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

arXiv: https://arxiv.org/abs/2603.29557 · HTML: https://mlsanity.com/paper/2603.29557/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 16 of 16)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [GFlowNet Foundations](https://mlsanity.com/paper/2111.09266/) (2021)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms](https://mlsanity.com/paper/2406.14228/) (2024)
- [Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process](https://mlsanity.com/paper/2407.20311/) (2024)
- [AI-Researcher: Autonomous Scientific Innovation](https://mlsanity.com/paper/2505.18705/) (2025)
- [Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents](https://mlsanity.com/paper/2410.13185/) (2024)
- [Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System](https://mlsanity.com/paper/2410.09403/) (2024)
- [AI4Research: A Survey of Artificial Intelligence for Scientific Research](https://mlsanity.com/paper/2507.01903/) (2025)
- [Evolving Deeper LLM Thinking](https://mlsanity.com/paper/2501.09891/) (2025)
- [Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows](https://mlsanity.com/paper/2512.16969/) (2025)
- [SciPIP: An LLM-based Scientific Paper Idea Proposer](https://mlsanity.com/paper/2410.23166/) (2024)
- [MedCare: Advancing Medical LLMs through Decoupling Clinical Alignment and Knowledge Aggregation](https://mlsanity.com/paper/2406.17484/) (2024)

## Built on by (most cited first, 3 of 3)

- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation](https://mlsanity.com/paper/2605.14790/) (2026)
- [Can LLM design high-quality experiments? A Comprehensive and Systematic Benchmark on Autonomous Experimental Design](https://mlsanity.com/paper/2608.03501/) (2026)

## Abstract (arXiv)

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.