Research map / Large language models / Agents, code and math
Simulating Human-Like Counseling: A Path- and Scenario-Guided Framework for Psychological Support Dialogue
Yuanchen Shi, Longyin Zhang, Maodong Li, Yibin Zheng, Xiuhong Wang, Fang Kong
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Planner agent (ablation) | CADSS · CPsDD | BLEU-4: 7.25 -> 16.54 | Improved |
| add Planner agent (ablation) | CADSS · CPsDD | ROUGE-L: 25.71 -> 37.97 | Improved |
| add Summarizer agent (ablation) | CADSS · CPsDD | BLEU-4: 16.04 -> 16.54 | Improved |
| add Profiler agent (ablation) | CADSS · CPsDD | strategy accuracy: 79.68 -> 80.98 | Improved |
| add Summarizer agent (ablation) | CADSS · CPsDD | strategy accuracy: 80.91 -> 80.98 | Improved |
| add Planner agent (ablation) | CADSS · ESConv | BLEU-4: 4.61 -> 5.64 | Improved |
| add Summarizer agent (ablation) | CADSS · ESConv | strategy accuracy: 45.64 -> 46.26 | Improved |
| add Profiler agent (ablation) | CADSS · ESConv | strategy accuracy: 45.57 -> 46.26 | Improved |
| add Profiler agent (ablation) | CADSS · ESConv | BLEU-4: 5.45 -> 5.64 | Improved |
| add all agents (ablation) | CADSS · CPsDD | BLEU-4: 6.79 -> 16.54 | Improved |
| add agents (ablation) | CADSS · CPsDD | Distinct-n: D-2 98.92 vs 99.04 (w/o all) | No clear effect |
| add Planner agent (ablation) | CADSS · ESConv | PPL: 31.81 -> 30.14 | Hurt |
Closest papers by meaning
- An LLM-based Simulation Framework for Embodied Conversational Agents in Psychological Counseling (AAAI 2026 · similarity 0.87)
- STAMPsy: Towards SpatioTemporal-Aware Mixed-Type Dialogues for Psychological Counseling (AAAI 2025 · similarity 0.87)
- Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents (ICLR 2024 · similarity 0.86)
- SocialSim: Towards Socialized Simulation of Emotional Support Conversation (AAAI 2025 · similarity 0.85)
- Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues (AAAI 2025 · similarity 0.85)
- TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots (NeurIPS 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
