PapersMulti-source78°

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

Why we picked it

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。

Body

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。

Original · 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.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Jac, LLM, agents, programming languages.

Source attribution: curated from arXiv cs.AI (@Jayanaka Dantanarayana, Savini Kashmira, Xiaoyu Ma, Malitha, Malitha Prabhashana, Lingjia Tang, Jason Mars). Cross-source corroboration: 11 independent sources have covered this development (including Aravind Srinivas, 掘金本周最热, IT之家), confirming industry-wide signal strength.

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