TIR-Bench - a Agents-X Collection

Agents-X 's Collections

rl

TIR-Bench

updated 26 days ago

Agents-X/TIR-Bench

Viewer • Updated 26 days ago • 1.22k • 278 • 2
TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning

Paper • 2511.01833 • Published 27 days ago • 15