资讯

CANDID: Candidate-Driven Intervention for Disciplined Execution in Local Computer-Use Agents

📅 2026-11-20 ⏱️ 约 5 分钟阅读 ✍️ AI导航编辑部 🔗 arxiv.org
CANDID: Candidate-Driven Intervention for Disciplined Execution in Local Computer-Use Agents
📝 内容摘要

Computer Science > Computation and Language [Submitted on 17 Nov 2026] Title:CANDID: Candidate-Driven Intervention

📌 核心要点

  • Computer Science > Computation and Language
  • [Submitted on 17 Nov 2026]
  • Bibliographic and Citation Tools

Computer Science > Computation and Language

[Submitted on 17 Nov 2026]

Title:CANDID: Candidate-Driven Intervention for Disciplined Execution in Local Computer-Use Agents

View PDF HTML (experimental)Abstract:We present CANDID (Candidate-Driven Intervention for Disciplined Execution), an execution-control framework designed to enhance the reliability of local computer-use agents (CUAs) in resource-constrained settings. While local CUAs feature robust baseline proficiency in single-step action prediction, they frequently fail at critical junctions due to rigid action loops or premature DONE decisions. Rather than imposing imprecise cognitive loads through textual reflection, CANDID repurposes parallel test-time scaling into a disciplined, execution-level intervention at sparse, failure-prone points. We introduce a loop-recovery mechanism to filter candidates away from repeated behaviors and a conservative, unanimous DONE gating policy that requires absolute consensus to terminate. Experiments on OSWorld demonstrate that CANDID's structural control significantly improves success rates, outperforming feedback-based alternatives with minimal execution overhead.

Additional Features

References & Citations

Loading...

Bibliographic and Citation Tools

Bibliographic Explorer (What is the Explorer?)

Connected Papers (What is Connected Papers?)

Litmaps (What is Litmaps?)

scite Smart Citations (What are Smart Citations?)

Code, Data and Media Associated with this Article

alphaXiv (What is alphaXiv?)

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub (What is DagsHub?)

Gotit.pub (What is GotitPub?)

Hugging Face (What is Huggingface?)

ScienceCast (What is ScienceCast?)

Demos

Recommenders and Search Tools

Influence Flower (What are Influence Flowers?)

CORE Recommender (What is CORE?)

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.

来源arxiv.org· 本文为编辑整理,仅供参考