Traverse Benchmark

What is Traverse?

Benchmark of human-verified annotations for locating hidden failures in long-horizon agent trajectories. Benchmark Radar tracks Traverse, cited by 1 source…

Released

2026-09-15

Evaluates

Language & Knowledge, Software & AI Compute, cs.LG

Openness

unknown

Importer

Claire Radar

Review status

ai-name-audit-deferred

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.17930

Traverse paper

• Paper https://arxiv.org/abs/2609.17930

Which sources cite Traverse?

• Traverse

Related Language & Knowledge, Software & AI Compute, cs.LG benchmarks

• 2d-fet-bench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• AARRI-Bench
• ABC-Bench
• Active-SWE
• ActiveSciBench
• AdaMem-Bench