构建可动态演化的心理咨询模拟器，支持多轮记忆保持
AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation
- 用情绪调节器与症状诱导器动态控制角色状态
- 三级记忆机制实现跨会话的短期与长期记忆融合
- 在真实对话数据上训练，适合心理健康研究应用
受限于真实求助者参与人工智能心理干预的成本与伦理问题，研究人员开发了基于大语言模型的对话代理（CAs），通过定制人物画像、症状和情境来模拟求助者。尽管已有进展，但实现更真实的模拟仍面临两大挑战：动态演化与多会话记忆。求助者的心理状态常随咨询过程波动，而咨询通常跨越多个会话。为此，我们提出AnnaAgent——一种具备情感与认知动态演化的代理系统，配备三级记忆机制。AnnaAgent引入基于真实咨询对话训练的情绪调节器与症状诱导器，实现对模拟器配置的动态调控；其三级记忆机制能有效整合会话间的短期与长期记忆。自动化与人工评估结果表明，相比现有基线，AnnaAgent在心理咨询服务模拟中表现更真实。经伦理审查并筛选的代码已发布于https://github.com/sci-m-wang/AnnaAgent。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。