Paper Detail
Marjan Moodi, Xuankang Zhu, Fernando De Mesentier Silva, Harold Chaput, Mohammad Reza Taesiri
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{moodi2026autoworldmodel,
title = {AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research},
author = {Marjan Moodi and Xuankang Zhu and Fernando De Mesentier Silva and Harold Chaput and Mohammad Reza Taesiri},
year = {2026},
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 a},
url = {https://huggingface.co/papers/2608.11216},
keywords = {world modeling, structured-state representation, dynamics modeling, rollout procedure, architectural change, training objective, huggingface daily},
eprint = {2608.11216},
archiveprefix = {arXiv},
}
{}