Cites: AI Finds A Way

13 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.

• First return, then explore
  arxiv:2004.12919 · evidence: title
• Learning in High Dimension Always Amounts to Extrapolation
  arxiv:2110.09485 · evidence: id
• Mastering Diverse Domains through World Models
  arxiv:2301.04104 · evidence: id
• Progress measures for grokking via mechanistic interpretability
  arxiv:2301.05217 · evidence: title
• Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
  arxiv:2402.16822 · evidence: title
• The Llama 3 Herd of Models
  arxiv:2407.21783 · evidence: id
• Automated Design of Agentic Systems
  arxiv:2408.08435 · evidence: id
• Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
  arxiv:2505.22954 · evidence: id
• Hyperagents
  arxiv:2603.19461 · evidence: id
• Mathematical discoveries from program search with large language models
  doi:10.1038/s41586-023-06924-6 · evidence: id
• MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
  url:minedojo.org · evidence: title
• Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
  url:openai.com/research/weak-to-strong-generalization · evidence: id
• Reinforcement Learning from Human Feedback
  url:rlhfbook.com · evidence: url