{"ok":true,"article":{"slug":"autoworldmodel-bench-a-state-centric-benchmark-for-automated-world-model-researc-d7fbde8a","title":"AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research","url":"https://arxiv.org/abs/2608.11216","canonical":"https://www.aimode.news/article/autoworldmodel-bench-a-state-centric-benchmark-for-automated-world-model-researc-d7fbde8a","sourceName":"arXiv cs.AI","summary":"arXiv:2608.11216v1 Announce Type: new Abstract: World modeling is an unsettled field: architectures, training objectives, and state representations interact in complex ways, and no single recipe dominates across environments. This makes it an ideal testbed for AI coding agents acting as autonomous researchers--a setting in which the improvement direction is not specified in advance, unlike the engineering-to-spec tasks that dominate current agent benchmarks. We introduce AutoWorldModel-Bench, a closed-loop benchmark in which frontier coding agents autonomously improve a provided world-model starter under a fixed compute budget. The benchmark spans eight game environments under a unified structured-state representation--ground-truth entity state extracted from each game and consumed through a shared tensor format--which isolates dynamics modeling from perception and enables minutes-per-run iteration. Across 64 sessions, Codex-5.4 and Claude Opus 4.6 improve their starter on 63; in 91% of sessions the winning edit is a non-trivial research-style modification--a new objective, representation, rollout procedure, or architectural change--rather than a hyperparameter tweak. Our benchmark offers a setting in which frontier coding agents can be evaluated on open-ended research rather than engineering-to-spec problems.","category":"AI","image":null,"lang":"en","publishedAt":"2026-08-13T04:00:00+00:00","createdAt":"2026-08-13T04:00:14.554378+00:00"}}