BrowseComp-ZH

🧭 BrowseComp-ZH: Benchmarking the Web Browsing Ability of Large Language Models in Chinese BrowseComp-ZH is the first high-difficulty benchmark specifically designed to evaluate the real-world web browsing and reasoning capabilities of large language models (LLMs) in the Chinese information ecosystem. Inspired by Brow

Papers using BrowseComp-ZH (12)

SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research2026Scaling Agents via Continual Pre-training2025SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent2026Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window2025Mach-Mind-4-Flash Technical Report2026Tongyi DeepResearch Technical Report2026InfoSeeker: A Scalable Hierarchical Parallel Agent Framework for Web Information Seeking2026MiroFlow: Towards High-Performance and Robust Open-Source Agent Framework for General Deep Research Tasks2026WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning2026Yunque DeepResearch Technical Report2026MARINE: Theoretical Optimization and Design for Multi-Agent Recursive IN-context Enhancement2025Mirothinker: Pushing The Performance Boundaries Of Open-source Research Agents Via Model, Context, And Interactive Scaling2025