Self-Evolving Search Index
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
Learning to Coach for Experiential Learning
2
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
1
Discovery Foundation Models: Toward Open-Ended Discovery Intelligence
1
Can LLMs Engineer Their Own Agent Harness? ByteDance Seed’s HarnessDev Says Only 34 of 64 Changes Generalize
4 min1
Negative Self-Distillation: Learning to Reason by Avoiding Flaws
1
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
1
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience
