This paper identifies suboptimalities in default GPU-first scheduling for AI tool workloads and proposes an agentic scheduler that adaptively assigns tools to GPU or CPU based on runtime factors.

This paper introduces SwarmX, a system for scheduling agentic AI applications in GPU-CPU clusters using neural predictors, reducing tail latency by up to 61.5% and sustaining up to 2x the throughput o…

The paper introduces AsyncTool, a new benchmark designed to evaluate LLM agents' ability to handle multiple, concurrent tasks with delayed tool feedback, demonstrating that asynchronous coordination i…

The paper introduces DEFT, a novel Mixture-of-Experts DRL architecture, to intelligently schedule dynamic cloud workflows with varying deadlines, significantly improving performance over existing sing…

RACE-Sched is an asynchronous agentic framework that successfully integrates low-latency, real-time scheduling decisions with advanced, long-horizon reasoning provided by Large Language Models.

The paper introduces Hyperparam, a set of lightweight JavaScript libraries designed to enable direct, model-aware querying of unstructured data (like agent traces) within client-side AI applications.

The paper extends results for interval scheduling to the more general throughput problem in the real-time model with constant competitive ratios for specific weight functions and advance notice.

MOSAIC is a novel scheduling framework that significantly accelerates Mixture-of-Agents (MoA) workloads by jointly optimizing expert placement and utilizing confidence-aware adaptive aggregation.

The paper presents a tool-making pipeline for production LLM agents that compiles repeated steps into validated, versioned tools before deployment, reducing latency and error rate.

This paper systematically analyzes security risks in cloud-hosted, tool-enabled AI agents, concluding that most risks stem from over-privileged tools and capability-intent mismatches rather than novel…

This paper analyzes tool-calling in LLM agents, demonstrating that evaluation results are highly sensitive to implementation details and proposing new techniques to significantly improve the efficienc…

The paper argues that observed gains in multimodal agents using tools may be due to learning tool-calling patterns rather than genuine capability expansion, finding that tool access provides little co…

HighTide is an evolving, AI-assisted, open-source benchmark suite for VLSI design, providing a comprehensive and scalable platform for hardware development.

The paper proposes FeasiGen, a method to automatically create infeasible tasks for tool-using agents, and finds that most current agents struggle significantly to detect and stop when faced with such…

The paper proposes EAPO, a framework that enables agentic models to learn when to forgo using external tools, thereby mitigating tool abuse while maintaining high reasoning accuracy.

The paper proposes a conservative extension of Lustre's clock calculus to facilitate the embedding of ML models in reactive applications.

This paper evaluates AI agent systems for electronic design automation (EDA) using a unified benchmark called FluxBench, assessing their performance across various EDA workflows and tasks.

The paper introduces E-Bench, a synthetic benchmark for evaluating multi-step tool use in Large Language Models across three product domains.

The paper introduces TASTE, an automatic task synthesis method that generates challenging agent benchmarks by evolving tool sequences, demonstrating that existing benchmarks are saturated and that TAS…