Large language models (LLMs) have enabled powerful advances in natural language understanding and generation. Yet their application to complex, real-world scientific workflows remain limited by challenges in memory, planning, and tool integration. Here, we introduce SciBORG (Scientific Bespoke Artificial Intelligence Agents Optimized for Research Goals), a modular agentic framework that allows LLM-based agents to autonomously plan, reason, and achieve robust and reliable domain-specific task execution. Agents are constructed dynamically from source code documentation and augmented with finite-state automata (FSA) memory, enabling persistent state tracking and context-aware decision-making. This approach eliminates the need for manual prompt engineering and allows for robust, scalable deployment across diverse applications via maintaining context across extended workflows and to recover from tool or execution failures. We validate SciBORG through integration with both physical and virtual hardware, such as microwave synthesizers for executing user-specified reactions, with context-aware decision making and demonstrate its use in autonomous multi-step bioassay retrieval from the PubChem database utilizing multi-step planning, reasoning, agent-to-agent communication and coordination for execution of exploratory tasks. Systematic benchmarking shows that SciBORG agents achieve reliable execution, adaptive planning, and interpretable state transitions. Our results show that memory and state awareness are critical enablers of agentic planning and reliability, offering a generalizable foundation for deploying AI agents in complex environments.

At HPE Discover 2022, The Edge-to-Cloud-Conference, you'll find the best of edge, cloud, and everything in between – all in one place. The good news is that once again you can attend the event LIVE in Las Vegas, June 28-30, 2022. Or you can choose to participate virtually. From the latest insights in secure connectivity and hybrid cloud to AI and unified data analytics, HPE Discover 2022 is the best place to find the information you need to stay ahead of the trends and technologies that can rapidly move your business forward. We invite you to explore the full line-up of sessions on our content catalog.

The conference starts on Monday, April 12th and is virtual. "The sessions at NVIDIA'S GTC event are always illuminating. Kinetic Vision's two presentations will show how new AI-driven digital twin models are changing the foundations of retail operations and product development," said Jeremy Jarrett, Executive Vice President of Kinetic Vision. The first session is a deep dive into physics-informed neural networks (PINNs). This innovative technology is able to provide real-time simulation results within the design environment, and could even create'intelligent CAD' to guide the user towards the most functional design.

There are many reasons why you would want to leverage Watson Assistant to make your Einstein Bot "better". In a previous blog, I spoke to just some of the key reasons why you would need to do so. I will provide additional detail here but first, let's look at how you integrate Watson into your Einstein Bot. The obvious table stakes, you need a Watson Assistant service to integrate with Bots. If you don't already have one, you can get a free IBM Cloud account to deploy a Watson Assistant service, which you can do in about a minute, also for free.