paper-with-me

홈 › Papers

SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarios

2026-05-08 · Jackson Clark, Yiming Su, Saad Mohammad Rafid Pial, Yifang Tian, Lily Gniedziejko, Hans-Arno Jacobsen, Yinfang Chen, Tianyin Xu arxiv

AI agents are increasingly used to diagnose and mitigate failures in production systems, known as agentic Site Reliability Engineering (SRE). Current SRE benchmarks are limited to oversimplistic SRE tasks and are unfortunately hard to extend due to bespoke designs. We present SREGym, a high-fidelity benchmark for SRE agents. SREGym exposes a live system environment built atop real-world cloud-native system stacks, where high-fidelity failure scenarios are simulated through fault injectors. SREGym models the complexity of production environments by simulating (1) a wide range of faults at different layers, (2) various ambient noises, and (3) diverse failure modes such as metastable failures and correlated failures. SREGym is architected as a modular, extensible framework that orchestrates fault and noise injectors across stacks. SREGym currently includes 90 realistic, challenging SRE problems. We use SREGym to evaluate frontier agents and show that their capabilities varies significantly in addressing different kinds of failures, with up to 40% differences in end-to-end results. SREGym is actively maintained as an open-source project and has been used by researchers and practitioners.

📄 PDF Abstract BibTeX arXiv:2605.07161

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks

2026-03-20 · Xiang Long, Li Du, Yilong Xu, RongJian Xu 외 arxiv

OpenClaw-style personal assistants extend LLM agents from isolated tool use to open-ended, stateful, and personalized software environments. Evaluating these assistants is fundamentally a fidelity problem: benchmarks mus…

MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents

2025-12-14 · Youngmin Im, Byeongung Jo, Jaeyoung Wi, Seungwoo Baek 외 arxiv

Mobile GUI Agents, AI agents capable of interacting with mobile applications on behalf of users, have the potential to transform human computer interaction. However, current evaluation practices for GUI agents face two f…

BankerToolBench: Evaluating AI Agents in End-to-End Investment Banking Workflows

2026-04-13 · Elaine Lau, Markus Dücker, Ronak Chaudhary, Hui Wen Goh 외 arxiv

Existing AI benchmarks lack the fidelity to assess economically meaningful progress on professional workflows. To evaluate frontier AI agents in a high-value, labor-intensive profession, we introduce BankerToolBench (BTB…

A2Eval: Agentic and Automated Evaluation for Embodied Brain

2026-02-02 · Shuai Zhang, Jiayu Hu, Zijie Chen, Zeyuan Ding 외 arxiv

Current embodied VLM evaluation relies on static, expert-defined, manually annotated benchmarks that exhibit severe redundancy and coverage imbalance. This labor intensive paradigm drains computational and annotation res…

SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation

2026-01-21 · Xichen Zhang, Ziyi He, Yinghao Zhu, Sitong Wu 외 arxiv

Search agents have emerged as a pivotal paradigm for solving open-ended, knowledge-intensive reasoning tasks. However, training these agents via Reinforcement Learning (RL) faces a critical dilemma: interacting with live…

Reinforcement Learning