IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas

arXiv:2610.08781v1 Announce Type: cross Abstract: Scientific research often begins by synthesizing ideas from a set of related papers to identify gaps and formulate new directions. However, training language models to perform this form of literature-grounded ideation remains challenging, as existing approaches based on prompting or feedback lack structured supervision for how papers should be synthesized. We introduce IdeaAnchor, a paradigm for training LLMs to perform research ideation using structured specifications as privileged signals. Each IdeaAnchor instance encodes how each input paper should be synthesized into a successful idea, including their functional roles, relationships, and target synthesis criteria. We build this paradigm by mining instances from published papers, capturing how real ideas emerge from prior literature. We then train models via demonstration, self-distillation, and reinforcement learning, and further enhance generation with retrieval at inference time. Experiments show consistent improvements in ideation quality. Our analysis reveals a functional decomposition: anchor-based training strengthens creative synthesis, retrieval enhances detail elaboration, and combining both yields the best performance.

Related

• Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders
• ReMIND: Orchestrating Modular Large Language Models for Controllable Serendipity A REM-Inspired System Design for Emergent Creative Ideation
• Automating Categorization of Scientific Texts with In-Context Learning and Prompt-Chaining in Large Language Models

Source: arXiv cs.AI | 2026-10-07