arXiv subjects

Deven Panchal

Publications and source records attributed to Deven Panchal.

4 recordsLinked to original sources

arXiv2025

Simpliflow: A Lightweight Open-Source Framework for Rapid Creation and Deployment of Generative Agentic AI Workflows

Generative Agentic AI systems are emerging as a powerful paradigm for automating complex, multi-step tasks. However, many existing frameworks for building these systems introduce significant complexity, a steep learning curve, and substantial boilerplate code, hindering rapid prototyping and deployment. This paper introduces simpliflow, a lightweight, open-source Python framework designed to address these challenges. simpliflow enables the rapid development and orchestration of linear, deterministic agentic workflows through a declarative, JSON-based configuration. Its modular architecture decouples agent management, workflow execution, and post-processing, promoting ease of use and extensibility. By integrating with LiteLLM, it supports over 100 Large Language Models (LLMs) out-of-the-box. We present the architecture, operational flow, and core features of simpliflow, demonstrating its utility through diverse use cases ranging from software development simulation to real-time system interaction. A comparative analysis with prominent frameworks like LangChain and AutoGen highlights simpliflow's unique position as a tool optimized for simplicity, control, and speed in deterministic workflow environments.

cs.AI↗

arXiv2024

Enabling Software Defined Optical Networks

This paper gives an overview of Software Defined Optical Networks or SDONs and how they can be implemented. It traces the evolution of Optical networks upto GMPLS and traces the idea of SDN and builds upto OpenFlow. The paper explores the need for SDONs and explains what a SDON solution could look like, including the hardware. It also seeks to explain how OpenFlow could be used as a part of this solution to overcome the limitations of GMPLS.

cs.NI↗

arXiv2024

5G Cellular -- An Energy Efficiency Perspective

While the 5G technology of cellular communications promises great capacity and coverage to access information anywhere and anytime, it is feared to have huge power consumption. Significant research been has been directed towards solving this problem which exists both on the subscribers side as well as the operators side. There have been efforts like predicting traffic, modifying the physical layer etc. towards making the 5G technology more energy efficient. The aim of this study is to see the technology enablers for 5G from an energy efficiency perspective. Efforts will be made to point out specific areas in 5G cellular where improvements or modifications could make 5G cellular more energy efficient.

cs.NI↗

arXiv2024

Deployment of Microcells by integrating LTE-U with LTE

With increasing data requirements of users, cellular operators are finding new ways to fulfil these requirements. These attempts involve the practice of deploying Wi-Fi access points nearer to the user and backhauling it to the nearest eNB (in case of LTE and LTE-A). The paper studies LTE-U, an extension of LTE which works in the unlicensed spectrum, as a potential solution to this problem. It is based on the idea of densification. Network deployments incorporating LTE-U will be able to better cater to the growing data rate demand of voice and video, thus reducing the load on eNB. Further we explore the possibility of LTE-U as an alternative to Wi-Fi or co-existing with Wi-Fi deployments and issues revolving around this idea. We show that LTE-U deployment solves the problem of capacity in both cases.

cs.NI↗