Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling

  • 类型：arxiv
  • 标识：2609.19499
  • 链接：https://arxiv.org/abs/2609.19499
  • 主分类：llm-infra
  • 形态：method
  • 被引：0
  • 被引来源：Semantic Scholar + OpenAlex
  • S2被引：0
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：The results show that candidate count alone is not enough to describe the systems cost of multi-candidate test-time scaling and Evaluations should report not only candidate count and accuracy, but also generation schedule and GPU-level systems metrics.
  • OpenAlex ID：W7213609415
  • OpenAlex DOI：10.48550/arxiv.2609.19499
  • DOI：10.48550/arxiv.2609.19499
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://doi.org/10.48550/arxiv.2609.19499
  • OpenAlex更新：2026-09-20
  • 待LLM分类：否
  • 标题中文：样本数量远远不够：候选生成策略决定 LLM 测试时扩展的能耗与性能
  • TLDR中文：结果表明，仅靠候选数量不足以刻画多候选 test-time scaling 的系统成本；评测应同时报告候选数量与准确率，以及生成调度和 GPU 层级的系统指标。
  • 来源文件：
  • /inbox/tom/_candidates/2026-09-19-agent-rag-longcontext-candidates.json
  • [OpenAlex backfill]
  • /inbox/tom/_candidates/2026-09-20-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-09-21-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-09-21-agent-memory-tool-use-candidates.json
  • [S2 enrich]