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

arXiv: https://arxiv.org/abs/2605.07011 · HTML: https://mlsanity.com/paper/2605.07011/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 73 references that are in the map.
- First posted on arXiv 7 May 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)
- LLM alignment / RLHF / preference optimisation / [Medical LLM alignment](https://mlsanity.com/alignment/medical-llm-alignment/)

## Builds on (most cited first, 14 of 14)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning](https://mlsanity.com/paper/2405.00451/) (2024)
- [Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization](https://mlsanity.com/paper/2310.03708/) (2023)
- [SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks](https://mlsanity.com/paper/2503.15478/) (2025)
- [SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents](https://mlsanity.com/paper/2403.08715/) (2024)
- [Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles](https://mlsanity.com/paper/2407.00870/) (2024)
- [Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF](https://mlsanity.com/paper/2410.04612/) (2024)
- [PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator](https://mlsanity.com/paper/2308.11534/) (2023)
- [Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter](https://mlsanity.com/paper/2503.05362/) (2025)
- [DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulation](https://mlsanity.com/paper/2512.20773/) (2025)

## Abstract (arXiv)

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.