AI Paper Atlas

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

AAAI 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 0 citations (OpenAlex)

Read the paper

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 changedWhereMeasuredEffect
add Planner agent (ablation)CADSS · CPsDDBLEU-4: 7.25 -> 16.54Improved
add Planner agent (ablation)CADSS · CPsDDROUGE-L: 25.71 -> 37.97Improved
add Summarizer agent (ablation)CADSS · CPsDDBLEU-4: 16.04 -> 16.54Improved
add Profiler agent (ablation)CADSS · CPsDDstrategy accuracy: 79.68 -> 80.98Improved
add Summarizer agent (ablation)CADSS · CPsDDstrategy accuracy: 80.91 -> 80.98Improved
add Planner agent (ablation)CADSS · ESConvBLEU-4: 4.61 -> 5.64Improved
add Summarizer agent (ablation)CADSS · ESConvstrategy accuracy: 45.64 -> 46.26Improved
add Profiler agent (ablation)CADSS · ESConvstrategy accuracy: 45.57 -> 46.26Improved
add Profiler agent (ablation)CADSS · ESConvBLEU-4: 5.45 -> 5.64Improved
add all agents (ablation)CADSS · CPsDDBLEU-4: 6.79 -> 16.54Improved
add agents (ablation)CADSS · CPsDDDistinct-n: D-2 98.92 vs 99.04 (w/o all)No clear effect
add Planner agent (ablation)CADSS · ESConvPPL: 31.81 -> 30.14Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy