Research domain
Agents & Tool Use
Generative Modeling227 benchmarks · 111 papersMathematical Problem Solving214 benchmarks · 152 papersTool Use138 benchmarks · 103 papersFunction Calling115 benchmarks · 88 papersWeb navigation76 benchmarks · 75 papersTool Calling75 benchmarks · 37 papersTask Planning71 benchmarks · 20 papersTool Retrieval54 benchmarks · 16 papersGUI Navigation52 benchmarks · 34 papersWorld Modeling43 benchmarks · 21 papersAgentic Search41 benchmarks · 14 papersTool selection31 benchmarks · 13 papersAgentic Reasoning30 benchmarks · 22 papersAgentic Tool-use29 benchmarks · 29 papersDeep search28 benchmarks · 14 papersAgentic Coding28 benchmarks · 18 papersZero-shot Coordination25 benchmarks · 7 papersPrompt Injection Attack24 benchmarks · 11 papersGeneral AI Assistant Tasks22 benchmarks · 30 papersAgentic Task22 benchmarks · 10 papershuman-robot task planning and allocation21 benchmarks · 2 papersComputer Use20 benchmarks · 14 papersTargeted Web Crawling18 benchmarks · 1 papersGUI Automation18 benchmarks · 12 papersAgent Task Completion17 benchmarks · 9 papersLTL Instruction Following17 benchmarks · 2 papersTask success17 benchmarks · 7 papersAgentic16 benchmarks · 8 papersAgentic Task Completion16 benchmarks · 10 papersFailure attribution16 benchmarks · 6 papersWeb Agent Navigation16 benchmarks · 12 papersAgent Task16 benchmarks · 18 papers