Categories: AI/ML Research

Stateful vs. Stateless Agent Design: Tradeoffs for Scalable Agentic Systems

In this article, you will learn how an agent’s approach to managing state — stateless or stateful — shapes both its implementation and the deployment…

ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Recent large language models (LLMs) advancements sparked a growing research interest in tool assisted LLMs solving real-world challenges, which calls for comprehensive evaluation of tool-use capabilities. While previous works focused on either evaluating over stateless web services (RESTful API), based on a single turn user prompt, or an off-policy dialog…

August 14, 2024

In "FAANG"

Psyberg: Automated end to end catch up

By Abhinaya Shetty, Bharath MummadisettyThis blog post will cover how Psyberg helps automate the end-to-end catchup of different pipelines, including dimension tables.In the previous installments of this series, we introduced Psyberg and delved into its core operational modes: Stateless and Stateful Data Processing. Now, let’s explore the state of our…

November 16, 2023

In "FAANG"