NVIDIA-labs OO Agents: Native Python Object-Oriented Agents
NVIDIA
The paper proposes representing LLM agents as ordinary Python objects: methods are actions, fields are state, docstrings are prompts, and type annotations are contracts, with stub methods completed by an LLM at runtime while normal methods run as regular code. The framework is evaluated on SWE-bench Verified, Terminal-Bench 2.0, and ARC-AGI-3.
Why it matters
Proposes a lightweight, code-native abstraction for building agents that blends deterministic and LLM-driven logic in the same object, an alternative to prompt-template or graph-based agent frameworks.
Importance: 2/5
Notable agent-framework paper; below the 100-upvote HF Daily bump threshold.