AI & ML
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness
arXiv cs.SE0 views
arXiv:2610.08621v1 Announce Type: cross Abstract: Recent game design agents have made substantial progress in generating playable games. However, program correctness does not ensure an enjoyable experience for players. We present Recursive Game Creator, an experience-oriented harness to advance agentic game development from rough game prototypes into entertaining games. Recursive Game Creator organizes recursive development around four components: Designer, Builder, Player, and Reviewer. The Designer translates user instructions and Reviewer's feedback into detailed plans. The Builder turns these plans into candidate games. The coding-native Player creates and executes reusable policies through programmatic interfaces to efficiently collect diverse gameplay trajectories, mitigating evaluation bias caused by slow GUI-based collection. The Reviewer uses carefully designed trajectory-based metrics to induce player preferences, integrating with visual evidence and explicit textual preferences to evaluate games against game-specific criteria. Finally, the Reviewer accepts the better version and provides improvement reviews for the next round, closing the recursive loop. Our method achieves state-of-the-art overall performance of 77.89 on GameCraft-Bench. On GameASG-Bench, it achieves a strict task success rate of 53.2%, a 34.1% improvement over the same-model baseline, and the highest mean runtime-check pass rate at 93.4% among compared methods. A user study shows longer playtime and higher ratings. Code is coming soon.
Source:https://arxiv.org/abs/2610.08621PreviousHow Much Evidence Should a Coding Agent's Self-Correction Carry? Adaptive Dirichlet Evidence for Self-DistillationNextParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic Coding
Related posts
The world has a new plan to save nature, but it still needs the money
0Ars Technica

Could data center backlash flip Florida?
0The Verge

Vivo’s first Pro Max phone proves its Ultra is still in a league of its own
0The Verge

Why Peacock is making a huge bet on YouTube
0The Verge
Ninja’s first-ever microwave just replaced two of my kitchen appliances at once
0TechCrunch
Marvell and Lumentum sign definitive 115 billion dollars all-stock merger to build an AI-connectivity leader
0dev.to