Skip to content
aiqbenchAI & Quantum Intelligence
NewsInsightsBenchmarksSkillsAsk AILearnAbout
...Loading your session
NewsInsightsBenchmarksSkillsAsk AILearnAbout
Back to list
aiqbench takeAI Research

aiqbench analysis

Composing insight from the full article — this may take a moment.

1
Source coveringarXiv

SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations

arXiv·November 17, 2026·3 min read

From arXiv

Full text

arXiv:2611.20218v1 Announce Type: cross Abstract: A coding agent working within a software organization must establish what to build, collaborate with colleagues, and verify what it delivers. We introduce SWE-CoWork, a benchmark comprising 101 development assignments across 101 real repositories, 11 programming languages, and 12 application domains. Each assignment places an agent in a simulated engineering organization with 26 colleagues who have distinct responsibilities, bounded knowledge, and controlled collaboration behavior. Starting from a brief handoff, agents must recover requirements distributed across colleagues and workplace records, reconcile conflicting evidence, and implement changes evaluated by private executable tests.

We evaluate eleven models and find a substantial gap between partial implementation and complete task delivery. The two leading models satisfy approximately 63% of fail-to-pass (F2P) tests but complete fewer than 8% of assignments. Providing complete requirements upfront improves F2P by approximately 16 percentage points for Seed Evolving and GPT-6 Astra, yet leaves complete task success unchanged. Requirement-level trajectory analysis reveals failures throughout the delivery process: Claude-Opus-5.5 directs a mean of 93% of first questions about queried cards to their accountable owners across runs but obtains only 64% of colleague-held requirements.

Deferred questions go unfollowed, implementations remain incomplete even after requirements are acquired, and 31% of requirements reported as completed fail their tests. These findings highlight sustained requirement tracking, from clarification through implementation, verification, and handoff, as a key challenge for reliable autonomous software engineering.

Abstract:A coding agent working within a software organization must establish what to build, collaborate with colleagues, and verify what it delivers. We introduce SWE-CoWork, a benchmark comprising 101 development assignments across 101 real repositories, 11 programming languages, and 12 application domains. Each assignment places an agent in a simulated engineering organization with 26 colleagues who have distinct responsibilities, bounded knowledge, and controlled collaboration behavior. Starting from a brief handoff, agents must recover requirements distributed across colleagues and workplace records, reconcile conflicting evidence, and implement changes evaluated by private executable tests.

We evaluate eleven models and find a substantial gap between partial implementation and complete task delivery. The two leading models satisfy approximately 63% of fail-to-pass (F2P) tests but complete fewer than 8% of assignments. Providing complete requirements upfront improves F2P by approximately 16 percentage points for Seed Evolving and GPT-6 Astra, yet leaves complete task success unchanged. Requirement-level trajectory analysis reveals failures throughout the delivery process: Claude-Opus-5.5 directs a mean of 93% of first questions about queried cards to their accountable owners across runs but obtains only 64% of colleague-held requirements.

Deferred questions go unfollowed, implementations remain incomplete even after requirements are acquired, and 31% of requirements reported as completed fail their tests. These findings highlight sustained requirement tracking, from clarification through implementation, verification, and handoff, as a key challenge for reliable autonomous software engineering.

Software Engineering (cs.SE); Artificial Intelligence (cs.AI)

arXiv:2611.20218 [cs.SE]

(or arXiv:2611.20218v1 [cs.SE] for this version)

https://doi.org/10.48550/arXiv.2611.20218 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

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.

Full text under the publisher's open licence · 322 words

Read at arXiv ↗Ask about this article

Related coverage

Machine Learning

Benchmarking Literature Retrieval for a Model Organism: A Dictyostelium Case Study

arXiv · Oct 5, 2026

AI Research

Self-Organizing Agent Teams Learn to Reason Together

arXiv · Sep 22, 2026

AI Safety

The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology

LessWrong · Jul 23, 2026

Machine Learning

BrainWideBench: Benchmarking large-scale pretraining and across-animal transfer in multi-region neural recordings

arXiv · Sep 21, 2026

Article info

Source

arXiv

Published

November 17, 2026

Read time

3 min

Category

AI Research
aiqbench
AI & Quantum Intelligence© aiqbench. All rights reserved.

Feeds:RSS·JSON Feed

LanguageEnglish·Românăbeta
NewsAI & TechQuantumInsights
ExploreBenchmarksLearn
CompanyAboutTrustLegal noticeTerms of ServicePrivacy PolicyCopyright noticesData erasureReport content

The aiqbench take, the insights, the daily digest and Ask answers are written by AI models from the sources shown, without editorial review before publication. They may contain errors — check the source. How the model is used →

  • News
  • Insights
  • Ask AI
  • Benchmarks
  • Account