一句话：提出基于LLM的多智能体框架，可生成、解释并与人类开发者协商敏捷工作量估算。
敏捷开发中，工作量估算通常由团队主观讨论完成，易导致不一致和不准确。已有机器学习方法虽提升精度，但难以解释估算依据，也无法与团队成员交互。本文提出一种基于大语言模型的多智能体框架，用于敏捷工作量估算：智能体不仅能给出估算，还能相互协调、沟通，并与人类开发者讨论以达成共识。作者在真实数据集上与当前最优技术比较，多数情况下在所有评价指标上更优；同时开展开发者用户研究，显示与智能体协作进行估算的体验获得压倒性积极反馈。
Effort estimation is a crucial activity in agile software development, where teams collaboratively review, discuss, and estimate the effort required to complete user stories in a product backlog. Current practices in agile effort estimation heavily rely on subjective assessments, leading to inaccuracies and inconsistencies in the estimates. While recent machine learning-based methods show promising accuracy, they cannot explain or justify their estimates and lack the capability to interact with human team members. Our paper fills this significant gap by leveraging the powerful capabilities of Large Language Models (LLMs). We propose a novel LLM-based multi-agent framework for agile estimation that not only can produce estimates, but also can coordinate, communicate and discuss with human developers and other agents to reach a consensus. Evaluation results on a real-life dataset show that our approach outperforms state-of-the-art techniques across all evaluation metrics in the majority of cases. Our human study with software development practitioners also demonstrates an overwhelmingly positive experience in collaborating with our agents in agile effort estimation.
DOI 原文 ·
@inproceedings{paperbot9329,
title = {An LLM-based multi-agent framework for agile effort estimation},
author = {Thanh-Long Bui and Hoa Khanh Dam and Rashina Hoda},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00090}
}