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 12 · SOTA2 Research
Back to Research
Research domain
Agents & Tool Use
Search tasks
Search
3 benchmarks · 1 papers
Web GUI Task Automation
3 benchmarks · 1 papers
Next-Action
3 benchmarks · 1 papers
Head-to-Head Evaluation
3 benchmarks · 1 papers
Runtime Agent Memory
3 benchmarks · 4 papers
Multi-turn agent task
3 benchmarks · 1 papers
Agent Behavior Evaluation
3 benchmarks · 1 papers
Task Planning and Program Generation
3 benchmarks · 1 papers
Agent Verification
3 benchmarks · 1 papers
Video Scrubbing
3 benchmarks · 1 papers
Risk Scenario Generation
3 benchmarks · 2 papers
Agent Memory Retrieval
3 benchmarks · 2 papers
Terminal Agentic Trajectory Generation
3 benchmarks · 3 papers
Mobile GUI Task Execution
3 benchmarks · 1 papers
Task-free exploration
3 benchmarks · 1 papers
Proactive Agent Task
3 benchmarks · 2 papers
Long-term Planning
3 benchmarks · 1 papers
Agentic Oversight
3 benchmarks · 1 papers
Cross-factor predictive validity
3 benchmarks · 1 papers
Lifelong Agent Interaction
3 benchmarks · 3 papers
Downstream evaluation
3 benchmarks · 1 papers
Repeated Negotiation
3 benchmarks · 1 papers
Tool / Agent
3 benchmarks · 1 papers
Sequential Crafting
3 benchmarks · 1 papers
Agentic execution trace analysis
3 benchmarks · 4 papers
Trip Planning
3 benchmarks · 1 papers
Agent Trajectory Performance
3 benchmarks · 4 papers
Multi-hop tool use
3 benchmarks · 1 papers
Step-level tool invocation safety detection
3 benchmarks · 1 papers
Web Navigation Task Completion
3 benchmarks · 1 papers
Web-based task completion
3 benchmarks · 1 papers
Web-based Agent Reasoning
3 benchmarks · 1 papers
Monkey-banana task execution
Page 12 of 49
Previous
Next