Benchmark
SteerBench-Work
What is SteerBench-Work?
SteerBench-Work evaluates agent steering decisions at action boundaries in workplace scenarios across seven domains, with 106 incident-anchored scenarios and…
- Released
- 2026-08-12
- Evaluates
- Agents, Biology & Drug Discovery, Finance, General AI, Language & Knowledge
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2608.12654
SteerBench-Work paper
No reported scores are on record for this benchmark yet.