Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives

TL;DR

Idea2Story tackles the inefficiency and unreliability of runtime-only autonomous scientific discovery by introducing a two-stage, pre-computation driven pipeline. It offline builds a structured knowledge graph of reusable methodological units from a curated pool of peer reviewed work, extracting core units and organizing them as canonicalized nodes and their composition relationships. At runtime, underspecified user intents are grounded by retrieving and composing these learned patterns from the graph, followed by a review-guided refinement loop to ensure novelty and feasibility. The approach yields coherent, methodologically grounded, and novel research patterns, demonstrated through qualitative analyses and end-to-end demonstrations, and is supported by a publicly available codebase. This offline knowledge grounding provides a scalable foundation for reliable autonomous discovery and mitigates context window bottlenecks inherent to large language models.

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.

Figures (4)

• Figure 1: Overview of the two-stage framework in Idea2Story. The offline stage constructs a structured knowledge graph by extracting and organizing reusable method units from a curated paper corpus. The online stage retrieves and composes research patterns from the knowledge graph to ground underspecified user intent into concrete and coherent research directions.
• Figure 2: Offline knowledge graph construction in Idea2Story. Academic papers and their associated review artifacts are first anonymized and safety-filtered, then deconstructed into layered methodological representations. These layers capture complementary aspects of a paper, including its core research idea, domain context, high-level story skeleton, and packaging actions. The extracted elements are normalized into atomic method units and meta-methods, which are connected through composition and similarity relations. Reviewer feedback is incorporated as additional signals to refine relations and validate abstractions.
• Figure 3: An example of a method unit extracted from an accepted paper, illustrating the separation of the base problem, solution pattern, and higher-level research story.
• Figure 4: Visualization of the knowledge graph substructure induced by high-frequency research domains.