Smart-TCP: An Agentic AI-based Autonomous and Adaptive TCP Protocol
Yule Han, Kezhi Wang, Kun Yang

TL;DR
Smart-TCP introduces an AI-driven, autonomous TCP protocol leveraging Large Language Models to enhance reliability and adaptability, demonstrating high success rates in static prediction and error detection.
Contribution
It presents a novel agentic AI-based architecture for TCP, integrating LLMs and tool use to improve protocol autonomy and performance.
Findings
Achieved 93.33% success rate in end-to-end sessions.
Demonstrated effectiveness in static prediction and error detection.
Validated the technical feasibility of agentic AI-based TCP.
Abstract
The Transmission Control Protocol (TCP) relies on a state machine and deterministic arithmetic to ensure reliable connections. However, traditional protocol logic driven by hard-coded state machines struggles to meet the demands of intelligent and autonomous network architectures. Here, we adopt the agentic AI-based paradigm, driven by Large Language Models (LLMs), characterized by context perception, autonomous reasoning, and tool use. Based on this, we propose Smart-TCP, which re-imagines TCP's core control logic as an autonomous agent. Specifically, the proposed architecture employs a context aggregation mechanism to synthesize the protocol context, utilizes the LLM for autonomous logical reasoning, and invokes an Arithmetic Logic Unit (ALU) as a tool for computation. Furthermore, we establish a dual-agent interaction framework based on this architecture and implement TCP protocol…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNetwork Traffic and Congestion Control · Software-Defined Networks and 5G · IoT and Edge/Fog Computing
