The paper proposes that reusable agent skills should incorporate visual elements alongside text, introduces three forms of visual skills and an automatic conversion system, and reports better performance on GUI and visual-centric tasks.
JobBench: Aligning Agent Work With Human Will
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Current benchmarks for occupational AI agents are scoped primarily by economic values, telling a replacement story. We introduce JobBench, which evaluates AI agents on the workflows that experts identify as high-priority for delegation, empowering humans based on their needs instead of replacing them with GDP value. JobBench covers 130 agentic tasks across 35 occupations. Each task is packaged as a workspace of heterogeneous reference files, requiring the agent to reason through the cluttered information streams of real professional work. Outputs are graded by a fact-anchored chain of rubrics, averaging 35.6 binary criteria per task. We evaluate 36 models; the strongest, Claude Opus~4.7 under Claude Code, reaches only 45.9 %. We hope JobBench shifts the community's target labour-market effect from replacement to enhancement: building agents that do what humans actually want delegated, not only what is most economically valuable.
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Agent Skills Should Go Beyond Text: The Case for Visual Skills
The paper proposes that reusable agent skills should incorporate visual elements alongside text, introduces three forms of visual skills and an automatic conversion system, and reports better performance on GUI and visual-centric tasks.