Progressive Ideation using an Agentic AI Framework for Human-AI Co-Creation

2026-01-01

arXiv.org

AI Summary

This work addresses the challenge novice designers face in generating novel and diverse ideas in engineering design, as well as the limitations of existing “one-shot” AI systems that produce semantically clustered outputs. To overcome these issues, the authors propose MIDAS, a novel multi-agent collaborative framework that simulates human metacognitive creative processes. By integrating both global and local semantic novelty assessment mechanisms, MIDAS enables progressive idea evolution. The framework repositions designers from passive selectors to active co-creators, fostering deep human-AI collaboration. Experimental results demonstrate that MIDAS significantly enhances both the diversity and novelty of generated concepts, establishing a new paradigm for human-AI co-creation in engineering design.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Multiagent Systems: Mechanism Design

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The generation of truly novel and diverse ideas is important for contemporary engineering design, yet it remains a significant cognitive challenge for novice designers. Current'single-spurt'AI systems exacerbate this challenge by producing a high volume of semantically clustered ideas. We propose MIDAS (Meta-cognitive Ideation through Distributed Agentic AI System), a novel framework that replaces the single-AI paradigm with a distributed'team'of specialized AI agents designed to emulate the human meta-cognitive ideation workflow. This agentic system progressively refines ideas and assesses each one for both global novelty (against existing solutions) and local novelty (against previously generated ideas). MIDAS, therefore, demonstrates a viable and progressive paradigm for true human-AI co-creation, elevating the human designer from a passive filterer to a participatory, active, collaborative partner.

Problem

• novelty
• idea generation
• engineering design
• cognitive challenge
• AI co-creation

Innovation

• Agentic AI
• Human-AI Co-Creation
• Meta-cognitive Ideation
• Distributed AI Agents
• Progressive Ideation