3 papers
cs.AI2026
Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation
Saroj Mishra
Multi-step agentic retrieval-augmented generation (RAG) pipelines have demonstrated significant capability for complex reasoning tasks, yet remain vulnerable to a class of failure…
cs.AI2026
SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
Saroj Mishra, Suman Niroula, Umesh Yadav +3
Retrieval-Augmented Generation (RAG) systems are increasingly evolving into agentic architectures where large language models autonomously coordinate multi-step reasoning, dynamic…
cs.CR2025
Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem
Shiva Gaire, Srijan Gyawali, Saroj Mishra +3
The Model Context Protocol (MCP) has emerged as the de facto standard for connecting Large Language Models (LLMs) to external data and tools, effectively functioning as the "USB-C…