CORTEXA
← Browse
arxivcs.AIcs.OS2026-07-22

Defining AI-Native Systems: Autonomy as Revision Authority

Cheng Tan

AI has begun to write systems code: agents now synthesize, verify, and deploy system components. Despite this shift, "AI-native" remains a marketing term with no precise technical definition. This paper gives it one. We define AI-nativeness along a single axis---authority over the system's own decisions rather than by the capability of the underlying AI models. Building on a decision-level model of a system, we distinguish occupancy (who executes a decision) from revision authority (who may change it), organize revision authority into a ladder---self-tuning, self-rewriting, self-architecting and define a system as AI-native when an AI autonomously rewrites the system's own implementations. The definition further requires an escalation detector, a verification procedure, and a verified fallback, while leaving purpose and correctness human-owned.

View free PDFSource page

Related papers

arxivcs.SEcs.AIcs.OS2026-07-20

TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization

Alex Mathai, Shobini Iyer, Aleksandr Nogikh, Petros Maniatis, Franjo Ivancic, Junfeng Yang, et al.

Coding agents are increasingly used to accelerate code generation in many downstream tasks, such as fixing bugs, building applications, and prototyping. However, despite their value as coding assistants, agent-generated code tends to be larger and more verbose than the correspond…

View free PDFSource page
arxivcs.LGcs.AIcs.CLcs.OS2026-07-19

WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning

Ryan Xu, Atlas Zhao, David Bao, Frank Du

Long-horizon rollout generation has become the dominant systems bottleneck in agentic reinforcement learning (RL). As agents interact with environments over many turns, trajectories rapidly grow to tens of thousands of tokens, making synchronous RL training increasingly constrain…

View free PDFSource page
arxivcs.OScs.AIcs.PF2026-07-06

Elastic Gang: Per-Token Membership Change for a Hard-Barriered LLM Inference Gang Co-Scheduled with OS Processes

Daeyeon Son

On-device LLM decoding is a hard-barriered CPU-SIMD computation that wants every core for milliseconds per token, while the rest of the OS wants those same cores continuously. A barriered gang cannot simply be dropped into a preemptive scheduler: an unannounced departure deadlock…

View free PDFSource page