# Benchmarking LLM Serving Systems for Agentic AI Workloads with XPerf

arXiv: https://arxiv.org/abs/2608.20370 · HTML: https://mlsanity.com/paper/2608.20370/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 66 references that are in the map.
- First posted on arXiv 19 Jun 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)
- Efficient LLM inference and serving / [Efficient reasoning and agent inference](https://mlsanity.com/inference/efficient-reasoning-and-agent-inference/)

## Builds on (most cited first, 29 of 29)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention](https://mlsanity.com/paper/2502.11089/) (2025)
- [Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks](https://mlsanity.com/paper/2411.04468/) (2024)
- [MLPerf Inference Benchmark](https://mlsanity.com/paper/1911.02549/) (2019)
- [An LLM Compiler for Parallel Function Calling](https://mlsanity.com/paper/2312.04511/) (2023)
- [AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?](https://mlsanity.com/paper/2407.15711/) (2024)
- [Parrot: Efficient Serving of LLM-based Applications with Semantic Variable](https://mlsanity.com/paper/2405.19888/) (2024)
- [Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation](https://mlsanity.com/paper/2510.11977/) (2025)
- [AgentRxiv: Towards Collaborative Autonomous Research](https://mlsanity.com/paper/2503.18102/) (2025)
- [Preble: Efficient Distributed Prompt Scheduling for LLM Serving](https://mlsanity.com/paper/2407.00023/) (2024)
- [ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning](https://mlsanity.com/paper/2410.02052/) (2024)
- [KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows](https://mlsanity.com/paper/2507.07400/) (2025)
- [Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference](https://mlsanity.com/paper/2506.09501/) (2025)
- [Teola: Towards End-to-End Optimization of LLM-based Applications](https://mlsanity.com/paper/2407.00326/) (2024)
- [DyFlow: Dynamic Workflow Framework for Agentic Reasoning](https://mlsanity.com/paper/2509.26062/) (2025)
- [Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents](https://mlsanity.com/paper/2402.17896/) (2024)
- [LLM-Powered AI Agent Systems and Their Applications in Industry](https://mlsanity.com/paper/2505.16120/) (2025)
- [ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference System](https://mlsanity.com/paper/2602.13692/) (2026)
- [Pie: A Programmable Serving System for Emerging LLM Applications](https://mlsanity.com/paper/2510.24051/) (2025)
- [Kairos: Low-latency Multi-Agent Serving with Shared LLMs and Excessive Loads in the Public Cloud](https://mlsanity.com/paper/2508.06948/) (2025)

## Built on by (most cited first, 1 of 1)

- [AgBench: Agentic AI Benchmarks for Personal AI Devices](https://mlsanity.com/paper/2609.38652/) (2026)

## Abstract (arXiv)

We present XPerf, a benchmarking framework that load-tests LLM serving systems with diverse agentic AI workloads. It provides detailed profiling of the serving system and hardware, enabling users to identify performance bottlenecks introduced by agentic workloads. Benchmarking LLM serving systems under agentic workloads is challenging - agentic applications rely on nondeterministic LLM outputs to guide their control flow; therefore, workload patterns vary unpredictably from run to run. XPerf minimizes this workload variation with a fine-grained trace replay approach: it enables users to easily collect traces from real agentic applications, synthesize new workloads with various patterns if needed, and reproducibly replay them on different LLM serving systems. XPerf includes eight agentic applications across diverse use cases (e.g., coding, deep research, and Q&A) by default. Our empirical study using these workloads shows that XPerf accurately replays agentic workloads, provides detailed performance breakdowns, scales to larger serving systems, and assists in serving system debugging. We will open-source XPerf on GitHub.