NVIDIA-labs OO Agents: Native Python Object-Oriented Agents

• URL: http://arxiv.org/abs/2607.20709v1
• Date: Wed, 22 Jul 2026 20:25:55 GMT
• Title: NVIDIA-labs OO Agents: Native Python Object-Oriented Agents
• Abstract summary: We present NVIDIA Object-Oriented Agents (NOOA), a model-agnostic Python framework for building reliable AI agents.<n>NOOA takes a simpler approach: an agent is a Python object. Its methods are the actions the model can take, fields are its state, docstrings are its prompts, and its type annotations are contracts.
• Score: 8.777370925453148
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Traditional agent development is split across prompt templates, tool schemas, callback code, and workflow graphs. We present NVIDIA Object-Oriented Agents (NOOA), a model-agnostic Python framework for building reliable AI agents. NOOA takes a simpler approach: an agent is a Python object. Its methods are the actions the model can take, fields are its state, docstrings are its prompts, and its type annotations are contracts. A method whose code body consists of "..." is completed at runtime by an LLM-driven agent loop, while methods with normal bodies remain standard deterministic Python. This gives developers and agents the same interface, so agent behavior can be tested, traced, refactored, and improved just like other software. This paper makes three contributions. (1) We present the agent-as-a-Python-object programming model and the design principles behind it. Where Python has existing abstractions, we adopt them directly. Agent-specific capabilities--context, events, state rendering, long-term memory, and validated LLM loops--are exposed through simple Pythonic APIs, so both developers and agents share one familiar programming model. (2) We identify six model-facing ideas that NOOA is, to our knowledge, the first to combine on a single surface: typed input/output, pass-by-reference over live objects, code as action, programmable loop engineering, explicit object state, and model-callable harness APIs for context and events. We find the community already converging on several of these ideas--often as experimental or partial features--and present the comparison to encourage further adoption. (3) We demonstrate that current models use this interface effectively, both in targeted capability tests and on agentic and reasoning benchmarks such as SWE-bench Verified and Terminal-Bench 2.0 and ARC-AGI-3.

Related papers

• Prime Agent: A Self-Improving RLM Harness [5.540645425386541]
  Prime Agent is an open-source harness for long-horizon evaluation and coding-agent.<n>It standardizes execution, recovery, verification, and resource accounting while leaving strategy construction to the model.<n>Prime Agent raises ARC-AGI-3 RHAE Best@1 from 30% to 95.5% and matches or exceeds native and popular harnesses.
  arXiv  Detail & Related papers  (2026-08-24T17:54:19Z)
• Agents All the Way Down; A Methodology for Building Custom AI Agents from Substrate to Production [1.0499611180329804]
  No published practice sets out how to build one end to end.<n>This paper writes that practice down as a methodology, Agents All the Way Down.<n>It was distilled from the AAC, a custom agent for the open-source LAMB platform.
  arXiv  Detail & Related papers  (2026-06-10T09:44:54Z)
• Code as Agent Harness [107.31925305395957]
  In emerging agentic systems, code is no longer only a target output.<n>Code increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification.<n>This survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.
  arXiv  Detail & Related papers  (2026-05-18T17:59:03Z)
• AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse [14.413401094877122]
  Recent works on LLM-based agent self-evolution primarily record successful experiences as textual prompts or reflections.<n>We propose AgentFactory, a new self-evolution paradigm that preserves successful task solutions as executable subagent code.<n>Saved subagents are pure Python code with standardized documentation, enabling portability across any Python-capable system.
  arXiv  Detail & Related papers  (2026-03-18T17:58:25Z)
• Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback [51.22403664895878]
  Agent2World is a tool-augmented multi-agent framework that achieves strong inference-time world-model generation.<n>It also serves as a data engine for supervised fine-tuning, by grounding generation in multi-agent feedback.
  arXiv  Detail & Related papers  (2025-12-26T18:54:14Z)
• EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths [30.69327461098545]
  Current approaches to agent programming often entangle two aspects of agent design: the core workflow logic and the inference-time strategy.<n>We introduce "probabilistic angelic nondeterminism" ("PAN"), a programming model that disentangles these two concerns.<n>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.
  arXiv  Detail & Related papers  (2025-12-03T08:50:16Z)
• AgentGym: Evolving Large Language Model-based Agents across Diverse Environments [116.97648507802926]
  Large language models (LLMs) are considered a promising foundation to build such agents. We take the first step towards building generally-capable LLM-based agents with self-evolution ability. We propose AgentGym, a new framework featuring a variety of environments and tasks for broad, real-time, uni-format, and concurrent agent exploration.
  arXiv  Detail & Related papers  (2024-06-06T15:15:41Z)
• AgentKit: Structured LLM Reasoning with Dynamic Graphs [91.09525140733987]
  We propose an intuitive LLM prompting framework (AgentKit) for multifunctional agents. AgentKit offers a unified framework for explicitly constructing a complex "thought process" from simple natural language prompts.
  arXiv  Detail & Related papers  (2024-04-17T15:40:45Z)
• Executable Code Actions Elicit Better LLM Agents [76.95566120678787]
  This work proposes to use Python code to consolidate Large Language Model (LLM) agents' actions into a unified action space (CodeAct) integrated with a Python interpreter, CodeAct can execute code actions and dynamically revise prior actions or emit new actions upon new observations through multi-turn interactions. The encouraging performance of CodeAct motivates us to build an open-source LLM agent that interacts with environments by executing interpretable code and collaborates with users using natural language.
  arXiv  Detail & Related papers  (2024-02-01T21:38:58Z)
• pymdp: A Python library for active inference in discrete state spaces [52.85819390191516]
  pymdp is an open-source package for simulating active inference in Python. We provide the first open-source package for simulating active inference with POMDPs.
  arXiv  Detail & Related papers  (2022-01-11T12:18:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.