# Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter

arXiv: https://arxiv.org/abs/2503.05362 · HTML: https://mlsanity.com/paper/2503.05362/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2025.

## Built on by (most cited first, 17 of 17)

- [RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents](https://mlsanity.com/paper/2507.03112/) (2025)
- [Emotional Supporters often Use Multiple Strategies in a Single Turn](https://mlsanity.com/paper/2505.15316/) (2025)
- [DecoupledESC: Enhancing Emotional Support Generation via Strategy-Response Decoupled Preference Optimization](https://mlsanity.com/paper/2505.16995/) (2025)
- [Towards Open-Ended Emotional Support Conversations in LLMs via Reinforcement Learning with Future-Oriented Rewards](https://mlsanity.com/paper/2508.12935/) (2025)
- [Affective Flow Language Model for Emotional Support Conversation](https://mlsanity.com/paper/2602.08826/) (2026)
- [MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue](https://mlsanity.com/paper/2603.06194/) (2026)
- [MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models](https://mlsanity.com/paper/2604.17730/) (2026)
- [PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning](https://mlsanity.com/paper/2508.09521/) (2025)
- [TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent](https://mlsanity.com/paper/2601.18700/) (2026)
- [Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation](https://mlsanity.com/paper/2609.03727/) (2026)
- [Mitigating Strategy Preference Bias in Emotional Support Conversation via Uncertainty Estimations](https://mlsanity.com/paper/2509.12661/) (2025)
- [Cognitive Policy-Driven LLM for Diagnosis and Intervention of Cognitive Distortions in Emotional Support Conversation](https://mlsanity.com/paper/2604.17178/) (2026)
- [Dual-Agent Co-Training for Health Coaching via Implicit Adversarial Preference Optimization](https://mlsanity.com/paper/2605.07011/) (2026)
- [Dual-Loop Self-Evolution via Verifiable Emotion Feedback for Multi-Turn Empathetic Dialogue](https://mlsanity.com/paper/2608.10626/) (2026)
- [ESCRAG-R1: Retrieval-Augmented Reinforcement Learning for Emotional Support Conversation](https://mlsanity.com/paper/2608.21925/) (2026)
- [Multi-Expert Conformal Risk Control for Pairwise LLM Judging in Open-Ended Dialogue](https://mlsanity.com/paper/2608.26529/) (2026)
- [Proactive Dialogue Policy Optimization via Cognitive-State Transition](https://mlsanity.com/paper/2609.34948/) (2026)

## Abstract (arXiv)

The growing emotional stress in modern society has increased the demand for Emotional Support Conversations (ESC). While Large Language Models (LLMs) show promise for ESC, they face two key challenges: (1) low strategy selection accuracy, and (2) preference bias, limiting their adaptability to emotional needs of users. Existing supervised fine-tuning (SFT) struggles to address these issues, as it rigidly trains models on single gold-standard responses without modeling nuanced strategy trade-offs. To overcome these limitations, we propose Chain-of-Strategy Optimization (CSO), a novel approach that optimizes strategy selection preferences at each dialogue turn. We first leverage Monte Carlo Tree Search to construct ESC-Pro, a high-quality preference dataset with turn-level strategy-response pairs. Training on ESC-Pro with CSO improves both strategy accuracy and bias mitigation, enabling LLMs to generate more empathetic and contextually appropriate responses. Experiments on LLaMA-3.1-8B, Gemma-2-9B, and Qwen2.5-7B demonstrate that CSO outperforms standard SFT, highlighting the efficacy of fine-grained, turn-level preference modeling in ESC.