# IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST

DevFeed: [IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST](<https://devfeed.tech/articles/ibm-and-uc-berkeley-diagnose-why-enterprise-agents-fail-using-it-bench-and-mast-7267.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/ibm-research/itbenchandmast>)

Author: Ayhan Sebin; Rohan Arora; Saurabh Jha

Published: 2026-02-18T16:15:45Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [ibm](<https://devfeed.tech/topics/ibm.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [site-reliability-engineering](<https://devfeed.tech/topics/site-reliability-engineering.md>), [incident](<https://devfeed.tech/topics/incident.md>), [Kubernetes](<https://devfeed.tech/topics/kubernetes.md>), [finops](<https://devfeed.tech/topics/finops.md>), [Security](<https://devfeed.tech/topics/security.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [automation](<https://devfeed.tech/tags/automation.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [gpt-oss](<https://devfeed.tech/tags/gpt-oss.md>), [hallucinations](<https://devfeed.tech/tags/hallucinations.md>), [ibm](<https://devfeed.tech/tags/ibm.md>), [incident](<https://devfeed.tech/tags/incident.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [llm](<https://devfeed.tech/tags/llm.md>), [logs](<https://devfeed.tech/tags/logs.md>), [loops](<https://devfeed.tech/tags/loops.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [performance](<https://devfeed.tech/tags/performance.md>), [research](<https://devfeed.tech/tags/research.md>), [systems](<https://devfeed.tech/tags/systems.md>), [tool](<https://devfeed.tech/tags/tool.md>)

## AI overview

IBM Research and UC Berkeley analyze why agentic LLM systems fail in enterprise IT automation using ITBench traces and the MAST failure taxonomy. Their analysis of 310 SRE traces compares Gemini-3-Flash, Kimi-K2, and GPT-OSS-120B, identifying verification errors, cascading failures, premature termination, looping, and hallucinations as major reliability problems.

## Source excerpt

IBM Research and UC Berkeley collaborated to study how agentic LLM systems break in real-world IT automation, for tasks involving incident triage, logs/metrics queries, and Kubernetes actions in long-horizon tool loops. Benchmarks typically reduce performance to a single number, telling you whether an agent failed but never why. To solve this black-box problem, we applied MAST (Multi-Agent System Failure Taxonomy), an emerging practice for diagnosing agentic reliability ).