The authors built a multi-agent meta-learning system that co-evolves two components: game-agnostic procedural search mechanisms written in C++, and domain-specific heuristics synthesized from each game's rules.
Language models discover search algorithms that transfer across games
A multi-agent system co-evolved general search procedures and game-specific heuristics, then tested them against established Monte Carlo tree search methods.
Big Tech
Zun Li · John Schultz · Marc Lanctot · Daniel Hennes
Google DeepMind
Research Digest··2 min read
Li and colleagues used large language models as code-generation engines to evolve modular game-playing algorithms under fixed compute budgets.
Why this paper
From Google DeepMind
In one line
A multi-agent LLM system discovers modular game-playing search algorithms that outperform most MCTS baselines across more than 400 games and transfer to unseen domains.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§