BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//LANS Seminar - ECPv6.16.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:LANS Seminar
X-ORIGINAL-URL:https://wordpress.cels.anl.gov/lans-seminars
X-WR-CALDESC:Events for LANS Seminar
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20250309T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20251102T070000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20260308T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20261101T070000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20270314T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20271107T070000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20260611T143000
DTEND;TZID=America/Chicago:20260611T153000
DTSTAMP:20260610T212635
CREATED:20260608T145429Z
LAST-MODIFIED:20260608T200245Z
UID:4024-1781188200-1781191800@wordpress.cels.anl.gov
SUMMARY:LANS Seminar
DESCRIPTION:Seminar Title: Introducing AISAC: A General-Purpose AI Scientific Assistant for Research Environments \n  \nSpeaker: Chandrachur Bhattacharya\, Researche Scientist\, Transportation and Power Systems Division\, Argonne National Laboratory \n  \nDate: Thursday\, June 11\, 2026 \nTime: 2:30 PM-3:30 PM (Virtual) \nLocation: Hybrid\, Bldg. 240\, Conference Room 4301 \nHost: Pinaki Pal \n  \nDescription: Scientific AI is at an inflection point. Recent co-scientist systems have demonstrated that LLM agents can generate hypotheses\, synthesize literature\, and execute experiments — but these systems are built for demonstration\, not for sustained deployment inside scientific institutions. Real research environments impose requirements that go largely unaddressed: provenance and reproducibility of reasoning chains\, transparency and auditability of agent behavior\, safe and governed code and data execution\, and deployment within institutional constraints including vetted inference endpoints\, HPC infrastructure\, and federated authentication. AISAC (AI Scientific Assistant Core) is a production multi-agent framework developed at Argonne National Laboratory to address this gap. Rather than proposing new agent algorithms\, AISAC contributes a governed execution substrate — a reusable infrastructure stack on which many domain-adapted scientific co-scientists can be built and deployed without requiring domain scientists to become framework developers.This talk details the architecture and design principles behind AISAC. We describe its bounded driver/helper orchestration model\, which enforces strict role separation between planning and execution agents and applies hard limits on recursion depth\, delegation steps\, and tool rounds. We discuss context engineering as a first-class problem — dual-floor budget management\, non-destructive message trimming\, and RAG-aware escalation that preserves evidence fidelity rather than silently summarizing. We present AISAC’s layered persistence model spanning conversation memory\, semantic recall\, user preferences\, per-agent notes\, and post-run skill learning — enabling cumulative usefulness without fine-tuning. We cover the live observability and runtime steerability model that makes agent behavior inspectable\, replayable\, and interruptible. Finally\, we describe deployment across laptop\, HPC\, and air-gapped environments from a single codebase\, and interoperability with MCP partner agents\, skills\, and standard industry schemas. AISAC is currently in active use across six scientific domains at Argonne including combustion science\, materials research\, critical minerals\, and energy process safety. We close with lessons learned from production deployment and the path toward broader DOE adoption. \n  \n\nBio: Chandrachur Bhattacharya is a researcher in the Transportation and Power Systems Division at Argonne National Laboratory\, where his work sits at the intersection of computational fluid dynamics\, energy sciences\, and applied AI. With a background in combustion and fluid mechanics\, he has spent over a decade developing and applying machine learning and AI methods to energy science problems\, spanning surrogate modeling\, data-driven simulation\, and scientific workflow automation. His current focus is AI for science: building practical\, deployable AI infrastructure for scientific research\, developing AISAC (AI Scientific Assistant Core)\, a production multi-agent framework for deploying domain-adapted scientific co-scientists across real institutional workflows\, now in active use across six (and increasing) scientific domains at Argonne National Laboratory. \n  \n  \nPlease note that the meeting URL for this event can be seen on the cels-seminars website which requires an Argonne login.
URL:https://wordpress.cels.anl.gov/lans-seminars/event/lans-seminar-204/
LOCATION:https://wordpress.cels.anl.gov/cels-seminars/event/lans-seminar-219/
CATEGORIES:Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20260615T130000
DTEND;TZID=America/Chicago:20260615T140000
DTSTAMP:20260610T212635
CREATED:20260608T200228Z
LAST-MODIFIED:20260608T200228Z
UID:4028-1781528400-1781532000@wordpress.cels.anl.gov
SUMMARY:CS & LANS Seminar
DESCRIPTION:Seminar Title: From Workflows to AI Agents: The Evolution of Scientific Automation \n  \nSpeaker: Ewa Deelman\, Ph.D\, Research Professor\, University of Southern California (USC)\, Computer Science Department\, and Research Director\, USC Information Sciences Institute (ISI) \n  \nDate: Monday\, June 15\, 2026 \nTime: 1:00 PM-2:00 PM (In-Person) \nLocation: Hybrid\, Bldg. 240\, TCS Conference Room 1404 \nHost: Krishnan Raghavan \n  \nDescription: Scientific workflows have transformed the way researchers automate complex computations\, data management\, and large-scale analyses. Today\, advances in AI are extending automation beyond execution into workflow design\, operational decision-making\, and resource coordination. This talk traces that evolution through three generations of scientific automation: workflow automation with Pegasus\, AI-assisted workflow creation and management with PegasusAI\, and distributed agent-based infrastructure coordination in SWARM. Together\, these approaches illustrate a shift from automating tasks to enabling increasingly autonomous scientific systems capable of adapting to dynamic resources\, data\, and experimental needs. The talk concludes by considering how these capabilities may contribute to future autonomous scientific facilities and self-driving laboratories and identifies key cyberinfrastructure challenges and research opportunities along the way. \n  \n\nBio: Ewa Deelman\, Ph.D is a Research Professor at the University of Southern California (USC) Computer Science Department and a Research Director at the USC Information Sciences Institute (ISI).  At ISI\, she is leading the Science Automation Technologies Center. She is an AAAS\, IEEE\, and USC/ISI Fellow. The USC/ISI Science Automation Technologies Center explores the interplay between automation and the management of scientific workflows that include resource provisioning and data management\, considering reproducibility and open science. Dr. Deelman is also the Principal Investigator and Director of the NSF-funded Cyberinfrastructure Center of Excellence that serves the NSF Major and Midscale Facilities. Recently\, Dr. Deelman received the IEEE Sidney Fernbach Memorial Award for “pioneering research and software engineering in distributed systems in support of scientific workflows”. \n  \nPlease note that the meeting URL for this event can be seen on the cels-seminars website which requires an Argonne login.
URL:https://wordpress.cels.anl.gov/lans-seminars/event/cs-lans-seminar/
LOCATION:https://wordpress.cels.anl.gov/cels-seminars/event/cs-lans-seminar-2/
CATEGORIES:Seminar
END:VEVENT
END:VCALENDAR