MoRI: Learning Motivation-Grounded Reasoning for Scientific Ideation in Large Language Models

arXiv:2603.19044v2 Announce Type: replace Abstract: Scientific ideation aims to propose novel solutions within a given scientific context. Existing LLM-based agentic approaches emulate human research workflows, yet inadequately model scientific reasoning, resulting in surface-level conceptual recombinations that lack technical depth and scientific grounding. To address this issue, we propose extbf{MoRI} (extbf{Mo}tivation-grounded extbf{R}easoning for Scientific extbf{I}deation), a framework that enables LLMs to explicitly learn the reasoning process from research motivations to methodologies. The base LLM is initialized via supervised fine-tuning to generate a research motivation from a given context, and is subsequently trained under a composite reinforcement learning reward that approximates scientific rigor: (1) entropy-aware information gain encourages the model to uncover and elaborate high-complexity technical details grounded in ground-truth methodologies, and (2) contrastive semantic gain constrains the reasoning trajectory to remain conceptually aligned with scientifically valid solutions. Empirical results show that MoRI consistently outperforms strong commercial LLMs and complex agentic baselines across multiple dimensions, including novelty, technical rigor, and feasibility. The code is available on href{https://github.com/ECNU-Text-Computing/IdeaGeneration}{GitHub}.

Related

• MIND: AI Co-Scientist for Material Research
• What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations
• Structure-Grounded Knowledge Retrieval via Code Dependencies for Multi-Step Data Reasoning
• A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks

Source: arXiv cs.CL | 2026-04-21