Paper 2601.20833
Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives
- Published
- Jan 2026
- Research lab
- Independent
- Citations
- 5
- GitHub
- 1.4K stars
01 In brief
Summary
Idea2Story is a framework for autonomous scientific discovery that shifts literature understanding from online reasoning to offline knowledge construction.
It builds a structured methodological knowledge graph from peer-reviewed papers (about 13,000 from NeurIPS and ICLR over three years) and their review feedback, extracting reusable method units and composing them into research patterns.
At runtime, user research intents are aligned to these patterns via multi-view retrieval (idea, domain, paper levels), and patterns are refined through an LLM-based review loop.
This approach reduces computational cost, alleviates context window limitations, and mitigates hallucination compared to runtime-centric agents.
Qualitative comparisons show Idea2Story generates research patterns with clearer problem reformulation, stronger methodological structure, and higher novelty than direct LLM generation.
The codebase is publicly available at https://github.com/AgentAlphaAGI/Idea2Paper.git.
Future work includes integrating experimental agents for a closed-loop pipeline and translating patterns into complete paper drafts.
02 From the paper
Abstract
Autonomous scientific discovery with large language model (LLM)-based agents has recently made substantial progress, demonstrating the ability to automate end-to-end research workflows. However, existing systems largely rely on runtime-centric execution paradigms, repeatedly reading, summarizing, and reasoning over large volumes of scientific literature online. This on-the-spot computation strategy incurs high computational cost, suffers from context window limitations, and often leads to brittle reasoning and hallucination. We propose Idea2Story, a pre-computation-driven framework for autonomous scientific discovery that shifts literature understanding from online reasoning to offline knowledge construction. Idea2Story continuously collects peer-reviewed papers together with their review feedback, extracts core methodological units, composes reusable research patterns, and organizes them into a structured methodological knowledge graph. At runtime, underspecified user research intents are aligned to established research paradigms, enabling efficient retrieval and reuse of high-quality research patterns instead of open-ended generation and trial-and-error. By grounding research planning and execution in a pre-built knowledge graph, Idea2Story alleviates the context window bottleneck of LLMs and substantially reduces repeated runtime reasoning over literature. We conduct qualitative analyses and preliminary empirical studies demonstrating that Idea2Story can generate coherent, methodologically grounded, and novel research patterns, and can produce several high-quality research demonstrations in an end-to-end setting. These results suggest that offline knowledge construction provides a practical and scalable foundation for reliable autonomous scientific discovery.