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 5 · SOTA2 Research
Back to Research
Research domain
Agents & Tool Use
Search tasks
Search
6 benchmarks · 2 papers
Agentic Capability
6 benchmarks · 1 papers
Web Agent Automation
6 benchmarks · 6 papers
Mathematical Word Problems
6 benchmarks · 1 papers
Multi-agent recommendation
6 benchmarks · 1 papers
Agent Classification
6 benchmarks · 4 papers
Text-based Game Playing
6 benchmarks · 8 papers
Terminal Task Execution
6 benchmarks · 1 papers
Deceptive Maze Navigation
6 benchmarks · 1 papers
Customer Support Interaction
6 benchmarks · 4 papers
Multi-turn Agent Interaction
6 benchmarks · 1 papers
Agentic Workflow Performance Prediction
5 benchmarks · 1 papers
Autonomous Agent Task Execution under Injection
5 benchmarks · 1 papers
Speech Function Calling
5 benchmarks · 3 papers
Multimodal Agent Task
5 benchmarks · 2 papers
Agent & Alignment
5 benchmarks · 1 papers
Workflow Reconstruction
5 benchmarks · 1 papers
Multi-agent Observation Sharing
5 benchmarks · 4 papers
Agentic Tasks
5 benchmarks · 5 papers
Long-context memory management
5 benchmarks · 7 papers
Multi-Turn Tool Calling
5 benchmarks · 1 papers
MTG Gameplay
5 benchmarks · 11 papers
Web agent tasks
5 benchmarks · 3 papers
Visual Tool-Use
5 benchmarks · 3 papers
Agent Reasoning
5 benchmarks · 2 papers
Multimodal Tool-use Reasoning
5 benchmarks · 2 papers
Search-based planning
5 benchmarks · 3 papers
Interactive Environment Task Completion
5 benchmarks · 1 papers
Text-based Task Completion
5 benchmarks · 2 papers
Multi-Agent Strategic Reasoning
5 benchmarks · 2 papers
Asynchronous planning
5 benchmarks · 1 papers
Tool-use Grasping
5 benchmarks · 2 papers
Multi-agent Debate
Page 5 of 49
Previous
Next