AutoWorldModel-Bench

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

05:39

2026-08-13

aiunderstanding.org

artificial-intelligence

AutoWorldModel-Bench Tests Whether Coding Agents Can Improve World Models

Researchers introduced AutoWorldModel-Bench, a closed-loop benchmark in which coding agents modify and evaluate a starter world model under a fixed compute budget, reporting that Codex-5.4 and Claude …

04:00

2026-08-13

arxiv.org

artificial-intelligence

AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research

Researchers introduced AutoWorldModel-Bench, a closed-loop benchmark for evaluating AI coding agents as autonomous researchers, spanning eight game environments with a unified structured-state represe…

// co-occurs with top 3 entities

Codex-5.4 2 Claude Opus 4.6 2 arXiv 1

// topics top 5 topics

artificial intelligence 2 ai research 2 ai agents 2 machine learning 2 ai tools 1