CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL
Paper • 2609.39533 • Published • 19
Virtual Xposed
Xposed
AI & ML interests
None yet
Recent Activity
upvoted a paper about 11 hours ago
CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL upvoted a paper about 12 hours ago
Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark upvoted a paper 3 days ago
Multi-Agent Egocentric World Model with Fine-Grained Embodied InteractionOrganizations
None yet