[2512.04123] Measuring Agents in Production

Skip to main content

arXiv is now an independent nonprofit!<br>Learn more<br>&times;

Search arXiv

Press Enter to search &middot; Advanced search

-->

Computer Science > Computers and Society

arXiv:2512.04123 (cs)

[Submitted on 2 Dec 2025 (v1), last revised 4 Jun 2026 (this version, v4)]

Title:Measuring Agents in Production

Authors:Melissa Z. Pan, Negar Arabzadeh, Riccardo Cogo, Yuxuan Zhu, Alexander Xiong, Lakshya A Agrawal, Huanzhi Mao, Emma Shen, Sid Pallerla, Liana Patel, Shu Liu, Tianneng Shi, Xiaoyuan Liu, Jared Quincy Davis, Emmanuele Lacavalla, Alessandro Basile, Shuyi Yang, Paul Castro, Daniel Kang, Koushik Sen, Dawn Song, Joseph E. Gonzalez, Ion Stoica, Matei Zaharia, Marquita Ellis<br>View a PDF of the paper titled Measuring Agents in Production, by Melissa Z. Pan and 24 other authors

View PDF

Abstract:LLM-based agents already operate in production across many industries, yet we lack an understanding of what technical methods make deployments successful. We present the first systematic study of Measuring Agents in Production, MAP, using first-hand data from agent developers. We conducted 20 case studies via in-depth interviews and surveyed 86 deployed systems practitioners across 26 domains. We investigate why organizations build agents, how they build them, how they evaluate them, and their top development challenges. Our study finds that production agents are built using simple, controllable approaches: 68% execute at most 10 steps before human intervention, 70% rely on prompting off-the-shelf models instead of weight tuning, and 74% depend primarily on human evaluation. Reliability (consistent correct behavior over time) remains the top development challenge, which practitioners currently address through systems-level design. MAP documents the current state of production agents, providing the research community with visibility into deployment realities and underexplored research avenues.

Comments:<br>Accepted to the 43rd International Conference on Machine Learning (ICML 2026) as Oral Presentation

Subjects:

Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Software Engineering (cs.SE)

Cite as:<br>arXiv:2512.04123 [cs.CY]

(or<br>arXiv:2512.04123v4 [cs.CY] for this version)

https://doi.org/10.48550/arXiv.2512.04123

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Melissa Pan [view email]<br>[v1]<br>Tue, 2 Dec 2025 16:45:10 UTC (337 KB)

[v2]<br>Fri, 30 Jan 2026 22:21:00 UTC (345 KB)

[v3]<br>Tue, 3 Feb 2026 18:06:26 UTC (345 KB)

[v4]<br>Thu, 4 Jun 2026 19:57:38 UTC (340 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Measuring Agents in Production, by Melissa Z. Pan and 24 other authors<br>View PDF<br>TeX Source

view license

Current browse context:

cs.CY

next >

new<br>recent<br>| 2025-12

Change to browse by:

cs<br>cs.AI<br>cs.LG<br>cs.SE

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

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? |<br>Disable MathJax (What is MathJax?)

Major funding support from