Cites: Self-Improvements in Modern Agentic Systems: A Survey

14 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: title
• Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
  arxiv:2309.16797 · evidence: title
• Metalearning Continual Learning Algorithms
  arxiv:2312.00276 · evidence: id
• Language Agents as Optimizable Graphs
  arxiv:2402.16823 · evidence: title
• Automated Design of Agentic Systems
  arxiv:2408.08435 · evidence: title
• LADDER: Self-Improving LLMs Through Recursive Problem Decomposition
  arxiv:2503.00735 · evidence: title
• TTRL: Test-Time Reinforcement Learning
  arxiv:2504.16084 · evidence: title
• Learning to Reason without External Rewards
  arxiv:2505.19590 · evidence: id
• Can Large Reasoning Models Self-Train?
  arxiv:2505.21444 · evidence: id
• Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
  arxiv:2505.22954 · evidence: title
• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
  arxiv:2507.19457 · evidence: title
• MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
  arxiv:2601.03192 · evidence: id
• Overcoming catastrophic forgetting in neural networks
  doi:10.1073/pnas.1611835114 · evidence: title
• ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
  url:sakana.ai/shinka-evolve · evidence: title