JobBench: Aligning Agent Work With Human Will
JobBench is a new benchmark for AI agents that evaluates them on workflows experts prioritize for delegation, aiming to empower humans rather than replace them based on GDP value.
Article intelligence
Key points
- Covers 130 agentic tasks across 35 occupations
- Averages 35.6 binary criteria per task
- Best model Claude Opus 4.7 scores only 45.9%
- Shifts focus from replacement to enhancement
Why it matters
This matters because covers 130 agentic tasks across 35 occupations.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.26329] JobBench: Aligning Agent Work With Human Will
[Submitted on 25 May 2026]
Title:JobBench: Aligning Agent Work With Human Will
View a PDF of the paper titled JobBench: Aligning Agent Work With Human Will, by Yuetai Li and 23 other authors
View PDF HTML (experimental)
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.
Subjects:
Artificial Intelligence (cs.AI)
Cite as: arXiv:2605.26329 [cs.AI]
(or arXiv:2605.26329v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2605.26329
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Yuetai Li [view email] [v1] Mon, 25 May 2026 21:07:02 UTC (3,425 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled JobBench: Aligning Agent Work With Human Will, by Yuetai Li and 23 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-05
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)