{
  "id": 15215,
  "url": "https://arxiv.org/abs/2607.28573v1",
  "title": "Rethinking Inference-Time Scaling in Local Computer-Use Agents: Failure Modes and Compute Tradeoffs",
  "summary": "Deploying autonomous computer-use agents (CUAs) locally is increasingly important for privacy, cost efficiency, and practical usability, yet improving their performance under strict hardware constraints remains challenging. While recent studies show that inference-time scaling can improve frontier computer-use agents through additional computation during execution, its effectiveness for resource-constrained local models remains poorly understood. We present a systematic empirical study of infere",
  "authors": "Woongkyu Lee, Jungwook Choi",
  "category": "research",
  "topics": "privacy-surveillance,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-30T17:36:36.000Z",
  "fetched_at": "2026-07-31T05:10:57.675Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/15215",
  "original_url": "https://arxiv.org/abs/2607.28573v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}