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

arXiv: https://arxiv.org/abs/2509.21849 · HTML: https://mlsanity.com/paper/2509.21849/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 22 of 22)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://mlsanity.com/paper/1603.08023/) (2016)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [MIME: MIMicking Emotions for Empathetic Response Generation](https://mlsanity.com/paper/2010.01454/) (2020)
- [MoEL: Mixture of Empathetic Listeners](https://mlsanity.com/paper/1908.07687/) (2019)
- [CEM: Commonsense-aware Empathetic Response Generation](https://mlsanity.com/paper/2109.05739/) (2021)
- [Knowledge Bridging for Empathetic Dialogue Generation](https://mlsanity.com/paper/2009.09708/) (2020)
- [DialogueLLM: Context and Emotion Knowledge-Tuned Large Language Models for Emotion Recognition in Conversations](https://mlsanity.com/paper/2310.11374/) (2023)
- [Rethinking and Refining the Distinct Metric](https://mlsanity.com/paper/2202.13587/) (2022)
- [CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation](https://mlsanity.com/paper/2208.08845/) (2022)
- [Exemplars-guided Empathetic Response Generation Controlled by the Elements of Human Communication](https://mlsanity.com/paper/2106.11791/) (2021)
- [Fine-Grained Emotion Prediction by Modeling Emotion Definitions](https://mlsanity.com/paper/2107.12135/) (2021)
- [DiffusEmp: A Diffusion Model-Based Framework with Multi-Grained Control for Empathetic Response Generation](https://mlsanity.com/paper/2306.01657/) (2023)
- [Reasoning before Responding: Integrating Commonsense-based Causality Explanation for Empathetic Response Generation](https://mlsanity.com/paper/2308.00085/) (2023)
- [CARE: Causality Reasoning for Empathetic Responses by Conditional Graph Generation](https://mlsanity.com/paper/2211.00255/) (2022)
- [Wish I Can Feel What You Feel: A Neural Approach for Empathetic Response Generation](https://mlsanity.com/paper/2212.02000/) (2022)
- [CAF-I: A Collaborative Multi-Agent Framework for Enhanced Irony Detection with Large Language Models](https://mlsanity.com/paper/2506.08430/) (2025)

## Abstract (arXiv)

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.