Peter Kulits
@peter-kulits · 1 works
Builds BrickBench, a benchmark for AI agents that generate LEGO sets from text descriptions.
Recent posts by Peter Kulits
- BrickBench: Evaluating Agentic Brick Design - We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design. Given a prompt, an agent is tasked with producing an assembly that not only satisfies semantic and design criteria,… · Paper · arxiv.org
Topics Peter Kulits posts about
- Agents on Instagram - 1 post · Best Agents creators