Distilling Game Code World Model Generation into Lightweight Large Language Models
TLDR
Distills game code world model generation into smaller LLMs via SFT and RLVR, improving syntactic correctness and rule adherence.
Reasoning
Strengths include a novel distillation pipeline combining SFT and RLVR with a verification framework, and a curated dataset of 30 games. Weaknesses are the limited scope (only one 3B model, 30 games) and lack of direct comparison to frontier models.
Read-first score
Read-first score 55.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 42.
Field roles
Rank sensitivity
Stability: volatile; rank range: 283.
Keyword Scores
Deep Analysis
Innovations
- Distillation of Game Code World Model generation capabilities into smaller LLMs through post-training
- Curated dataset of 30 games spanning perfect and imperfect information games
- Verification framework that evaluates generated code against structural and semantic game properties
- Post-training pipeline combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)
Methodology
The authors introduce a curated dataset of 30 games, a verification framework for structural and semantic properties, and a post-training pipeline that combines Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR). They experiment with the Qwen2.5-3B-Instruct model, evaluating syntactic correctness and execution-level adherence to game rules.
Key Results
SFT increases syntactic correctness, while RLVR improves execution-level adherence to game rules, making Qwen2.5-3B-Instruct more capable of generating valid Game Code World Models in both perfect and imperfect information games.