TRACE: Two-Phase RL for Causal Graph Exploration and Deeper Psychological Intervention in Dynamic Counseling Scenarios

Shilin Tang, Zunyi Yin, Xuefeng Liang, Guanghui Shi, Song Tong, Chen Guangyu


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.
Anthology ID:
2026.findings-acl.1711
Volume:
Findings of the Association for Computational Linguistics: ACL 2026
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
34229–34260
Language:
URL:
https://aclanthology.org/2026.findings-acl.1711/
DOI:
10.18653/v1/2026.findings-acl.1711
Bibkey:
Cite (ACL):
Shilin Tang, Zunyi Yin, Xuefeng Liang, Guanghui Shi, Song Tong, and Chen Guangyu. 2026. TRACE: Two-Phase RL for Causal Graph Exploration and Deeper Psychological Intervention in Dynamic Counseling Scenarios. In Findings of the Association for Computational Linguistics: ACL 2026, pages 34229–34260, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
TRACE: Two-Phase RL for Causal Graph Exploration and Deeper Psychological Intervention in Dynamic Counseling Scenarios (Tang et al., Findings 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.findings-acl.1711.pdf
Checklist:
 2026.findings-acl.1711.checklist.pdf