DeciCAD: Harness-Grounded Learning of Action Policies for CAD Agents
From the abstract
Large Language Model agents operate through closed-loop action policies whose decision space is defined by an agent harness. We investigate how this operating space shapes agent behavior and policy learning in computer-aided design (CAD), a professional domain characterized by persistent state, geometric constraints, and long-horizon procedures.
From the abstract. Our summary is in progress.
The full text is not republished here because the paper's license does not allow it. Read the original on arXiv.