Cites: Harnesses for models (Lilian Weng, 2026)

12 citation edges inside this catalog. A title match is weaker evidence than an identifier match. Zero entries does not mean no citations on the web.

• Self-Refine: Iterative Refinement with Self-Feedback
  arxiv:2303.17651 · evidence: id
• Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
  arxiv:2309.16797 · evidence: id
• Automated Design of Agentic Systems
  arxiv:2408.08435 · evidence: id
• MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
  arxiv:2410.07095 · evidence: id
• Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
  arxiv:2505.22954 · evidence: id
• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
  arxiv:2507.19457 · evidence: id
• Learning to Discover at Test Time
  arxiv:2601.16175 · evidence: id
• Meta Context Engineering via Agentic Skill Evolution
  arxiv:2601.21557 · evidence: id
• Hyperagents
  arxiv:2603.19461 · evidence: id
• Meta-Harness: End-to-End Optimization of Model Harnesses
  arxiv:2603.28052 · evidence: id
• Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
  arxiv:2604.25850 · evidence: id
• ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
  url:sakana.ai/shinka-evolve · evidence: id