BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20261101T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260808T021739Z UID:8B88AF20-AAD3-4B61-A3DF-4B0BAD7E329D DTSTART;TZID=America/New_York:20260803T190000 DTEND;TZID=America/New_York:20260803T200000 DESCRIPTION:Special Presentation by Anirban Majumder\n\nHosted by the Exper t Tech Talks (IEEE Philadelphia Section)\n\nDate/Time: Monday\, 3 August 2 026 @ 7 PM Eastern Time\n\nTopic:\n\nFrom LLMs to Autonomous AI Agents: Bu ilding Enterprise-Ready Agentic Systems\n\nAbstract:\n\nThe rapid advancem ent of Large Language Models (LLMs) has fundamentally reshaped intelligent systems\, enabling natural language reasoning\, code generation\, and com plex decision support. More recently\, the emergence of agentic AI has shi fted the research focus from single-model interactions toward autonomous s ystems capable of planning\, memory management\, tool utilization\, multi- step reasoning\, and collaborative problem solving. While these capabiliti es demonstrate significant promise\, translating research prototypes into enterprise-scale deployments remains an open systems engineering and AI re search challenge. This talk presents a research-oriented perspective on th e design of enterprise-ready agentic systems. We examine the architectural foundations of autonomous AI agents\, including planning and reasoning st rategies\, Retrieval-Augmented Generation (RAG)\, structured and long-term memory\, tool invocation\, workflow orchestration\, and multi-agent colla boration. Particular emphasis is placed on emerging design patterns that e nable scalable\, modular\, and resilient agentic applications capable of o perating in dynamic\, high-risk environments. Beyond system architecture\, the presentation explores current research challenges in evaluating auton omous AI systems. Topics include benchmarking agent reasoning\, measuring task completion and robustness\, mitigating hallucinations\, ensuring expl ainability\, quantifying uncertainty\, and incorporating human oversight i nto autonomous decision-making. The discussion also covers safety\, govern ance\, observability\, and compliance considerations that are essential fo r deploying agentic AI in domains such as fraud detection\, cybersecurity\ , financial services\, healthcare\, and enterprise operations. Drawing fro m recent advances in generative AI and practical experience developing pro duction-scale AI systems\, the talk bridges the gap between cutting-edge r esearch and industrial deployment. It concludes by highlighting open resea rch opportunities in self-improving agents\, adaptive memory architectures \, agent communication protocols\, lifelong learning\, and trustworthy mul ti-agent ecosystems. Attendees will gain a comprehensive understanding of the scientific principles\, engineering trade-offs\, and research directio ns that will shape the next generation of autonomous enterprise AI systems .\n\nSpeaker:\n\n[Profile image]\n\nAnirban Majumder is an Applied Scienti st II at Amazon and an AI/ML leader with more than 20 years of experience designing and deploying machine learning systems at enterprise scale. His work spans generative AI\, large language models\, fraud detection\, risk modeling\, intelligent agents\, causal inference\, and production machine learning. Throughout his career at Amazon and leading technology consultin g organizations\, Anirban has led the development of AI solutions that hav e delivered tens of millions of dollars in measurable business impact. His recent work focuses on agentic AI systems\, LLM evaluation\, responsible AI\, safety benchmarking\, and scalable multi-agent workflows for enterpri se applications. Anirban is a Senior Member of IEEE\, Member of ACM and ha s authored multiple peer-reviewed publications in artificial intelligence\ , fraud detection\, AI agents\, and healthcare AI\, including research pub lications at ACM SIGKDD and EMNLP. He is also a co-inventor on granted pat ents spanning AI-driven materials science and digital health technologies. In addition to his research\, he serves as a technical reviewer for books and mentors scientists and engineers on production AI systems and respons ible deployment of generative AI. His interests include building trustwort hy autonomous AI systems that combine advanced reasoning capabilities with robust governance\, safety\, and measurable business outcomes.