Related papers: DataFlow: An LLM-Driven Framework for Unified Data…
Large language model (LLM)-based systems are becoming increasingly popular for solving tasks by constructing executable workflows that interleave LLM calls, information retrieval, tool use, code execution, memory updates, and verification.…
In the world of Big Data analytics, there is a series of tools aiming at simplifying programming applications to be executed on clusters. Although each tool claims to provide better programming, data and execution models, for which only…
Serverless computing that runs functions with auto-scaling is a popular task execution pattern in the cloud-native era. By connecting serverless functions into workflows, tenants can achieve complex functionality. Prior researches adopt the…
TensorFlow is a popular cloud computing framework that targets machine learning applications. It separates the specification of application logic (in a dataflow graph) from the execution of the logic. TensorFlow's native runtime executes…
Large Language Models (LLMs) have shown remarkable proficiency in natural language understanding (NLU), opening doors for innovative applications. We introduce StreamLink - an LLM-driven distributed data system designed to improve the…
Parallel dataflow systems have become a standard technology for large-scale data analytics. Complex data analysis programs in areas such as machine learning and graph analytics often involve control flow, i.e., iterations and branching.…
GraphFlow is a visual workflow system designed to improve the reliability of agentic AI automation in multi-step, mission-critical processes. In these workflows, small errors compound rapidly: under an idealized model of independent steps,…
Modern software systems require code that is not only functional but also maintainable and well-structured. Although Large Language Models (LLMs) are increasingly used to automate software development, most studies focus on isolated,…
Recent advances in large language models (LLMs) transform how machine learning (ML) pipelines are developed and evaluated. LLMs enable a new type of workload, agentic pipeline search, in which autonomous or semi-autonomous agents generate,…
Large Language Models (LLMs) have revolutionized natural language interaction with data. The "holy grail" of data analytics is to build autonomous Data Agents that can self-drive complex data analysis workflows. However, current…
Multimodal Large Language Models (MLLMs) have achieved remarkable advances by integrating text, image, and audio understanding within a unified architecture. However, existing distributed training frameworks remain fundamentally data-blind:…
In the age of large language models (LLMs), autonomous agents have emerged as a powerful paradigm for achieving general intelligence. These agents dynamically leverage tools, memory, and reasoning capabilities to accomplish user-defined…
AI agents can extend their capabilities at inference time by loading reusable skills into context, yet equipping an agent with too many skills, particularly irrelevant ones, degrades performance. As community-driven skill repositories grow,…
Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled powerful autonomous agents capable of complex reasoning and multi-modal tool use. Despite their growing capabilities, today's agent frameworks…
Traditional Data+AI systems utilize data-driven techniques to optimize performance, but they rely heavily on human experts to orchestrate system pipelines, enabling them to adapt to changes in data, queries, tasks, and environments. For…
Developing language model-based dialogue agents requires effective data to train models that can follow specific task logic. However, most existing data simulation methods focus on increasing diversity in language, topics, or dialogue acts…
We study compiled AI, a paradigm in which large language models generate executable code artifacts during a compilation phase, after which workflows execute deterministically without further model invocation. This paradigm has antecedents…
Reinforcement learning (RL) is increasingly used to improve the reasoning, coding, and tool-use capabilities of large language models, but agentic RL remains prohibitively expensive. Scaling RL to agentic LLMs requires supporting complex…
Recent availability of Large Language Models (LLMs) has led to the development of numerous LLM-based approaches aimed at providing natural language interfaces for various end-user tasks. These end-user tasks in turn can typically be…
Building deployment-ready LLM agents requires complex orchestration of tools, data sources, and control flow logic, yet existing systems tightly couple agent logic to specific programming languages and deployment models. We present a…