AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation

TL;DR

AnnaAgent is a novel AI system that simulates seekers in mental health counseling with dynamic emotional states and multi-session memory, improving realism over previous models.

Contribution

It introduces a dynamic agent with tertiary memory and emotion modulation trained on real dialogues, advancing realistic multi-session seeker simulation in mental health AI.

Findings

Achieves more realistic seeker simulation than existing baselines.

Effective integration of short-term and long-term memory across sessions.

Validated through automated and manual evaluation methods.

Abstract

Constrained by the cost and ethical concerns of involving real seekers in AI-driven mental health, researchers develop LLM-based conversational agents (CAs) with tailored configurations, such as profiles, symptoms, and scenarios, to simulate seekers. While these efforts advance AI in mental health, achieving more realistic seeker simulation remains hindered by two key challenges: dynamic evolution and multi-session memory. Seekers' mental states often fluctuate during counseling, which typically spans multiple sessions. To address this, we propose AnnaAgent, an emotional and cognitive dynamic agent system equipped with tertiary memory. AnnaAgent incorporates an emotion modulator and a complaint elicitor trained on real counseling dialogues, enabling dynamic control of the simulator's configurations. Additionally, its tertiary memory mechanism effectively integrates short-term and long-term memory across sessions. Evaluation results, both automated and manual, demonstrate that AnnaAgent achieves more realistic seeker simulation in psychological counseling compared to existing baselines. The ethically reviewed and screened code can be found on https://github.com/sci-m-wang/AnnaAgent.