BrowseComp

BrowseComp is a benchmark used to evaluate the performance of models in managing context during multi-round interactions.

Papers using BrowseComp (6)

Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning2026SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward Gating2026OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories2026Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters2026A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning2025WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning2025