Following the TRACE: A Structured Path to Empathetic Response Generation with Multi-Agent Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Ziqi, Zhou, Ziyang, Li, Yilin, Zhang, Haiyang, Chen, Yangbin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909993879470080
author Liu, Ziqi
Zhou, Ziyang
Li, Yilin
Zhang, Haiyang
Chen, Yangbin
author_facet Liu, Ziqi
Zhou, Ziyang
Li, Yilin
Zhang, Haiyang
Chen, Yangbin
contents Empathetic response generation is a crucial task for creating more human-like and supportive conversational agents. However, existing methods face a core trade-off between the analytical depth of specialized models and the generative fluency of Large Language Models (LLMs). To address this, we propose TRACE, Task-decomposed Reasoning for Affective Communication and Empathy, a novel framework that models empathy as a structured cognitive process by decomposing the task into a pipeline for analysis and synthesis. By building a comprehensive understanding before generation, TRACE unites deep analysis with expressive generation. Experimental results show that our framework significantly outperforms strong baselines in both automatic and LLM-based evaluations, confirming that our structured decomposition is a promising paradigm for creating more capable and interpretable empathetic agents. Our code is available at https://anonymous.4open.science/r/TRACE-18EF/README.md.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21849
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Following the TRACE: A Structured Path to Empathetic Response Generation with Multi-Agent Models
Liu, Ziqi
Zhou, Ziyang
Li, Yilin
Zhang, Haiyang
Chen, Yangbin
Computation and Language
Multiagent Systems
Empathetic response generation is a crucial task for creating more human-like and supportive conversational agents. However, existing methods face a core trade-off between the analytical depth of specialized models and the generative fluency of Large Language Models (LLMs). To address this, we propose TRACE, Task-decomposed Reasoning for Affective Communication and Empathy, a novel framework that models empathy as a structured cognitive process by decomposing the task into a pipeline for analysis and synthesis. By building a comprehensive understanding before generation, TRACE unites deep analysis with expressive generation. Experimental results show that our framework significantly outperforms strong baselines in both automatic and LLM-based evaluations, confirming that our structured decomposition is a promising paradigm for creating more capable and interpretable empathetic agents. Our code is available at https://anonymous.4open.science/r/TRACE-18EF/README.md.
title Following the TRACE: A Structured Path to Empathetic Response Generation with Multi-Agent Models
topic Computation and Language
Multiagent Systems
url https://arxiv.org/abs/2509.21849