Collaborative agents improve automated related work writing in research
Assembling the CREW: A Collaborative Multi-agent Reinforcement Learning Framework for Automated Related Work Generation
Machine Learning
Summary
Writing the related work section of a research paper takes a lot of time. The authors created a new system called CREW that uses multiple AI agents working together more flexibly to write this section. Instead of following a fixed step-by-step plan, the AI agents choose what actions to take, like finding papers or writing summaries, based on what works best. This approach leads to better writing quality and uses fewer computing resources.
What this means in practice
- •For academic writing software developers: Create tools that auto-generate related work sections by coordinating multiple AI agents that adaptively choose writing tasks to improve quality and efficiency.
- •For legal document teams: Develop AI systems that collaboratively analyze and summarize previous legal cases to assist in drafting related work or precedent sections.
Authors
Hai-Dang Dang, Bao-Yen Pham, Bao Nguyen, Tran Thi Huong, Huynh Thi Thanh Binh
Abstract
Automatic Related Work Generation (RWG) significantly reduces the human time and effort required to author the Related Work Section (RWS) of a research paper. However, prior methods leveraging multi-agent Large Language Models (LLMs) typically rely on a predefined workflow, where each agent is responsible for a specific step in the entire process. This rigid, static inter-agent coordination limits the adaptive collaboration required to synthesize complex scientific literature. To address this limitation, we propose CREW (Collaborative Reinforcement Learning for Related Work Generation), a novel framework where LLM agents bypass heuristic pipelines to dynamically coordinate by autonomously selecting actions, such as Retrieve, Disseminate, Compose, and Critique, driven by a policy optimized via Independent Proximal Policy Optimization (IPPO). Extensive experiments on a standard RWG benchmark demonstrate that our approach yields substantial quality improvements over strong existing baselines, while significantly reducing token costs. Code is available at https://github.com/YenPBao/CREW-Collaborative-MARL.git