Pith. sign in

REVIEW 9 cited by

ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.05352 v1 pith:3Z2ODSFK submitted 2025-02-07 cs.AI cs.DCcs.MA

classification cs.AIcs.DCcs.MA
keywords agentsautomationitbenchscenariosreal-worldtaskscisofinops
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Realizing the vision of using AI agents to automate critical IT tasks depends on the ability to measure and understand effectiveness of proposed solutions. We introduce ITBench, a framework that offers a systematic methodology for benchmarking AI agents to address real-world IT automation tasks. Our initial release targets three key areas: Site Reliability Engineering (SRE), Compliance and Security Operations (CISO), and Financial Operations (FinOps). The design enables AI researchers to understand the challenges and opportunities of AI agents for IT automation with push-button workflows and interpretable metrics. ITBench includes an initial set of 94 real-world scenarios, which can be easily extended by community contributions. Our results show that agents powered by state-of-the-art models resolve only 13.8% of SRE scenarios, 25.2% of CISO scenarios, and 0% of FinOps scenarios. We expect ITBench to be a key enabler of AI-driven IT automation that is correct, safe, and fast.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Pooled Leaderboards Hide System-Specific Winners: A Reporting-Protocol Audit of Offline Root-Cause Analysis Benchmarks

    cs.AI 2026-06 unverdicted novelty 7.0 of 10

    Pooled top-1 accuracy rankings in RCA benchmarks do not reliably identify per-subsystem winners, as pairwise comparisons across 11 subsystems show effects of both signs and leave-one-system-out selection incurs regret...

  2. Beyond Component Testing: Validating Agentic AI Systems

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Agentic AI cannot be adequately validated by component tests alone; trajectory-in-context validation is required, and current practice is mature only for behavioral evaluation.

  3. LLMs Corrupt Your Documents When You Delegate

    cs.CL 2026-04 unverdicted novelty 6.0 of 10

    LLMs corrupt an average of 25% of document content during long delegated editing workflows across 52 domains, even frontier models, and agentic tools do not mitigate the issue.

  4. Auditable Graph-Guided Root Cause Analysis for Kubernetes Incidents

    cs.SE 2026-06 conditional novelty 5.0 of 10

    Graph Traversal Agent improves root-cause F1 from 0.6087 to 0.9130 on ITBench snapshots but the gain is benchmark-coupled to cases where the injected fault is already in the evidence graph.

  5. Synthetic Scenario Generation for Evaluation of Industry 4.0 Agents

    cs.AI 2026-05 conditional novelty 5.0 of 10

    A synthetic scenario generation pipeline can expand an industrial agent benchmark to new asset classes with comparable quality and large runtime savings.

  6. Runtime-Structured Task Decomposition for Agentic Coding Systems

    cs.SE 2026-05 unverdicted novelty 5.0 of 10

    Runtime-structured task decomposition reduces retry costs in agentic coding systems by up to 51.7% versus monolithic prompts by rerunning only failed subtasks on two software engineering workloads.

  7. From Assistance to Agency: Rethinking Autonomy and Control in CI/CD Pipelines

    cs.SE 2026-05 unverdicted novelty 5.0 of 10

    The central challenge in AI-augmented CI/CD is designing authority transfer from humans to agents under constraints, as current systems remain limited to bounded data-plane autonomy backed by external governance.

  8. Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery

    eess.SY 2026-05 unverdicted novelty 5.0 of 10

    The paper introduces Experiment-as-Code Labs as a declarative stack synthesizing AI agents, systems orchestration, and physical lab control for AI-driven discovery.

  9. Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery

    eess.SY 2026-05 unverdicted novelty 5.0 of 10

    Experiment-as-Code Labs encodes experiments as declarative configurations that AI agents generate, systems software analyzes and orchestrates, and device APIs execute on physical lab hardware.

Pith tools