الملخص
Most methods that optimize LLM prompts and agent workflows assume that task-specific output schemas, extraction instructions, and evaluation criteria are predefined. For scientific extraction agents, however, a short task goal may not fully determine these components, while specifying them manually is costly. We study the upstream problem of constructing the task-specific configuration from a weak specification containing only a short goal and unannotated reference documents. Rather than treating automatic construction as a fixed preprocessing step, our framework constructs a task-specific schema, extraction instructions, and base training rubrics, then keeps schema construction and extraction instructions editable during optimization. Failure-focused updates concentrate textual-gradient feedback on lower-scoring documents, while training-time evaluation criteria adapt to recurring failures. On a heterogeneous-catalysis literature corpus, automatic construction remains improvable, and optimizing both schema construction and extraction instructions performs best across all four judge-rubric settings, with ablations and blinded human evaluation supporting the proposed formulation.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Dong, Z., Yang, W., Liu, Z., Li, C., Liu, L., Tan, T., & Xie, H. (2026). From Weak Task Specifications to Scientific Extraction Agents: Optimizing Task Construction. https://omanscience.com/ar/articles/from-weak-task-specifications-to-scientific-extraction-agents-optimizing-task-construction
MLA 9
Dong, Zixiao, et al. "From Weak Task Specifications to Scientific Extraction Agents: Optimizing Task Construction." https://omanscience.com/ar/articles/from-weak-task-specifications-to-scientific-extraction-agents-optimizing-task-construction.
شيكاغو (المؤلف–التاريخ)
Dong, Zixiao, Wei Yang, Zihao Liu, Chenshu Li, Longzhang Liu, Tao Tan, and Hong Xie. 2026. "From Weak Task Specifications to Scientific Extraction Agents: Optimizing Task Construction." https://omanscience.com/ar/articles/from-weak-task-specifications-to-scientific-extraction-agents-optimizing-task-construction.
هارفارد
Dong, Z., Yang, W., Liu, Z., Li, C., Liu, L., Tan, T. and Xie, H. (2026) 'From Weak Task Specifications to Scientific Extraction Agents: Optimizing Task Construction', Available at: https://omanscience.com/ar/articles/from-weak-task-specifications-to-scientific-extraction-agents-optimizing-task-construction.
فانكوفر
Dong Z, Yang W, Liu Z, Li C, Liu L, Tan T, et al. From Weak Task Specifications to Scientific Extraction Agents: Optimizing Task Construction. https://omanscience.com/ar/articles/from-weak-task-specifications-to-scientific-extraction-agents-optimizing-task-construction
IEEE
Z. Dong, W. Yang, Z. Liu, C. Li, L. Liu, T. Tan, and H. Xie, "From Weak Task Specifications to Scientific Extraction Agents: Optimizing Task Construction," https://omanscience.com/ar/articles/from-weak-task-specifications-to-scientific-extraction-agents-optimizing-task-construction.