NLP Group at University of Minnesota

@minnesotanlp

Datasets

The Amazing Agent Race (AAR): 1400 multi-step scavenger-hunt puzzles for evaluating LLM agents on tool use, web navigation, and arithmetic reasoning. Includes linear (800) and DAG (600) variants across 4 difficulty levels.

1,400 tasksZae Myung Kim

Tasks

minnesotanlp/aar-dag-easy-sample_003

1.0latestrev. 1

aar, tool-use, multi-step

Zae Myung Kim

minnesotanlp/aar-dag-easy-sample_004

1.0latestrev. 1

aar, tool-use, multi-step

Zae Myung Kim

minnesotanlp/aar-dag-easy-sample_011

1.0latestrev. 1

aar, tool-use, multi-step

Zae Myung Kim

minnesotanlp/aar-dag-easy-sample_013

1.0latestrev. 1

aar, tool-use, multi-step

Zae Myung Kim

minnesotanlp/aar-dag-easy-sample_018

1.0latestrev. 1

aar, tool-use, multi-step

Zae Myung Kim

minnesotanlp/aar-dag-easy-sample_019

1.0latestrev. 1

aar, tool-use, multi-step

Zae Myung Kim

See all tasks →