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

arXiv: https://arxiv.org/abs/2506.00551 · HTML: https://mlsanity.com/paper/2506.00551/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 62 references that are in the map.
- First posted on arXiv 31 May 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 19 of 19)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink](https://mlsanity.com/paper/2204.05149/) (2022)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations](https://mlsanity.com/paper/2311.00273/) (2023)
- [Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment](https://mlsanity.com/paper/2401.12474/) (2024)
- [CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling](https://mlsanity.com/paper/2405.16433/) (2024)
- [The Oscars of AI Theater: A Survey on Role-Playing with Language Models](https://mlsanity.com/paper/2407.11484/) (2024)
- [Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions](https://mlsanity.com/paper/2408.15787/) (2024)
- [D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat](https://mlsanity.com/paper/2205.11764/) (2022)
- [PsycoLLM: Enhancing LLM for Psychological Understanding and Evaluation](https://mlsanity.com/paper/2407.05721/) (2024)
- [Leveraging Large Language Model as Simulated Patients for Clinical Education](https://mlsanity.com/paper/2404.13066/) (2024)
- [Depression Diagnosis Dialogue Simulation: Self-improving Psychiatrist with Tertiary Memory](https://mlsanity.com/paper/2409.15084/) (2024)
- [Deep Learning Mental Health Dialogue System](https://mlsanity.com/paper/2301.09412/) (2023)
- [Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts](https://mlsanity.com/paper/2409.13449/) (2024)

## Built on by (most cited first, 21 of 21)

- [ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional Support](https://mlsanity.com/paper/2602.01885/) (2026)
- [LifeSim: Long-Horizon User Life Simulator for Personalized Assistant Evaluation](https://mlsanity.com/paper/2603.12152/) (2026)
- [TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling](https://mlsanity.com/paper/2510.25758/) (2025)
- [PatientHub: A Unified Framework for Patient Simulation](https://mlsanity.com/paper/2602.11684/) (2026)
- [Controlling Long-Horizon Behavior in Language Model Agents with Explicit State Dynamics](https://mlsanity.com/paper/2601.16087/) (2026)
- [Responsible Evaluation of AI for Mental Health](https://mlsanity.com/paper/2602.00065/) (2026)
- [Momento: Evaluating Persistent Memory and Reasoning with Multi-Session Agentic Conversations](https://mlsanity.com/paper/2606.00832/) (2026)
- [Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events](https://mlsanity.com/paper/2608.06485/) (2026)
- [LLMs vs. Chinese Anime Enthusiasts: A Comparative Study on Emotionally Supportive Role-Playing](https://mlsanity.com/paper/2508.06388/) (2025)
- [PsyCLIENT: Client Simulation via Conversational Trajectory Modeling for Trainee Practice and Model Evaluation in Mental Health Counseling](https://mlsanity.com/paper/2601.07312/) (2026)
- [Stress-Testing Emotional Support Models: Moving from Homogeneous to Diverse Help Seekers](https://mlsanity.com/paper/2601.07698/) (2026)
- [DMT-CBT: Longitudinal Therapeutic State Modeling for CBT Counseling](https://mlsanity.com/paper/2606.03132/) (2026)
- [PatientAct: Theory-Grounded Mental Health Client Simulation](https://mlsanity.com/paper/2608.12750/) (2026)
- [Enhancing Mental Health Counseling Support in Bangladesh using Culturally-Grounded Knowledge](https://mlsanity.com/paper/2604.14576/) (2026)
- [Cognitive Policy-Driven LLM for Diagnosis and Intervention of Cognitive Distortions in Emotional Support Conversation](https://mlsanity.com/paper/2604.17178/) (2026)
- [Trust Stack for Mental Health AI: A Survey of Calibration across Human, Interaction, and AI Layers](https://mlsanity.com/paper/2604.20166/) (2026)
- [When Clients Stop Following: A Cognitive Conceptualization Diagram-driven Framework for Strategic Counseling](https://mlsanity.com/paper/2606.04389/) (2026)
- [PRISM: Prosody-Integrated Multi-Agent Reasoning Framework for Empathetic Spoken Dialogue](https://mlsanity.com/paper/2606.12902/) (2026)
- [From Triggers to Emotions: A CPM-Grounded Appraisal Multi-Agent for Dynamic Emotional Evolution in Persona-Based Dialogue](https://mlsanity.com/paper/2607.07824/) (2026)
- [From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health](https://mlsanity.com/paper/2609.25186/) (2026)
- [MACBT: A Multi-Agent Cognitive Behavioral Therapy Decision Support System with Longitudinal Memory](https://mlsanity.com/paper/2609.30939/) (2026)

## Abstract (arXiv)

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.