Psy-Copilot: Visual Chain of Thought for Counseling
Keqi Chen, Zekai Sun, Huijun Lian, Yingming Gao, Ya Li
TL;DR
The paper tackles the challenge of opaque AI-assisted counseling by introducing Psy-COT, a visual, multi-level graph that encodes the causal and temporal chain of thought in therapeutic conversations, and Psy-Copilot, a retrieval-augmented agent that offers traceable reasoning to therapists. It constructs a 941-session COT graph with separate indices for dialogue and reasoning content and employs a two-stage retrieval mechanism to ground AI responses in retrieved cases and strategies. An interactive demo platform demonstrates AI–therapist collaboration, and the authors release an open-source pipeline for graph construction and deployment. Evaluation using EmoBench indicates that Psy-Copilot improves emotional intelligence metrics compared with baselines, supporting safer and more transparent AI-assisted counseling.
Abstract
Large language models (LLMs) are becoming increasingly popular in the field of psychological counseling. However, when human therapists work with LLMs in therapy sessions, it is hard to understand how the model gives the answers. To address this, we have constructed Psy-COT, a graph designed to visualize the thought processes of LLMs during therapy sessions. The Psy-COT graph presents semi-structured counseling conversations alongside step-by-step annotations that capture the reasoning and insights of therapists. Moreover, we have developed Psy-Copilot, which is a conversational AI assistant designed to assist human psychological therapists in their consultations. It can offer traceable psycho-information based on retrieval, including response candidates, similar dialogue sessions, related strategies, and visual traces of results. We have also built an interactive platform for AI-assisted counseling. It has an interface that displays the relevant parts of the retrieval sub-graph. The Psy-Copilot is designed not to replace psychotherapists but to foster collaboration between AI and human therapists, thereby promoting mental health development. Our code and demo are both open-sourced and available for use.