Dr. Zero: Self-Evolving Search Agents without Training Data
arxiv:2601.07055
Agents, open-endedness, AGI · 2026-01-11
Complete cleaned Markdown · Source Markdown including bibliography
Read in parts
Contents
- Dr. Zero: Self-Evolving Search Agents without Training Data
- Abstract
- 1 Introduction
- 2 Related Work
- 2.1 Reinforcement Learning
- 2.2 Search-Augmented LLMs
- 2.3 Self-Evolving LLMs
- 3 Methodology
- 3.1 Setup
- 3.2 Proposer Training
- 3.3 Solver Training
- 3.4 The Self-Evolving Dr. Zero
- 4 Experiments
- 4.1 Experiment Settings
- 4.2 Experiment Results
- 5 Conclusion