AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a model-harness system. While an ideal harness system should align with human design priors and accumulate reusable experience through empirical exploration to drive recursive self-improvement, existing paradigms remain static and fall short of this capability. In this paper, we present AutoDesign, a framework that aligns with human design priors, where a meta-harness optimizer guides a code agent to recursively improve harness based on r
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 60%Pluggable by design: An agent mesh for software modernization that adopts the next model release →
- FuzzySimilar title/name (fuzzy) · 87%strands-agents/harness-sdk →
“Fuzzy title match (0.94): “AutoDesign: Meta-Harness Optimization for Long-Horizon Agent” ≈ “strands-agents/harness-sdk””
- FuzzySimilar title/name (fuzzy) · 84%Thysrael/Horizon →
“Fuzzy title match (0.92): “AutoDesign: Meta-Harness Optimization for Long-Horizon Agent” ≈ “Thysrael/Horizon””
- FuzzyOverlapping authors or contributors · 62%affaan-m/ECC →
“Shared author/contributor keys: jiang”
- FuzzyOverlapping authors or contributors · 62%pytorch/pytorch →
“Shared author/contributor keys: zou”
- FuzzyOverlapping authors or contributors · 62%BerriAI/litellm →
“Shared author/contributor keys: jiang”
- LinkedLinked via arxiv author · 85%Yaxin Luo →
“AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design”
- LinkedLinked via arxiv author · 85%Haobin Jiang →
“AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design”