Skip to content
Agents

hacktrace: behavior-supervised detection of reward hacking during code generation.

arXiv:2610.03055v1 Announce Type: new Abstract: A coding agent can earn a passing grade by fixing its code, or by deleting the test that exposes the bug. Detecting such reward hacking requires recognizing attempted shortcuts, including those that fail. We rele

arXiv cs.AIResearch source·