arXiv Machine Learning By Babak Rahmani, Sebastian Dziadzio, Joschka Str\"uber, Sergio Hern\'andez-Guti\'errez, Matthias Bethge

RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments

Read the original on arXiv Machine Learning →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

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?