Towards Efficient and Robust Linguistic Emotion Diagnosis for Mental Health via Multi-Agent Instruction Refinement

2026-01-20

AI Summary

This work addresses the limited reliability of large language models in high-stakes clinical settings, where challenges such as prompt sensitivity, complex emotional comorbidities, and inefficient extraction of clinical cues hinder accurate affective diagnosis. To this end, we propose APOLO, a novel framework that formulates prompt optimization as a partially observable Markov decision process and introduces a multi-agent collaborative architecture comprising Planner, Teacher, Critic, Student, and Target agents. This design enables systematic exploration of fine-grained prompt spaces through closed-loop, iterative refinement of prompting strategies. Experimental results demonstrate that APOLO significantly improves diagnostic accuracy and robustness across multiple domain-specific and hierarchical benchmarks, thereby enhancing the trustworthiness, generalizability, and scalability of language models in mental health applications.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Linguistic expressions of emotions such as depression, anxiety, and trauma-related states are pervasive in clinical notes, counseling dialogues, and online mental health communities, and accurate recognition of these emotions is essential for clinical triage, risk assessment, and timely intervention. Although large language models (LLMs) have demonstrated strong generalization ability in emotion analysis tasks, their diagnostic reliability in high-stakes, context-intensive medical settings remains highly sensitive to prompt design. Moreover, existing methods face two key challenges: emotional comorbidity, in which multiple intertwined emotional states complicate prediction, and inefficient exploration of clinically relevant cues. To address these challenges, we propose APOLO (Automated Prompt Optimization for Linguistic Emotion Diagnosis), a framework that systematically explores a broader and finer-grained prompt space to improve diagnostic efficiency and robustness. APOLO formulates instruction refinement as a Partially Observable Markov Decision Process and adopts a multi-agent collaboration mechanism involving Planner, Teacher, Critic, Student, and Target roles. Within this closed-loop framework, the Planner defines an optimization trajectory, while the Teacher-Critic-Student agents iteratively refine prompts to enhance reasoning stability and effectiveness, and the Target agent determines whether to continue optimization based on performance evaluation. Experimental results show that APOLO consistently improves diagnostic accuracy and robustness across domain-specific and stratified benchmarks, demonstrating a scalable and generalizable paradigm for trustworthy LLM applications in mental healthcare.

Problem

• linguistic emotion diagnosis
• emotional comorbidity
• mental health
• large language models
• clinical cue extraction

Innovation

• multi-agent collaboration
• prompt optimization
• emotion diagnosis
• partially observable Markov decision process
• large language models