用搜索路径提升大模型智能体编程可靠性
EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths
- 提出概率天使非确定性模型，分离流程逻辑与推理策略
- 通过装饰器将代码编译为可搜索空间，支持快速策略切换
- 三案例验证：低代码实现更高可靠性与策略灵活调整
我们提出一种新型智能体编程方法，用于基于大语言模型的智能体开发。现有方法常将核心工作流逻辑与运行时策略（如树搜索）混杂在一起。本文引入“概率天使非确定性”（PAN）编程模型，将两者解耦，使程序员可独立描述工作流，并通过少量输入更改，自由实验不同推理策略。我们实现了Python版的EnCompass框架，利用装饰器将智能体工作流程序编译为搜索空间。三个案例展示该框架如何在极少额外编码下显著提升智能体可靠性，并轻松切换不同推理策略。
原文摘要 · Abstract (English)
We introduce a new approach to agent programming, the development of LLM-based agents. Current approaches to agent programming often entangle two aspects of agent design: the core workflow logic and the inference-time strategy (e.g., tree search). We introduce "probabilistic angelic nondeterminism" ("PAN"), a programming model that disentangles these two concerns, allowing the programmer to describe the agent workflow and independently experiment with different inference-time strategies by simply changing a few inputs. We provide an implementation of PAN in Python as the EnCompass framework, which uses a Python decorator to compile agent workflow programs into a search space. We present three case studies that demonstrate how the framework lets the programmer quickly improve the reliability of an agent and easily switch between different inference-time strategies, all with little additional coding.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。