arXiv Open Access 2026

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

Qiyao Wang Hongbo Wang Longze Chen Zhihao Yang Guhong Chen +4 lainnya
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (9)

Q

Qiyao Wang

H

Hongbo Wang

L

Longze Chen

Z

Zhihao Yang

G

Guhong Chen

H

Hamid Alinejad-Rokny

H

Hui Li

Y

Yuan Lin

M

Min Yang

Format Sitasi

Wang, Q., Wang, H., Chen, L., Yang, Z., Chen, G., Alinejad-Rokny, H. et al. (2026). FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration. https://arxiv.org/abs/2603.29557

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2026
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