{
  "id": 17917,
  "url": "https://arxiv.org/abs/2608.07424v1",
  "title": "CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing",
  "summary": "Test-time scaling is often implemented by spending more compute along one axis: sampling more solutions, extending a chain of thought, or applying a stronger evaluator. Under a fixed inference budget, these choices compete. This paper formulates test-time reasoning as a compute-allocation problem in which a system must decide whether the next unit of compute should be spent on generation, verification, or stopping. We introduce CoBa, a compute-balanced routing policy that first obtains a small s",
  "authors": "Yan Zhou, Yue Ouyang, Kaiyang Zheng, Suncheng Xiang",
  "category": "research",
  "topics": "regulation",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-07T17:12:13.000Z",
  "fetched_at": "2026-08-10T05:10:00.488Z",
  "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/17917",
  "original_url": "https://arxiv.org/abs/2608.07424v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}