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

TL;DR

AnnaAgent tackles the realism gap in AI-driven seeker simulation by addressing two core challenges: dynamic evolution of emotional states and multi-session memory. It integrates an emotion modulator and a chief-complaint elicitor to dynamically steer seeker configurations, paired with a tertiary memory system that schedules real-time, short-term, and long-term memories across counseling sessions. Trained on real counseling data and evaluated against multiple baselines, AnnaAgent demonstrates superior anthropomorphism and personality fidelity, and shows resilience across backbone LLMs. The approach promises more ethically informed, scalable tools for counselor training and mental health research, with explicit acknowledgment of privacy and misuse risks.

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.

Figures (9)

• Figure 1: Examples of the two challenges in seeker simulation. Subfigure (a) for dynamic evolution and (b) for multi-session memory.
• Figure 2: The overall structure of AnnaAgent. There are two groups of agents in AnnaAgent that are used to control dynamic evolution (upper part in the figure) and schedule multi-session memories (lower part in the figure), respectively. The middle part of the figure indicates different counseling sessions, with yellow indicating the previous session and red indicating the two states in the current session.
• Figure 3: Division of tertiary memory mechanisms
• Figure 4: G-Eval scores for personality fidelity.
• Figure 5: G-Eval scores of virtual seekers answering questions when ablating long-term memory, respectively. 'LTM' denotes Long-term Memory.