Reactions from ranked influencers
8 posts
3/5 CAD extracts functions from high-fitness programs, validates them, and adds them to a run-specific helper module. Later mutation and crossover calls can use the learned functions. Selected programs are refactored to call them only when behavior is preserved.
5/5 CAD turns program search into a process whose vocabulary changes during the run. Later programs inherit callable abstractions discovered from earlier high-fitness programs. Accepted at IEEE CoG 2026. With @Amidos2006 @togelius. Website: Paper:…
4/5 CAD raised mean final-best in all comparisons across Sokoban, Zelda, Lode Runner, and Dangerous Dave. The endpoint favored CAD whether search began with no helper library or a fixed hand-written expert API.
We got new cool stuff for ya. Especially if you're into PCG for games. Or genetic programming. Or agentic yada-yada, whatever it's called this month. What it is is an evolutionary loop that creates programs with LLM code writing, and abstracts a pool of reusable primitives.
🧵 1/5 What happens when a language model doesn't just write code, but dynamically creates its own expert API mid-run? Instead of evolving individual game levels, our new paper evolves entire generator programs using an LLM as the mutation and crossover operator.
🧵 1/5 What happens when a language model doesn't just write code, but dynamically creates its own expert API mid-run? Instead of evolving individual game levels, our new paper evolves entire generator programs using an LLM as the mutation and crossover operator.
3/5 CAD extracts functions from high-fitness programs, validates them, and adds them to a run-specific helper module. Later mutation and crossover calls can use the learned functions. Selected programs are refactored to call them only when behavior is preserved.