AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Meituan
AutoDesign recursively improves an agent's design workflow via a meta-harness optimizer that guides a code agent to refine a model-harness system based on feedback, tested on academic paper-to-poster generation.
Why it matters
Reports a top score of 78.32 on its poster-generation benchmark, beating the closed-source commercial system it calls Claude Design by 7.45 points, illustrating how harness-level optimization is becoming a competitive lever for agentic tasks.
Importance: 2/5
Notable paper: harness-level optimization beating a commercial baseline, official arXiv/HF source.
Sources
official
AutoDesign on HF Daily Papers