SearchMaster: Grounded and Regulated Self-Play for Search Agents

arXiv:2608.01822 · cs.AI · Submitted 2026-08-03 · Read on arXiv

cs.AI

Submitted: 2026-08-03

Updated: 2026-10-12

Code: https://github.com/WentaoTan/SearchMaster

Terminology

• Accuracy — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• GRPO — 1× in this paper · explained in 6 episodes

Sources

• Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data
• gpt-oss-120b & gpt-oss-20b Model Card
• xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations
• REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• R-Zero: Self-Evolving Reasoning LLM from Zero Data
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning
• WebSailor: Navigating Super-human Reasoning for Web Agent
• OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
• DeepSeek-V3 Technical Report
• WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents
• Search Self-play: Pushing the Frontier of Agent Capability without Supervision
• DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL
• O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering
• WebGPT: Browser-assisted question-answering with human feedback
• BrowseMaster: Towards Scalable Web Browsing via Tool-Augmented Programmatic Agent Pair
• SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• OpenAI GPT-5 System Card

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems