LLM evolves generator programs: Using AI for code gen and reasoning in PCG
Amidos2006 · x · 2026-08-21
A project where LLMs are used not just to discover new level generators, but to reason about and abstract them to aid future generators. Instead of evolving individual levels, the paper evolves entire generator programs using an LLM as the mutation and crossover operator. To be presented at IEEE COG.
More from Research
- τ0-VLA: Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Search — sii-research · 2026-08-22
- ITSMBench Open Sourced: 50 Tasks for Multi-turn Agent Evaluation — Shahules786 · 2026-08-22
- Recursion releases Nesso: 10x faster binding affinity model for drug discovery — anshulkundaje · 2026-08-22
- Interview with Owain Evans explores emergent misalignment and LLM persona safety — sjgadler · 2026-08-22
- NVIDIA & Berkeley open source tactile robotics method T-Rex — DrJimFan · 2026-08-22
- Lightwheel and Hugging Face release 100k-hour human manipulation dataset — vanstriendaniel · 2026-08-22