Back to Papers

FlexMind: Supporting deeper creative thinking with LLMs

Yaqing Yang

2025Computer science - human-computer interaction

Abstract

Effective ideation requires both broad exploration of diverse ideas and deep evaluation of their potential. Generative AI can support such processes, but current tools typically emphasize either generating many ideas or supporting in-depth consideration of a few, lacking support for both. Research also highlights risks of over-reliance on LLMs, including shallow exploration and negative creative outcomes. We present FlexMind, an AI-augmented system that scaffolds iterative exploration of ideas,

Relevance Assessment

Research Gap

Notes

Notes are automatically saved as you type

Tags

Creativity Frameworks › Logical CreativityCreativity Evaluation Methods › Human EvaluationModel Scale › Large (>32B)Creativity Evaluation Methods › Automatic MetricsProprietary Models › OpenAI ChatGPTResearch Focus › Prompt EngineeringCreativity Frameworks › Computational CreativityRelationship to Creativity › ImplicitHuman-In-The-Loop › Human–AI Co-Creation

Search Queries

Paper ID: 88916a75-1430-43d9-b21a-1568f6abbcfaAdded: 10/26/2025