Credo：面向智能体工作流的可复用声明式原语

中文摘要 AI 辅助

大语言模型（LLM）应用依赖于模型和harness（框架）：harness是决定每次调用可见内容、调用次数以及可信答案的程序。当前编码智能体可通过搜索候选程序来发现高效harness，但生成的产物是不透明的命令式代码块，其逻辑步骤、运行时信号、物理执行决策和提示策略仍为隐式且任务特定，导致后续任务必须从头开始harness搜索过程，复用潜力巨大。搜索得到的harness蕴含重要知识，如有效的逻辑步骤、关键信号、适配执行的物理算子决策、有效的提示策略，但这些知识被埋没在无结构、不可检查、不可复用的命令式代码中，也无来源或元数据。Credo通过恢复搜索得到的harness的结构化声明式描述、为每个提取的原语标记相关元数据、并带来源编目所有内容来解决该问题。编译器随后可绑定存储的原语，为新任务生成harness，无需从头开始搜索。本文提供了初步结果以展示该方法的潜力，并提出了数据库界可胜任的相关研究议程，包括基于声明式编目的基于成本的编译、模型和工作负载漂移下的编目维护。

英文摘要

An LLM application depends on both a model and a harness: the program that determines what each call sees, how many calls to make, and which answers to trust. Coding agents can now discover strong harnesses by searching over candidate programs, but the resulting artifact is an opaque block of imperative code whose logical steps, runtime signals, physical execution decisions, and prompt strategies remain implicit and task-specific, forcing subsequent tasks to start the harness search process from scratch. The potential for reuse, however, is substantial. A searched harness encodes significant knowledge, such as the logical steps that work, the signals that matter, the physical operator decisions that adapt execution, and the prompt strategies that are effective, yet this knowledge is buried in imperative code with no inspectable or reusable structure, nor does it carry any provenance or metadata. Credo addresses this problem by recovering a structured declarative description of a searched harness, tagging each extracted primitive with relevant metadata, and cataloguing all of it with provenance. A compiler can then bind stored primitives to generate harnesses for new tasks without having to start the search over from scratch. This paper provides preliminary results demonstrating the potential of our approach and lays out a related research agenda that the database community is well-positioned to tackle, including cost-based compilation over declarative catalogs and catalog maintenance under model and workload drift.

发表机构

• Brown University（布朗大学）
• Northwestern University（西北大学）

机构由 AI 辅助整理，请以论文原文为准。