the potential of automatically monitoring exercises for AI and robotic coaches, but deployment remains a challenge. We present our efforts on eliciting the detailed design specifications on how AI and robotic coaches could interact with and guide patient's exercises.
  arXiv  Detail & Related papers  (2021-06-15T22:06:39Z)
• PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training [94.87393610927812]
  We present an off-policy, interactive reinforcement learning algorithm that capitalizes on the strengths of both feedback and off-policy learning. We demonstrate that our approach is capable of learning tasks of higher complexity than previously considered by human-in-the-loop methods.
  arXiv  Detail & Related papers  (2021-06-09T14:10:50Z)

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.