arXiv Machine Learning

RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments

arXiv:2606. 26094v1 Announce Type: new Abstract: For most of scientific history, researchers studying behavior could only infer hidden mechanisms from outward actions: an inverse problem that becomes more tractable when observation is augmented by targeted intervention.

Hugging Face Trending Papers
Jun 24

RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments

For most of scientific history, researchers studying behavior could only infer hidden mechanisms from outward actions: an inverse problem that becomes more tractable when observation is augmented by targeted intervention. We pose a computational analogue: given only behavioral traces of an agent in a game environment, can a learner reconstruct the underlying decision program as executable code, and how much does this reconstruction improve with the ability to design controlled experiments?

arXiv AI
Jul 29

PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environments

arXiv:2605. 30880v4 Announce Type: replace-cross Abstract: World models for interactive text agents must typically be learned from observation-action trajectories alone.

By Jiaxin Bai, Yue Guo, Yifei Dong, Jiaxuan Xiong, Tianshi Zheng, Yixia Li, Tianqing Fang, Yufei Li, Yisen Gao, Haoyu Huang, Zhongwei Xie, Hong Ting Tsang, Zihao Wang, Lihui Liu, Jeff Z. Pan, Yangqiu Song
arXiv AI
Aug 3

DungeonBench: A Benchmark for Rules-Rich Tactical Reasoning in Dungeons & Dragons Combat

arXiv:2607. 29577v1 Announce Type: new Abstract: Games and simulators make valuable benchmarks by turning decisions into measurable outcomes, but many current suites under-test rules-rich tactical reasoning: the ability to choose well when geometry, timing, resources, objectives, and rule interactions all matter at once.

By Ismayil Ismayilov, Atakan Kara, Kaan Oktay