Metraipolis › archive › dc_7287f5ddeb09
Assembling the CREW: A Collaborative Multi-agent Reinforcement Learning Framework for Automated Related Work Generation — arXiv:2609.15721
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.15721
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:12:01.168Z
- SHA-256 of the archived text
c8337d97c467e42a5ac9abab76339d7d75889f48c572e5656d18573196c6e382- Stable URL of this page
https://metraipolis.com/documento/dc_7287f5ddeb09
How to cite
Assembling the CREW: A Collaborative Multi-agent Reinforcement Learning Framework for Automated Related Work Generation — arXiv:2609.15721 — arXiv (en), https://arxiv.org/abs/2609.15721 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7287f5ddeb09 (Metraipolis archive dc_7287f5ddeb09, sha256 c8337d97c467e42a5ac9abab76339d7d75889f48c572e5656d18573196c6e382)
BibTeX
@misc{dc7287f5ddeb09,
title = {Assembling the CREW: A Collaborative Multi-agent Reinforcement Learning Framework for Automated Related Work Generation — arXiv:2609.15721},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.15721},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7287f5ddeb09; sha256 c8337d97c467e42a5ac9abab76339d7d75889f48c572e5656d18573196c6e382},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15721. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 this https URL Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.15721 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T23:54:14.789Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).