Hugging Face Papers ↗ · 2026-11-17
深度思考并不会带来更好的选择:推理努力提升了LLM购物代理的置信度而非正确率
媒体报道 Hugging Face Papers 原文语言:中文
在三个购物基准测试中,增加大语言模型购物代理的思考力度并未在统计上改善产品选择的质量,但显著提高了其报告的置信度。同时,大多数模型的校准表现较差且存在相关错误。
全文
Across three shopping benchmarks, increasing large language model shopping agents' thinking effort did not statistically improve product-choice quality but significantly raised reported confidence, and most models were poorly calibrated with correlated errors.
正文以来源语言显示。