AI Paper Atlas

Research map / Large language models / Agents, code and math

MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation

Mengdi Liu, Wenjue Chen, Wenyue Chen, Cheng Yang, Fanqi Kong, Zhangyang Gao, Xiaoxue Cheng, Yiheng Li, Yujian Yuan, Keliang Li, Hong Chang, Shiguang Shan and 1 more

ICML 2026 · Large language models › Agents, code and math · approach: LLMs for scientific discovery

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add supernet controller instead of fixed Critical Thinking (ablation)MindFlow · IdeaBench (LLM-judged win rate)overall win rate: 0.336 -> 0.541Improved
add supernet controller instead of fixed Constraint-Driven Thinking (ablation)MindFlow · IdeaBench (LLM-judged win rate)overall win rate: 0.472 -> 0.541Improved
add supernet controller instead of fixed Counterfactual Thinking (ablation)MindFlow · IdeaBench (LLM-judged win rate)overall win rate: 0.426 -> 0.541Improved
add supernet controller instead of fixed Analogical Thinking (ablation)MindFlow · IdeaBench (LLM-judged win rate)overall win rate: 0.438 -> 0.541Improved
add supernet controller instead of fixed Divergent + Convergent Thinking (ablation)MindFlow · IdeaBench (LLM-judged win rate)overall win rate: 0.383 -> 0.541Improved
add supernet controller instead of fixed Counterfactual Thinking on problem finding novelty (ablation)MindFlow · IdeaBench (LLM-judged win rate)problem finding novelty: 0.901 -> 0.744Hurt
add supernet controller instead of fixed Critical Thinking on problem solving feasibility (ablation)MindFlow · IdeaBench (LLM-judged win rate)problem solving feasibility: 0.275 -> 0.257Mixed
use MindFlow instead of VIRSCI on problem solving feasibilityMindFlow · IdeaBench (LLM-judged win rate)problem solving feasibility: 0.109 -> 0.257Improved
use MindFlow instead of VIRSCI overall (LLM judged)MindFlow · IdeaBench (LLM-judged win rate)overall win rate: 0.470 -> 0.541Improved
use MindFlow instead of VIRSCI overall (human experts)MindFlow · IdeaBench (human expert, 50 queries)overall win rate: 0.475 -> 0.580Improved
use MindFlow instead of VIRSCI on Science domainMindFlow · IdeaBench Science domainoverall win rate: 0.473 -> 0.412Hurt
use MindFlow instead of VIRSCI on Robotics domainMindFlow · IdeaBench Robotics domainoverall win rate: 0.533 -> 0.694Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy