Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training

Computer Science > Artificial Intelligence [Submitted on 17 Apr 2026] Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training Moein Salimi, Babak Hosseini Mohtasham, Amin Aghakasiri, Mahdi Naieni, Amir Hossein Qeysarbeigi, Mohammad Masih Shalchian Nazer, Zahra Azar, Mahdi Jafari Siavoshani, Mohammad Hossein Rohban Large Language Models (LLMs) have demonstrated potential in automating scientific ideation, yet current approaches relying on iterative prompting or complex multi-agent architectures often suffer from hallucination or computational inefficiency. A critical bottleneck in applying Reinforcement Learning (RL) to this open-ended domain is reward hacking -- where models exploit imperfect evaluation proxies to maximize scores without producing genuine scientific innovation. To address these limitations, we propose an RL framework explicitly tailored for high-quality scientific idea generation. We propose the first multi-agent reward function designed to serve as a judge, decoupling methodological validation from implementation details while providing strict binary rewards that are robust to reward hacking. To effectively optimize against this sparse signal, we utilize an unbiased variant of Group Relative Policy Optimization to mitigate artificial length bias. We grounded our training in ICLR-320, a curated dataset of problem-solution pairs extracted from ICLR 2024 proceedings. Experiments demonstrate that our framework significantly outperforms state-of-the-art baselines across expert-evaluated metrics of novelty, feasibility, and effectiveness. Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2604.16723 [cs.AI]   (or arXiv:2604.16723v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.16723 Focus to learn more Submission history From: Mahdi Jafari Siavoshani [view email] [v1] Fri, 17 Apr 2026 21:54:15 UTC (4,479 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)