AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

ESCA: An Emotional Support Conversation Agent for Enhancing Reasonable Strategy Planning and Effective Expression

Jing Li, Yanxin Luo, Donghong Han, Yimeng Zhan, Xiaoming Fu, Baiyou Qiao, Gang Wu

AAAI 2026 · Multi-agent systems and games › LLM agents · approach: Agent data synthesis and behavior studies · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes ESCA, an LLM-based emotional support conversation agent aimed at improving strategy planning and the expression of support strategies in responses.

Problem

Emotional Support Conversation (ESC) requires planning reasonable support strategies over multi-turn dialogue and expressing them effectively in responses; existing methods struggle with both.

Approach

An LLM-based agent (ESCA) designed to plan support strategies more reasonably and express them more effectively in generated responses; specific mechanism not stated in the abstract provided.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add seeker state information (emotion, trust, behavior, stage) to the strategy planner (ablation)ESCA · ESConv goal achievementSR@10 (%): 37.31 -> 47.44Improved
add external knowledge to the prompt generator (ablation)ESCA · ESConv goal achievementSR@10 (%): 40.33 -> 47.44Improved
add the trained prompt generator instead of inserting retrieved knowledge directly (ablation)ESCA · ESConv goal achievementSR@10 (%): 32.31 -> 47.44Improved
add online RL (PPO) optimization of the prompt generator (ablation)ESCA · ESConv goal achievementSR@10 (%): 44.61 -> 47.44Improved
add online RL (PPO) optimization of the prompt generator (ablation)ESCA · ESConv response generationDistinct-1/2/3: D-1 6.32 -> 6.15; D-2 31.73 -> 30.51Hurt
use ESCA (LLaMA2-7b) instead of DPDP (LLaMA-13b) as the goal-achievement agentstrategy planning agent · ESConv goal achievementSR@10 (%): 32.31 -> 47.44Improved
use ESCA instead of D2RCU on response qualityresponse generator · ESConv response generationBLEU-4 / ROUGE-L: B-4 2.68 -> 2.50; R-L 18.12 -> 17.87; D-2 28.89 -> 30.51Mixed

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