Related papers: FlowCompile: An Optimizing Compiler for Structured…

Pipeline parallelism is an essential distributed parallelism method. Increasingly complex and diverse DNN models necessitate meticulously customized pipeline schedules for performance. However, existing practices typically rely on…

Large language models (LLMs) are increasingly explored for their reasoning capabilities, yet their ability to perform structured, constraint-based optimization from natural language remains insufficiently understood. This study evaluates…

Long-term planning in complex, text-based environments presents significant challenges due to open-ended action spaces, ambiguous observations, and sparse feedback. Recent research suggests that large language models (LLMs) encode rich…

Automatically compiling open-source software (OSS) projects is a vital, labor-intensive, and complex task, which makes it a good challenge for LLM Agents. Existing methods rely on manually curated rules and workflows, which cannot adapt to…

Generating diverse, readable statistical charts from tabular data remains challenging for LLMs, as many failures become apparent after rendering and are not detectable from data or code alone. Existing chart datasets also rarely provide…

State-of-the-art results in large language models (LLMs) often rely on scale, which becomes computationally expensive. This has sparked a research agenda to reduce these models' parameter counts and computational costs without significantly…

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…

flowengineR is an R package designed to provide a modular and extensible framework for building reproducible algorithmic workflows for general-purpose machine learning pipelines. It is motivated by the rapidly evolving field of algorithmic…

Automated data preparation pipeline construction is critical for machine learning success, yet existing methods suffer from two fundamental limitations: they treat pipeline construction as black-box optimization without quantifying…

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:…

Optimizing Pandas programs is a challenging problem. Existing systems and compiler-based approaches offer reliability but are either heavyweight or support only a limited set of optimizations. Conversely, using LLMs in a per-program…

Large language model (LLM) agents have demonstrated strong capabilities across diverse domains, yet automated agent design remains a significant challenge. Current automated agent design approaches are often constrained by limited search…

Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhibit extensive redundancy from overlapping prompts and…

Accurate prediction of resource consumption and runtime for cloud workflow jobs is critical for scheduling efficiency, yet remains challenging due to the semi-structured nature of job configurations -- comprising shell commands,…

Large language models (LLMs) are largely static and often redo reasoning or repeat mistakes. Prior experience reuse typically relies on external retrieval, which is similarity-based, can introduce noise, and adds latency. We introduce SEAM…

Data pipelines are essential in stream processing as they enable the efficient collection, processing, and delivery of real-time data, supporting rapid data analysis. In this paper, we present AutoStreamPipe, a novel framework that employs…

Structured LLM routing is often treated as a prompt-engineering problem. We argue that it is, more fundamentally, a systems-level burden-allocation problem. As large language models (LLMs) become core control components in agentic AI…

Flowcharts are typically presented as images, driving the trend of using vision-language models (VLMs) for end-to-end flowchart understanding. However, two key challenges arise: (i) Limited controllability--users have minimal influence over…

Modern LLM reasoning relies on extensive test-time computation, driven by internal model training and external agentic orchestration. However, this synergy is often inefficient, as model verbosity and poor instruction following lead to…

Existing serverless workflow orchestration systems are predominantly designed for a single-cloud FaaS system, leading to vendor lock-in. This restricts performance optimization, cost reduction, and availability of applications. However,…