VRL-Bench

What is VRL-Bench?

VRL-Bench is described as a harness for evaluating agents on computer control tasks under finite trial budgets, focused on trial-and-error learning.

Released

2026-09-11

Evaluates

General AI, Language & Knowledge, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

ai-name-audit-deferred

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.12404

VRL-Bench paper

• Paper https://arxiv.org/abs/2609.12404

Which sources cite VRL-Bench?

• VRL-Bench

Related General AI, Language & Knowledge, cs.AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench