<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Posts on Moulik Dayal | Data Scientist &amp; AI Curriculum Engineer</title><link>https://dayalmoulik.github.io/posts/</link><description>Recent content in Posts on Moulik Dayal | Data Scientist &amp; AI Curriculum Engineer</description><generator>Hugo -- gohugo.io</generator><language>en</language><lastBuildDate>Mon, 06 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://dayalmoulik.github.io/posts/index.xml" rel="self" type="application/rss+xml"/><item><title>TRISEVA: Multi-Agent RAG System for Cross-Domain Document QA</title><link>https://dayalmoulik.github.io/posts/triseva-multi-agent-rag/</link><pubDate>Mon, 06 Jul 2026 00:00:00 +0000</pubDate><guid>https://dayalmoulik.github.io/posts/triseva-multi-agent-rag/</guid><description>&lt;h2 id="introduction"&gt;Introduction&lt;/h2&gt;
&lt;p&gt;In the current landscape of Large Language Models (LLMs), retrieving accurate information from domain-specific documents is a major challenge. Standard Retrieval-Augmented Generation (RAG) systems often fail when dealing with complex terminology and structured files across highly diverse sectors like Healthcare, Law, and Agriculture.&lt;/p&gt;
&lt;p&gt;To solve this, I designed &lt;strong&gt;TRISEVA&lt;/strong&gt; (a Multi-Agent Retrieval-Augmented System) as part of my M.Tech dissertation at BITS Pilani.&lt;/p&gt;
&lt;h2 id="architecture"&gt;Architecture&lt;/h2&gt;
&lt;p&gt;TRISEVA employs a modular multi-agent architecture where specialized agents collaborate to analyze, retrieve, and formulate explainable answers:&lt;/p&gt;</description></item></channel></rss>