Scientific Hypothesis Generation

Follow this topic Ask about this topic

Momentum

9 papers in the last four weeks, up 125% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 66

All topics

Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training
Apr 17, 2026Moein Salimi, Babak Hosseini Mohtasham, Amin Aghakasiri +6Reward Hacking RL for Language Models
Sharif University of Technology · University of Tehran · Sharif University of Technology[cs.AI]
Continuous Knowledge Metabolism: Generating Scientific Hypotheses from Evolving Literature
Apr 14, 2026Jinkai Tao, Yubo Wang, Xiaoyu Liu +1Scientific Discovery Scientific Hypothesis Generation
TsingyuAI, Beijing, China · School of Information, Central University of Finance and Economics, Beijing, China · Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China +1
AI Can Learn Scientific Taste
Mar 15, 2026Jingqi Tong, Mingzhe Li, Hangcheng Li +20AI for Science Scientific Hypothesis Generation
Fudan University · Shanghai Innovation Institute · OpenMOSS Team +2
From Literature to Hypotheses: An AI Co-Scientist System for Biomarker-Guided Drug Combination Hypothesis Generation
Feb 28, 2026Raneen Younis, Suvinava Basak, Lukas Chavez +1Scientific Hypothesis Generation Oncology
Peter L. Reichertz Institute for Medical Informatics (PLRI), Hannover Medical School · Lower Saxony Center for Artificial Intelligence and Causal Methods in Medicine (CAIMed) · Sanford Burnham Prebys (SBP) Medical Discovery Institute
Accelerating scientific discovery with Co-Scientist
Feb 26, 2025Juraj Gottweis, Wei-Hung Weng, Alexander Daryin +48Multi-Agent LLM Systems Scientific Hypothesis Generation
Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders
May 27, 2024Xuemei Gu, Mario KrennAI-Assisted Scientific Research Scientific Hypothesis Generation
Max Planck Institute for the Science of Light, Staudtstrasse 2, 91058 Erlangen, Germany

Apr 17, 2026, cs.AIJ/K move · Enter open · S save

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

Moein Salimi, Babak Hosseini Mohtasham, Amin Aghakasiri, Mahdi Naieni+5

Sharif University of Technology · University of Tehran · Sharif University of Technology[cs.AI]

Reward Hacking RL for Language Models Multi-Agent LLM Systems Scientific Hypothesis Generation Large Language Model-Guided Scientific Discovery

Open paper AskPDF arXiv

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.

Momentum

Related topics

Latest papers 66

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

Continuous Knowledge Metabolism: Generating Scientific Hypotheses from Evolving Literature

AI Can Learn Scientific Taste

From Literature to Hypotheses: An AI Co-Scientist System for Biomarker-Guided Drug Combination Hypothesis Generation

Accelerating scientific discovery with Co-Scientist

Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders