Paper Detail

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

Qiyao Wang, Hongbo Wang, Longze Chen, Zhihao Yang, Guhong Chen, Hamid Alinejad-Rokny, Hui Li, Yuan Lin, Min Yang

huggingface Score 10.0

Published 2026-03-31 · First seen 2026-04-01

General AI

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{wang2026flowpie,
  title = {FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration},
  author = {Qiyao Wang and Hongbo Wang and Longze Chen and Zhihao Yang and Guhong Chen and Hamid Alinejad-Rokny and Hui Li and Yuan Lin and Min Yang},
  year = {2026},
  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 GFl},
  url = {https://huggingface.co/papers/2603.29557},
  keywords = {flow-guided Monte Carlo Tree Search, GFlowNets, generative reward model, isolation island paradigm, test-time idea evolution, selection, crossover, mutation, code available, huggingface daily},
  eprint = {2603.29557},
  archiveprefix = {arXiv},
}

Metadata

{}