Metraipolis › archive › dc_9bd60d13e249
MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation — arXiv:2610.11966
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11966
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T05:46:54.785Z
- SHA-256 of the archived text
ca9b896002dfd0aae57a0d61dc03b89937b0232fd4055c06656183596527363a- Stable URL of this page
https://metraipolis.com/documento/dc_9bd60d13e249
How to cite
MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation — arXiv:2610.11966 — arXiv (en), https://arxiv.org/abs/2610.11966 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9bd60d13e249 (Metraipolis archive dc_9bd60d13e249, sha256 ca9b896002dfd0aae57a0d61dc03b89937b0232fd4055c06656183596527363a)
BibTeX
@misc{dc9bd60d13e249,
title = {MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation — arXiv:2610.11966},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11966},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9bd60d13e249; sha256 ca9b896002dfd0aae57a0d61dc03b89937b0232fd4055c06656183596527363a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11966. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Research idea innovation is a fundamental engine of scientific progress, yet it remains difficult to generate and evaluate in a scalable and controllable way. This challenge lies in its inherently open-ended and multi-objective nature, where ideas should balance novelty, plausibility and feasibility. While recent LLM-based approaches have made progress through carefully designed prompts or agent pipelines, they are constrained by predefined, static ideation workflows. To address this limitation, we propose MindFlow, a framework that explicitly formulates ideation as a graph-structured Flow in Mind, which is composed of modular thinking operators and modeled by a probabilistic mind supernet. Given a research topic, a controller dynamically samples thinking flows to generate candidate ideas. This open-ended problem is optimized using a tournament-based relative ranking, enabling the controller to progressively favor higher-quality thinking flows. We further introduce an evaluation protocol that jointly assesses problem finding and problem solving, going beyond title- or abstractonly judgments. Across diverse topics, MindFlow shows its superiority as an explicit, controllable and optimizable research idea innovator. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2610.11966 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T05:46:44.186Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).