arXiv AI
Aug 6
Architectural Implications of Agentic AI Workflows
arXiv:2608. 04458v1 Announce Type: new Abstract: Agentic AI is emerging in datacenters, but its architectural implications remain unexplored.
MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems
arXiv:2604. 26963v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as the execution core of autonomous agents rather than as standalone text generators.
Related stories
arXiv AI
Jun 3
Libra: Efficient Resource Management for Agentic RL Post-Training
arXiv:2606. 03077v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a standard post-training paradigm for large language models (LLMs), extending beyond preference alignment to complex reasoning and multi-turn agentic behaviors.
arXiv AI
6d ago
Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines
Scepsy is a serving system designed to efficiently schedule arbitrary multi‑LLM agentic workflows on GPU clusters. It leverages the observation that each LLM’s share of execution time remains relatively stable across requests, profiling LLMs under various parallelism levels to build an Aggregate LLM Pipeline that predicts throughput and latency. Using this predictor, Scepsy searches for optimal GPU allocations—balancing fractional GPU shares, tensor parallelism, and replica counts—and then heuristically places them on the cluster to reduce fragmentation and honor network topology, achieving up to 2.5× higher throughput and 1.0–3.3× lower latency compared to baseline approaches.
arXiv Machine Learning
Aug 4
Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale
arXiv:2608. 00101v1 Announce Type: cross Abstract: AI coding agents like GitHub Copilot, Claude Code, and Codex interleave multi-step LLM inference with tool execution, creating a workload different from chatbots.
Hugging Face Trending Papers
Jun 8
AGENTSERVESIM: A Hardware-aware Simulator for Multi-Turn LLM Agent Serving
Multi-turn LLM agents interleave model calls with external tool invocations, shifting serving from stateless request processing to stateful program execution. Serving these workloads requires scheduling, KV-cache management, and routing policies that use program-level context, including turn dependencies, tool-induced gaps, and reusable KV state.
Hugging Face Trending Papers
5d ago
AgentPerfBench: A Benchmarking and Evaluation Suite for Inference Performance of Agentic LLMs
AgentPerfBench is a new benchmarking suite designed to evaluate the inference performance of agentic large language models (LLMs) that handle multi‑turn, tool‑using, and context‑expanding tasks. It builds on real traces from agentic benchmarks such as SWE‑Bench and TerminalBench, and generates synthetic profiles that reflect realistic input/output lengths and turn counts. The suite also provides kernel‑level Nsight Compute traces and a multi‑dimensional roofline model to identify hardware bottlenecks and quantify the gap between traditional chat benchmarks and agentic workloads.
arXiv AI
Jun 9
AGENTSERVESIM: A Hardware-aware Simulator for Multi-Turn LLM Agent Serving
arXiv:2606. 09613v1 Announce Type: cross Abstract: Multi-turn LLM agents interleave model calls with external tool invocations, shifting serving from stateless request processing to stateful program execution.
arXiv AI
Aug 26
PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents
PeakBench is a new benchmark designed to evaluate how large language model agents invoke multiple tools while respecting resource constraints and parallel execution. It provides executable multi‑tool workflows with dependency annotations and measured resource profiles, and introduces a two‑part evaluation framework that separates logical planning from physical scheduling. The study shows that strong logical planning alone does not guarantee safe or efficient execution, and that providing resource information can reduce overflows and improve utilization.
arXiv AI
Jul 24
Workload-Aware Caching for Multi-Agent Systems
arXiv:2607. 20495v1 Announce Type: new Abstract: Multi-agent systems decompose complex tasks into directed acyclic graphs (DAGs) of specialized agent executions, creating natural opportunities for caching intermediate results across queries.
arXiv Machine Learning
Jun 2
Multi-Agent Computer Use
arXiv:2606. 01533v1 Announce Type: cross Abstract: Computer use agents (CUAs) today are primarily deployed as single serial agents.
arXiv Machine Learning
Jun 2
Observation, Not Prediction: Conversation-Level Disaggregated Scheduling for Agentic Serving
arXiv:2606. 01839v1 Announce Type: cross Abstract: LLM-based agents resolve a user task through many turns of dependent inference and tool calls, producing a workload whose total cost is unknown when the task arrives.
arXiv AI
Jun 30
SwarmX: Agentic Scheduling for Low-Latency Agentic Systems
arXiv:2606. 21401v2 Announce Type: replace-cross Abstract: Agentic AI applications compose multiple model calls and tool executions, creating new scheduling challenges for GPU-CPU clusters.