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

aiqbench analysis

ENVAGENT demonstrates how multi-agent orchestration can automate the synthesis, building, and verification of Docker environments for scientific repositories, significantly outperforming standard language models in executability. By addressing the heterogeneity of software dependencies and build procedures, this framework reduces labor-intensive setup tasks that often bias AI evaluations in scientific computing. The accompanying ENVBENCH benchmark provides a rigorous rubric for assessing these automated environments across seven programming languages.
1
Source coveringarXiv

EnvAgent: Multi-Agent Approach to Building Science Environments in the Clouds

arXiv·November 19, 2026·2 min read

From arXiv

Full text

arXiv:2611.23258v1 Announce Type: cross Abstract: AI agents are transforming scientific computing and software workflows, but generating and executing code requires a correctly configured execution environment. Automating environment construction remains difficult because repositories encode heterogeneous, often incomplete requirements for operating systems, toolchains, dependencies, and build procedures. Existing workflows thus rely on developer-maintained Dockerfiles and setup scripts, making preparation labor-intensive, hard to scale, and potentially biasing evaluations. We present ENVAGENT, an agentic framework that synthesizes, builds, and verifies repository-level Docker environments.

ENVAGENT combines deterministic utilities for Docker execution and state management with coordinated agents for repository analysis, planning, Dockerfile synthesis, and iterative failure diagnosis and repair. We also introduce ENVBENCH, a benchmark of 54 scientific artifacts and open-source repositories spanning seven languages from Chameleon Trovi and Multi-SWE-bench. For each repository, we curate a declarative rubric of required structure, configuration, and functionality, and a shared evaluator applies 2,108 weighted checks across generated environments.

Across four matched language-model settings, ENVAGENT constructs 43.5 executable environments out of 54 on average, versus 23.5 for Codex and Claude Code, and scores 62.02 versus 24.19 on a composite of executability and rubric satisfaction. These results show that environment-specific agent orchestration substantially improves automated environment construction.

Abstract:AI agents are transforming scientific computing and software workflows, but generating and executing code requires a correctly configured execution environment. Automating environment construction remains difficult because repositories encode heterogeneous, often incomplete requirements for operating systems, toolchains, dependencies, and build procedures. Existing workflows thus rely on developer-maintained Dockerfiles and setup scripts, making preparation labor-intensive, hard to scale, and potentially biasing evaluations. We present ENVAGENT, an agentic framework that synthesizes, builds, and verifies repository-level Docker environments.

ENVAGENT combines deterministic utilities for Docker execution and state management with coordinated agents for repository analysis, planning, Dockerfile synthesis, and iterative failure diagnosis and repair. We also introduce ENVBENCH, a benchmark of 54 scientific artifacts and open-source repositories spanning seven languages from Chameleon Trovi and Multi-SWE-bench. For each repository, we curate a declarative rubric of required structure, configuration, and functionality, and a shared evaluator applies 2,108 weighted checks across generated environments.

Across four matched language-model settings, ENVAGENT constructs 43.5 executable environments out of 54 on average, versus 23.5 for Codex and Claude Code, and scores 62.02 versus 24.19 on a composite of executability and rubric satisfaction. These results show that environment-specific agent orchestration substantially improves automated environment construction.

12 pages, 3 figures. Accepted at AI4S@SC26 (SC26 Workshop)

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

I.2.2; I.2.11; D.2.9

arXiv:2611.23258 [cs.SE]

(or arXiv:2611.23258v1 [cs.SE] for this version)

https://doi.org/10.48550/arXiv.2611.23258 Focus to learn more arXiv-issued DOI via DataCite

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 · 299 words

Read at arXiv ↗Ask about this article

Related coverage

AI Research

Fig: Automated Multiagent Behavior Elicitor

arXiv · Oct 22, 2026

AI Research

Multi-agent rendezvous in fluid flows via reinforcement learning

arXiv · Jun 12, 2026

AI Products

Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation

arXiv · Jun 3, 2026

AI Research

Hybrid Optimization-Generative Motion Planning for Multiagent Affine Formations

arXiv · Nov 17, 2026

Article info

Source

arXiv

Published

November 19, 2026

Read time

2 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