Categories
Companies
Research
Sign in
Join
Loading the SOTA2 catalog…
WizWand is now SOTA2 Research
SOTA2
Research
Papers
Benchmarks
Datasets
Tasks
Agents & Tool Use AI research – Page 18 · SOTA2 Research
Back to Research
Research domain
Agents & Tool Use
Search tasks
Search
2 benchmarks · 1 papers
Steering Validation
2 benchmarks · 1 papers
Item Crafting and Interaction Tasks
2 benchmarks · 1 papers
device control
2 benchmarks · 1 papers
Enterprise interface interaction
2 benchmarks · 1 papers
Enterprise interface task completion
2 benchmarks · 1 papers
Knowledge-to-action question answering
2 benchmarks · 2 papers
Agent Routing
2 benchmarks · 1 papers
Subtasks
2 benchmarks · 1 papers
GUI Agent Automation
2 benchmarks · 1 papers
Agentic medical interaction
2 benchmarks · 5 papers
Mobile UI Control
2 benchmarks · 4 papers
Agentic Web Browsing
2 benchmarks · 1 papers
Regions of Interest Discovery
2 benchmarks · 1 papers
Tool-use agentic performance
2 benchmarks · 2 papers
Multi-turn tool-use interaction
2 benchmarks · 1 papers
Tool Selection Attack
2 benchmarks · 1 papers
Driving Hazard Explanation and Action Generation
2 benchmarks · 1 papers
Form-filling
2 benchmarks · 1 papers
Autonomous Task Completion
2 benchmarks · 1 papers
Visual Reasoning with Tool Use
2 benchmarks · 1 papers
Agent & OpenClaw
2 benchmarks · 2 papers
General Agent Capability
2 benchmarks · 2 papers
Multi-Agent Collaboration
2 benchmarks · 2 papers
Web Task
2 benchmarks · 1 papers
Agentic Affordance Reasoning
2 benchmarks · 1 papers
Multi-agent contract design approximation
2 benchmarks · 1 papers
Mobile Agent Interaction
2 benchmarks · 1 papers
Agent success prediction
2 benchmarks · 1 papers
Agent Planning and API Calling
2 benchmarks · 1 papers
Offline Constrained RLHF
2 benchmarks · 2 papers
GUI Agent Task Execution
2 benchmarks · 3 papers
Real-World Agent
Page 18 of 49
Previous
Next