给AI装上“直觉”:搜索快5倍，还更准
大模型做搜索时，每判断一条链接要不要点、证据够不够，都要“想”一遍，慢且没把握。这篇把这类短决策从大模型里拆出来，交给一个专门的小模型——它不生成文字，直接给每个选项打分，像人的直觉反应。拿不准的才交给大模型慢慢想。结果：决策快5倍，搜索时间快近4倍，准确率还从45%涨到54%。这不是让你明天就能用的工具，但它指了个方向：AI不一定要事事深思熟虑，该快则快、该慢则慢，才是更聪明的做法。
📄 原文摘要(英文)
Search agents repeatedly make short decisions about relevance, evidence sufficiency, and search actions. Using generative language models for these decisions introduces latency and unreliable confidence. We present SearchJev, a fast and calibrated System-1 model that separates search decisions from System-2 reasoning and generation. Given a search state and a decision schema, SearchJev directly scores legal options without autoregressive output generation. We propose Soft-Label Learning for Calibrated Decisions (SLCD) to learn decision probabilities from uncertain supervision and calibrate their confidence. In a dual-system search agent, SearchJev handles short decisions and delegates uncertain judgments to System 2, which retains planning, query generation, and answer composition. We also introduce SearchDecision-Bench, a benchmark unifying six types of search decisions for training and evaluation. On SearchDecision-Bench, SEARCHJEV improves decision quality over same-size Qwen3.5 autoregressive models, achieves 5.2-5.3 times faster decisions, and reduces average expected calibration error by 41-74%. On BrowseComp-Plus, the dual-system agents achieve a 3.7-4.7 times speedup in active search time while improving answer accuracy from 45% to up to 54%.