[2604.01527] REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage

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 > Software Engineering

arXiv:2604.01527 (cs)

[Submitted on 2 Apr 2026 (v1), last revised 10 May 2026 (this version, v3)]

Title:REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage

Authors:Smriti Jha, Matteo Paltenghi, Chandra Maddila, Vijayaraghavan Murali, Shubham Ugare, Satish Chandra<br>View a PDF of the paper titled REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage, by Smriti Jha and 5 other authors

View PDF<br>HTML (experimental)

Abstract:Production deployment of AI coding agents requires fast, reproducible evaluation signals. Existing industrial practices trade off speed and fidelity: online A/B testing takes weeks and risks user experience, shadow deployment yields signals that are not reproducible across runs, and public benchmarks diverge from production workloads in language distribution, prompt style, and codebase structure. This paper presents REAP (Relevance and Execution-Audited Pipeline), an automated curation pipeline that constructs production-derived benchmarks from real developer-agent sessions without manual labeling. Such curation, while in-distribution to production usage, runs into several challenges. Untestable prompts, misaligned tests, and test flakiness all compromise evaluation reliability. While tasks can be manually audited to ensure only high-quality tasks remain in the benchmark, this approach is infeasible in the monorepo setting: the build infrastructure state is often ephemeral in large monorepos and requires the benchmark to be continuously re-curated against the current codebase. As manual verification cannot be sustained at this cadence, REAP adds an automated verification layer using LLM-based task classification, agentic test-relevance validation, and multi-run stability checks to ensure the executable benchmark yields trustworthy signals. We use REAP to curate Harvest, a benchmark where each task feeds the coding agent a real developer prompt and verifies the resulting code change against fail-to-pass tests retrieved from production. Harvest's distribution spans more than four programming languages with a majority of tasks drawn from Hack. Model and harness evaluations reveal that solve rates range from 42.9% to 58.2% across five frontier models, surfacing capability differences that inform concrete deployment decisions.

Subjects:

Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Cite as:<br>arXiv:2604.01527 [cs.SE]

(or<br>arXiv:2604.01527v3 [cs.SE] for this version)

https://doi.org/10.48550/arXiv.2604.01527

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Smriti Jha [view email]<br>[v1]<br>Thu, 2 Apr 2026 01:52:55 UTC (1,433 KB)

[v2]<br>Fri, 3 Apr 2026 07:18:13 UTC (1,495 KB)

[v3]<br>Sun, 10 May 2026 22:39:05 UTC (421 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage, by Smriti Jha and 5 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.SE

next >

new<br>recent<br>| 2026-04

Change to browse by:

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

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...