\n\nCo-spon sored by: IEEE Future Networks AI/ML Working Group\n\nSpeaker(s): Anirban\ n\nVirtual: https://events.vtools.ieee.org/m/569769 LOCATION:Virtual: https://events.vtools.ieee.org/m/569769 ORGANIZER:rachitjain4444@gmail.com SEQUENCE:27 SUMMARY:Expert Tech Talks - From LLMs to Autonomous AI Agents: Building Ent erprise-Ready Agentic Systems URL;VALUE=URI:https://events.vtools.ieee.org/m/569769 X-ALT-DESC:Description: <br /><p class="MsoNormal" style="margin-top: 12.0p t\;">Special Presentation by<strong> Anirban Majumder</strong></p>\n<p cla ss="MsoNormal" style="margin-top: 12.0pt\;">Hosted by the Expert Tech Talk s (IEEE Philadelphia Section)</p>\n<p class="MsoNormal" style="margin-top: 12.0pt\;"><strong><span style="font-size: 14.0pt\; font-family: Copperpla te\; mso-fareast-font-family: PMingLiU\; mso-fareast-theme-font: minor-far east\; mso-bidi-font-family: Arial\; mso-bidi-theme-font: minor-bidi\; mso -ansi-language: EN-US\; mso-fareast-language: ZH-TW\; mso-bidi-language: A R-SA\;">Date/Time</span></strong><span style="font-size: 12.0pt\; font-fam ily: 'Calibri'\,sans-serif\; mso-ascii-theme-font: minor-latin\; mso-farea st-font-family: PMingLiU\; mso-fareast-theme-font: minor-fareast\; mso-han si-theme-font: minor-latin\; mso-bidi-font-family: Arial\; mso-bidi-theme- font: minor-bidi\; mso-ansi-language: EN-US\; mso-fareast-language: ZH-TW\ ; mso-bidi-language: AR-SA\;">: <strong>Monday\, 3 August 2026</strong><st rong> @ 7 PM Eastern Time</strong></span></p>\n<p class="MsoNormal" style= "margin-top: 12.0pt\;"><span style="font-size: 12.0pt\; font-family: 'Cali bri'\,sans-serif\; mso-ascii-theme-font: minor-latin\; mso-fareast-font-fa mily: PMingLiU\; mso-fareast-theme-font: minor-fareast\; mso-hansi-theme-f ont: minor-latin\; mso-bidi-font-family: Arial\; mso-bidi-theme-font: mino r-bidi\; mso-ansi-language: EN-US\; mso-fareast-language: ZH-TW\; mso-bidi -language: AR-SA\;"><strong><img src="https://events.vtools.ieee.org/vtool s_ui/media/display/ae3f3e64-8a3c-4cb6-a3d7-37009d5b7996"></strong></span>< /p>\n<p class="MsoNormal" style="margin-top: .25in\;"><strong><u><span sty le="font-size: 16.0pt\; font-family: Copperplate\;">Topic</span></u></stro ng><strong><span style="font-size: 16.0pt\; font-family: Copperplate\;">:< /span></strong></p>\n<h3>From LLMs to Autonomous AI Agents: Building Enter prise-Ready Agentic Systems</h3>\n<p class="MsoNormal" style="margin-top: .25in\;"><strong><u><span style="font-size: 16.0pt\; font-family: Copperpl ate\;">Abstract</span></u></strong><strong><span style="font-size: 16.0pt\ ; font-family: Copperplate\;">:</span></strong></p>\n<p>The rapid advancem ent of Large Language Models (LLMs) has fundamentally reshaped intelligent systems\,&nbsp\;enabling natural language reasoning\, code generation\, a nd complex decision support. More recently\, the&nbsp\;emergence of agenti c AI has shifted the research focus from single-model interactions toward autonomous&nbsp\;systems capable of planning\, memory management\, tool ut ilization\, multi-step reasoning\, and collaborative&nbsp\;problem solving . While these capabilities demonstrate significant promise\, translating r esearch prototypes into&nbsp\;enterprise-scale deployments remains an open systems engineering and AI research challenge.