TRACE: Two-Phase RL for Causal Graph Exploration and Deeper Psychological Intervention in Dynamic Counseling Scenarios
Year: 2026
Type: conference-paper
Abstract: LLMs have shown promise in mental health counseling, but existing models are limited to surface-level empathy or predefined therapeutic procedures and lack the ability to actively explore the root causes of psychological distress.Inspired by case conceptualization, we formalize counseling as the online reconstruction of a client's underlying causal graph through multi-turn dialogue.To this end, we propose TRACE, a two-phase reinforcement learning framework.It implements a causal-graph-driven reward scheme across two phases: an exploration phase that rewards the causal graph reconstruction following a surface-to-deep path, and an intervention phase that rewards targeted restructuring of irrational beliefs.Extensive experiments show that TRACE outperforms existing models, enabling causal-chain-aware psychological intervention beyond surface-level empathy.
Language: English
Subfield: Applied Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W7166815645