# NVIDIA 提出将 AI 智能体构建为 Python 对象

- 来源：elvis (@omarsar0)
- 发布时间：2026-07-30 07:00
- AIHOT 分数：37
- AIHOT 链接：https://aihot.virxact.com/items/cms6prrgp0acrrohzd3f4gv0h
- 原文链接：https://x.com/omarsar0/status/2082602113558077599

## AI 摘要

NVIDIA 发布新研究，提出将 AI 智能体构建为 Python 对象，用方法、字段、文档字符串和类型注解统一替代提示词模板、工具模式、回调代码和工作流图。该方法将概率性与确定性行为的边界置于源代码中，使智能体行为可测试、可追踪、可重构。相关论文已在 arXiv 发布。

## 正文

Super interesting new work from NVIDIA.

（bookmark it）

They suggest building agents as Python objects.

Very cool idea and I think it could a lot with agent reliability.

More below：

Agent development today spreads across prompt templates， tool schemas， callback code， and workflow graphs. NOOA replaces all four with one abstraction.

An agent is a Python object. Its methods are the actions the model can take， its fields hold state， its docstrings are the prompts， and its type annotations act as contracts.

A method whose body is "…" gets completed at runtime by a validated LLM loop. A method with a normal body stays deterministic Python.

That single convention puts the boundary between probabilistic and deterministic behavior right in the source.

Agent behavior becomes testable， traceable， and refactorable with the same tools you already use on the rest of your codebase.

NVIDIA reports six model-facing ideas combined on one surface， including pass-by-reference over live objects and model-callable harness APIs for context and events， evaluated on SWE-bench Verified， Terminal-Bench 2.0， and ARC-AGI-3.

Paper： https://arxiv.org/abs/2607.20709

Learn to build effective AI agents in our academy： https://academy.dair.ai/