&nbsp\;This talk presents a research-oriented perspective on the design of enterprise-ready agentic s ystems. We examine&nbsp\;the architectural foundations of autonomous AI ag ents\, including planning and reasoning strategies\, Retrieval-Augmented G eneration (RAG)\, structured and long-term memory\, tool invocation\, work flow orchestration\, and&nbsp\;multi-agent collaboration. Particular empha sis is placed on emerging design patterns that enable scalable\,&nbsp\;mod ular\, and resilient agentic applications capable of operating in dynamic\ , high-risk environments.&nbsp\;Beyond system architecture\, the presentat ion explores current research challenges in evaluating autonomous AI&nbsp\ ;systems. Topics include benchmarking agent reasoning\, measuring task com pletion and robustness\, mitigating&nbsp\;hallucinations\, ensuring explai nability\, quantifying uncertainty\, and incorporating human oversight int o autonomous&nbsp\;decision-making. The discussion also covers safety\, go vernance\, observability\, and compliance considerations that&nbsp\;are es sential for deploying agentic AI in domains such as fraud detection\, cybe rsecurity\, financial services\,&nbsp\;healthcare\, and enterprise operati ons.&nbsp\;Drawing from recent advances in generative AI and practical exp erience developing production-scale AI systems\,&nbsp\;the talk bridges th e gap between cutting-edge research and industrial deployment. It conclude s by highlighting&nbsp\;open research opportunities in self-improving agen ts\, adaptive memory architectures\, agent communication&nbsp\;protocols\, lifelong learning\, and trustworthy multi-agent ecosystems. Attendees wil l gain a comprehensive&nbsp\;understanding of the scientific principles\, engineering trade-offs\, and research directions that will shape the next& nbsp\;generation of autonomous enterprise AI systems.</p>\n<p><strong><spa n style="font-size: 16.0pt\; font-family: Copperplate\;"><u>Speaker</u>:</ span></strong></p>\n<table style="border-collapse: collapse\; width: 100%\ ; height: 383px\;" border="1"><colgroup><col style="width: 28.878049%\;">< col style="width: 71.02439%\;"></colgroup>\n<tbody>\n<tr style="height: 38 3px\;">\n<td style="height: 383px\;"><img class="_8a35839e _7f7490bf cde28 a1b _77540b0d b35977ea" src="https://media.licdn.com/dms/image/v2/D5603AQE ejKqXUKPyhQ/profile-displayphoto-shrink_800_800/profile-displayphoto-shrin k_800_800/0/1701663797173?e=1786579200&amp\;v=beta&amp\;t=XY3UKiCvLIuhIveG slCVoyLi1o_J14rzxa0duOhYe2w" alt="Profile image" width="224" height="224" data-loaded="true"></td>\n<td style="height: 383px\;">\n<p>&nbsp\;</p>\n<p >Anirban Majumder is an Applied Scientist II at Amazon and an AI/ML leader with more than 20 years of experience&nbsp\;designing and deploying machi ne learning systems at enterprise scale. His work spans generative AI\, la rge&nbsp\;language models\, fraud detection\, risk modeling\, intelligent agents\, causal inference\, and production machine&nbsp\;learning.&nbsp\;T hroughout his career at Amazon and leading technology consulting organizat ions\, Anirban has led the&nbsp\;development of AI solutions that have del ivered tens of millions of dollars in measurable business impact. His&nbsp \;recent work focuses on agentic AI systems\, LLM evaluation\, responsible AI\, safety benchmarking\, and scalable&nbsp\;multi-agent workflows for e nterprise applications.&nbsp\;Anirban is a Senior Member of IEEE\, Member of ACM and has authored multiple peer-reviewed publications in&nbsp\;artif icial intelligence\, fraud detection\, AI agents\, and healthcare AI\, inc luding research publications at ACM SIGKDD&nbsp\;and EMNLP. He is also a c o-inventor on granted patents spanning AI-driven materials science and dig ital health&nbsp\;technologies. In addition to his research\, he serves as a technical reviewer for books and mentors scientists and&nbsp\;engineers on production AI systems and responsible deployment of generative AI.&nbs p\;His interests include building trustworthy autonomous AI systems that c ombine advanced reasoning capabilities&nbsp\;with robust governance\, safe ty\, and measurable business outcomes.</p>\n<p>&nbsp\;</p>\n</td>\n</tr>\n </tbody>\n</table>\n<p>&nbsp\;</p> END:VEVENT END:VCALENDAR