Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Agents & Tool Use AI research – Page 21 · SOTA2 Research

Back to Research

Research domain

Agents & Tool Use

Search tasks

1 benchmarks · 1 papersMulti-turn Strategic Gameplay 1 benchmarks · 1 papersDiplomacy 1 benchmarks · 1 papersWeb Browsing Competition 1 benchmarks · 1 papersInteractive agent tasks 1 benchmarks · 1 papersTool-use AI Assistant 1 benchmarks · 1 papersTool-selection bias evaluation 1 benchmarks · 2 papersWeb Browsing Competition (Chinese)1 benchmarks · 1 papersAgent Generalization 1 benchmarks · 1 papersMulti-agent policy generation 1 benchmarks · 4 papersGUI Navigation and Action 1 benchmarks · 1 papersEnd-to-end terminal tasks 1 benchmarks · 1 papersAgentic Multimodal Tool-use

1 benchmarks · 4 papers

Task and Scenario Goal Completion

1 benchmarks · 1 papersCode Agent Simulation

1 benchmarks · 1 papersIndirect Prompt Injection Defense Evaluation

1 benchmarks · 1 papersSearch Agent Reasoning

1 benchmarks · 1 papersAPI Invocation Completion

1 benchmarks · 2 papersMultimodal Reasoning and Tool-use

1 benchmarks · 1 papersMandate Tool Invocation

1 benchmarks · 1 papersSole Planning

1 benchmarks · 1 papersIn-distribution Tool Use

1 benchmarks · 1 papersPlanning-style reasoning

1 benchmarks · 1 papersFinancial Specialist Tool Use

1 benchmarks · 1 papersSoftware Engineering Tool Use

1 benchmarks · 1 papersZero-Shot Generalist Tool Use

1 benchmarks · 1 papersAgent objective detection

1 benchmarks · 1 papersRoutine Task Management

1 benchmarks · 1 papersAgent Defense

1 benchmarks · 1 papersVisual Tool Reasoning

1 benchmarks · 1 papersPersonalized Assistant Interaction

1 benchmarks · 1 papersMobile Application Operation

1 benchmarks · 1 papersLanguage-based decision-making

Page 21 of 49