الملخص
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%.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Cao, C., Zuo, L., Papakostas, K., Xu, Q., Xu, S., Zhou, L., Ren, Z., Lyu, Y., & Yan, X. (2026). SearchJev: A Fast and Calibrated System-1 Model for Search Agents. https://omanscience.com/ar/articles/searchjev-a-fast-and-calibrated-system-1-model-for-search-agents
MLA 9
Cao, Congfeng, et al. "SearchJev: A Fast and Calibrated System-1 Model for Search Agents." https://omanscience.com/ar/articles/searchjev-a-fast-and-calibrated-system-1-model-for-search-agents.
شيكاغو (المؤلف–التاريخ)
Cao, Congfeng, Lipeng Zuo, Konstantinos Papakostas, Qiwei Xu, Songwei Xu, Lun Zhou, Zhaochun Ren, Yougang Lyu, and Xiaohui Yan. 2026. "SearchJev: A Fast and Calibrated System-1 Model for Search Agents." https://omanscience.com/ar/articles/searchjev-a-fast-and-calibrated-system-1-model-for-search-agents.
هارفارد
Cao, C., Zuo, L., Papakostas, K., Xu, Q., Xu, S., Zhou, L., Ren, Z., Lyu, Y. and Yan, X. (2026) 'SearchJev: A Fast and Calibrated System-1 Model for Search Agents', Available at: https://omanscience.com/ar/articles/searchjev-a-fast-and-calibrated-system-1-model-for-search-agents.
فانكوفر
Cao C, Zuo L, Papakostas K, Xu Q, Xu S, Zhou L, et al. SearchJev: A Fast and Calibrated System-1 Model for Search Agents. https://omanscience.com/ar/articles/searchjev-a-fast-and-calibrated-system-1-model-for-search-agents
IEEE
C. Cao, L. Zuo, K. Papakostas, Q. Xu, S. Xu, L. Zhou, Z. Ren, Y. Lyu, and X. Yan, "SearchJev: A Fast and Calibrated System-1 Model for Search Agents," https://omanscience.com/ar/articles/searchjev-a-fast-and-calibrated-system-1-model-for-search-agents.