论文多源确认78°

Jac 语言提出 Agent-Native 编程范式,AI 集成代码量减少 1.8-8.7 倍

Agent-Native by Design: A Programming Language for Agentic Applications

精选理由

做智能体开发的朋友可以看看这篇。Jac 是个 Python 超集,把 LLM 调用、工作流和状态写进语言本身,比用 OpenAI SDK 拼 SDK 代码省 1.8-8.7 倍,还支持纯配置切换推测执行和服务分区。受够了 LangChain 胶水代码的话值得试一下。

一项发表于 arXiv 的研究提出 Agent-Native Programming,并在 Python 超集语言 Jac 中实现。与 OpenAI SDK 等五个基线相比,Jac 在五个基准测试上把 AI 集成代码量减少 1.8-8.7 倍,任务质量持平。

正文

核心机制是把 LLM 调用、工作流结构和应用状态统一到一套执行语义下:"by llm()" 负责带类型检查的模型操作和工具调用,Object-Spatial Programming 表达工作流结构与状态,"visit ... by llm()" 让模型从可执行的工作流步骤中选择并调度下一步。模型决策与程序执行显式关联后,编译器和运行时可以做依赖分析与自动优化。

两个案例研究演示了仅通过配置就能实现推测执行和服务分区,依靠程序分析和运行时检查来保持工作流行为不变。对被胶水代码拖累的智能体开发者,这是一条绕过 LangChain 类框架的新路线。

原文 · arXiv cs.AI

Agent-Native by Design: A Programming Language for Agentic Applications

Building agentic applications requires combining large language model (LLM) operations, workflow structure and application state, and model-guided routing. With SDKs and agent frameworks, developers connect these components through supporting code that prepares model inputs, propagates state, and dispatches model-selected steps. Workflow changes can require coordinated updates to this code, increasing development and testing effort. Splitting execution logic between application code and framework internals also limits compiler visibility into control flow and state dependencies, hindering automatic optimization. We introduce Agent-Native Programming, which unifies these three components with shared execution semantics. We realize this approach in Jac, a Python-superset language, through "by llm()" for typed model operations and tool use, Object-Spatial Programming for workflow structure and state, and "visit ... by llm()" for model-guided routing. The routing construct derives the model's choices from executable workflow steps and schedules the selected steps. This explicit connection between model decisions and program execution gives the compiler and runtime a common basis for dependency analysis and automatic optimization. Across five benchmarks and five baselines, Jac achieves a 1.8-8.7x reduction in AI-integration code relative to the OpenAI SDK, with competitive observed task quality and lower coding-agent development effort. Two case studies demonstrate speculative execution and service partitioning through configuration alone, using program analysis and runtime checks to preserve workflow behavior under stated conditions.

产业坐标与信源核验

本条情报归属 AITOP「论文」核心栏目,重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:Jac、LLM、智能体、编程语言,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Jayanaka Dantanarayana, Savini Kashmira, Xiaoyu Ma, Malitha, Malitha Prabhashana, Lingjia Tang, Jason Mars),经 AITOP 多维评分管线结构化提炼。截至目前,全网已有 11 家独立信源对该事件进行交叉印证与跟进报道(含 Aravind Srinivas、掘金本周最热、IT之家 等),属于近期高关注度行业信号。

  • Aravind Srinivas11-15 03:10原文
  • 掘金本周最热11-15 03:31原文
  • IT之家11-16 01:01原文
  • lmarena.ai11-16 02:21原文
  • 阿里通义 Qwen11-16 02:55原文
  • 阿里云 Alibaba Cloud11-16 03:21原文
  • marktechpost11-16 09:08原文
  • Perplexity11-16 15:32原文
  • Vercel AI11-16 18:31原文
  • Rest of World11-16 19:16原文