{"ID":2865009,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21849","arxiv_id":"2509.21849","title":"Following the TRACE: A Structured Path to Empathetic Response Generation with Multi-Agent Models","abstract":"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.","short_abstract":"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-decom...","url_abs":"https://arxiv.org/abs/2509.21849","url_pdf":"https://arxiv.org/pdf/2509.21849v2","authors":"[\"Ziqi Liu\",\"Ziyang Zhou\",\"Yilin Li\",\"Haiyang Zhang\",\"Yangbin Chen\"]","published":"2025-09-26T04:20:37Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.MA\"]","methods":"[\"Large Language Model\",\"Language Model\"]","project_urls":"[\"https://anonymous.4open.science/r/TRACE-18EF/README.md\"]","has_code":false}