FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration

View PDF HTML (experimental)

Abstract:Scientific idea generation (SIG) is critical to AI-driven autonomous research, yet existing approaches are often constrained by a static retrieval-then-generation paradigm, leading to homogeneous and insufficiently divergent ideas. In this work, we propose FlowPIE, a tightly coupled retrieval-generation framework that treats literature exploration and idea generation as a co-evolving process. FlowPIE expands literature trajectories via a flow-guided Monte Carlo Tree Search (MCTS) inspired by GFlowNets, using the quality of current ideas assessed by an LLM-based generative reward model (GRM) as a supervised signal to guide adaptive retrieval and construct a diverse, high-quality initial population. Based on this population, FlowPIE models idea generation as a test-time idea evolution process, applying selection, crossover, and mutation with the isolation island paradigm and GRM-based fitness computation to incorporate cross-domain knowledge. It effectively mitigates the information cocoons arising from over-reliance on parametric knowledge and static literature. Extensive evaluations demonstrate that FlowPIE consistently produces ideas with higher novelty, feasibility and diversity compared to strong LLM-based and agent-based frameworks, while enabling reward scaling during test time.

Comments: 30 pages, 11 figures, 15 tables

Subjects:

Artificial Intelligence (cs.AI); Computation and Language (cs.CL)

Cite as: arXiv:2603.29557 [cs.AI]

(or arXiv:2603.29557v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2603.29557

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Qiyao Wang [view email] [v1] Tue, 31 Mar 2026 10:37:47 UTC (1,987 KB)