AI Paper Atlas

Research map / Large language models / Agents, code and math

MentalGuide: Towards Multi-Turn, State-Aware and Strategy-Driven Conversations for Mental Health Support

Jinwei He, Feng Lu

AAAI 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks

Read the paperCheck your idea against 137,217 papers

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 expert state-strategy prior probabilities (ablation)MentalGuide (Deepseek-V3) · Strategy correctnessaccuracy (%): 38.68 -> 52.45Improved
add expert state-strategy prior probabilities (ablation)MentalGuide (Qwen-3-Plus) · Strategy correctnessaccuracy (%): 41.15 -> 48.25Improved
add expert prior knowledge (ablation)MentalGuide (Deepseek-V3) · Strategic execution (multi-turn)score 0-3: 2.35 -> 2.52No clear effect
add expert prior knowledge (ablation)MentalGuide (Deepseek-V3) · Strategy distribution deviation per roundMr: 8.46 -> 6.02Improved
add expert prior knowledge (ablation)MentalGuide (Deepseek-V3) · Strategy distribution deviation per client stateMs: 11.62 -> 5.11Improved
use LLM-ranking weights 300/200/100 instead of 72/64/36 (ablation)MentalGuide · Strategy distribution deviation per roundMr: 6.02 -> 8.29Hurt
use LLM-ranking weights 30/20/10 instead of 72/64/36 (ablation)MentalGuide · Strategy distribution deviation per roundMr: 6.02 -> 9.23Hurt
select k=1 final strategy instead of 2 (ablation)MentalGuide · Strategy distribution deviation per roundMr: 6.02 -> 10.91Hurt
select k=3 final strategies instead of 2 (ablation)MentalGuide · Strategy distribution deviation per roundMr: 6.02 -> 7.45Hurt
MentalGuide vs RolePlay on same LLMRolePlay (Deepseek-V3) · Strategic execution (multi-turn)score 0-3: 1.55 -> 2.52Improved
MentalGuide vs RolePlay on single-turn emotional empathyRolePlay (Qwen-3-Plus) · Single-turn emotional empathyscore 0-3: 2.25 -> 2.58Improved
MentalGuide vs RolePlay and SoulChat in human expert rankingMentalGuide · Human expert ranking (10 scenarios, 10 psychologists)share of Rank 1: Rank 1 in 58% of cases; Rank 3 in 10%Improved

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