RSIGame: recursive self-improvement pushes Qwen-27B past GPT-5.5 one-shot at 11x fewer tokens
RSIGame · hf · 2026-10-01
RSIGame is an autonomous agentic game development framework with recursive self-improvement, addressing the overfitting that plagues naive iterative refinement.
A local explore-diagnose-improve loop explores the executable game and performs evidence-grounded fixes backed by an evolving checklist; a global loop tracks quality, keeps best checkpoints, and detects saturation or regression. Successful development experience is also internalized into the generator via training. Across 140 GameCraft-Bench tasks, two engines, and five generators, experience internalization lets Qwen3.8-27B reach 61.38 on Godot and 58.53 on Phaser, exceeding GPT-5.5 one-shot scores while cutting generation tokens 11x.
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16
- AI agent deletes 43,599 lines of OpenClaw test code in one PR — vincent_koc · 2026-11-16