cs.CLNov 17, 2026

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

Authors: Woongkyu Lee, Jungwook Choi

Organizations: Hanyang University

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.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. LocalLSTC: A Long Short-Term Control Architecture for Locally Deployed GUI Agents

    Aug 26, 2026Weiming Li, Helen Paik, Yulei SuiGUI AgentsLLM Agent Planning

  2. Know When to Escalate: Critic-Guided Adaptive Execution for Cloud-Local Embodied Agents

    Oct 22, 2026Wei Zhang, Lirong Xiang, Charles FlemingEmbodied AIAdaptive Model Routing