LANS Seminar
Seminar Title: Introducing AISAC: A General-Purpose AI Scientific Assistant for Research Environments
Speaker: Chandrachur Bhattacharya, Researche Scientist, Transportation and Power Systems Division, Argonne National Laboratory
Date: Thursday, June 11, 2026
Time: 2:30 PM-3:30 PM (Virtual)
Location: Hybrid, Bldg. 240, Conference Room 4301
Host: Pinaki Pal
Description: 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.
Bio: 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.
Please note that the meeting URL for this event can be seen on the cels-seminars website which requires an Argonne login.