arXiv subjects

Rajpreet Singh

Publications and source records attributed to Rajpreet Singh.

4 recordsLinked to original sources

arXiv2026

CSR-RAG: An Efficient Retrieval System for Text-to-SQL on the Enterprise Scale

Natural language to SQL translation (Text-to-SQL) is one of the long-standing problems that has recently benefited from advances in Large Language Models (LLMs). While most academic Text-to-SQL benchmarks request schema description as a part of natural language input, enterprise-scale applications often require table retrieval before SQL query generation. To address this need, we propose a novel hybrid Retrieval Augmented Generation (RAG) system consisting of contextual, structural, and relational retrieval (CSR-RAG) to achieve computationally efficient yet sufficiently accurate retrieval for enterprise-scale databases. Through extensive enterprise benchmarks, we demonstrate that CSR-RAG achieves up to 40% precision and over 80% recall while incurring a negligible average query generation latency of only 30ms on commodity data center hardware, which makes it appropriate for modern LLM-based enterprise-scale systems.

cs.CL↗

arXiv2025

Composable OS Kernel Architectures for Autonomous Intelligence

As intelligent systems permeate edge devices, cloud infrastructure, and embedded real-time environments, this research proposes a new OS kernel architecture for intelligent systems, transforming kernels from static resource managers to adaptive, AI-integrated platforms. Key contributions include: (1) treating Loadable Kernel Modules (LKMs) as AI-oriented computation units for fast sensory and cognitive processing in kernel space; (2) expanding the Linux kernel into an AI-native environment with built-in deep learning inference, floating-point acceleration, and real-time adaptive scheduling for efficient ML workloads; and (3) introducing a Neurosymbolic kernel design leveraging Category Theory and Homotopy Type Theory to unify symbolic reasoning and differentiable logic within OS internals. Together, these approaches enable operating systems to proactively anticipate and adapt to the cognitive needs of autonomous intelligent applications.

cs.OS↗

arXiv2025

Augmenting Von Neumann's Architecture for an Intelligent Future

This work presents a novel computer architecture that extends the Von Neumann model with a dedicated Reasoning Unit (RU) to enable native artificial general intelligence capabilities. The RU functions as a specialized co-processor that executes symbolic inference, multi-agent coordination, and hybrid symbolic-neural computation as fundamental architectural primitives. This hardware-embedded approach allows autonomous agents to perform goal-directed planning, dynamic knowledge manipulation, and introspective reasoning directly within the computational substrate at system scale. The architecture incorporates a reasoning-specific instruction set architecture, parallel symbolic processing pipelines, agent-aware kernel abstractions, and a unified memory hierarchy that seamlessly integrates cognitive and numerical workloads. Through systematic co-design across hardware, operating system, and agent runtime layers, this architecture establishes a computational foundation where reasoning, learning, and adaptation emerge as intrinsic execution properties rather than software abstractions, potentially enabling the development of general-purpose intelligent machines.

cs.AR↗

arXiv2025

A Ranking Framework for Network Resource Allocation and Scheduling via Hypergraphs

Resource allocation and scheduling are a common problem in various distributed systems. Although widely studied, the state-of-the-art solutions either do not scale or lack the expressive power to capture the most complex instances of the problem. To that end, we present a mathematical framework for hypergraph ranking and analysis, unifying graph theory, lattice theory, and semantic analysis. In our fundamental theorem, we prove the existence of partial order on entities of hypergraphs, extending traditional hypergraph analysis by introducing semantic operators that capture relationships between vertices and hyperedges. Within the boundaries of our framework, we introduce an algorithm to rank the node-hyperedge pairs with respect to the captured semantics. The strength of our approach lies in its applicability to complex ranking problems that can be modeled as hypergraphs, including network resource allocation, task scheduling, and table selection in Text-to-SQL. Through simulations, we demonstrate that our framework delivers nearly optimal problem solutions at a superior run time performance.

cs.DS↗