Participatory Evolution of Artificial Life Systems via Semantic Feedback
This work addresses the challenge of making AI-driven generative design more accessible and interactive for users, though it appears incremental as it builds on existing methods like CLIP and CMA-ES.
The paper tackles the problem of guiding artificial life evolution with natural language by introducing a semantic feedback framework, resulting in improved semantic alignment over manual tuning in user studies.
We present a semantic feedback framework that enables natural language to guide the evolution of artificial life systems. Integrating a prompt-to-parameter encoder, a CMA-ES optimizer, and CLIP-based evaluation, the system allows user intent to modulate both visual outcomes and underlying behavioral rules. Implemented in an interactive ecosystem simulation, the framework supports prompt refinement, multi-agent interaction, and emergent rule synthesis. User studies show improved semantic alignment over manual tuning and demonstrate the system's potential as a platform for participatory generative design and open-ended evolution.