--- title: "IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST" url: https://daily.dev/posts/ibm-and-uc-berkeley-diagnose-why-enterprise-agents-fail-using-it-bench-and-mast-k5a0ez19y source_url: https://huggingface.co/blog/ibm-research/itbenchandmast type: article source: "Hugging Face" published: 2026-02-18T16:17:22.153Z updated: 2026-02-18T16:17:48.878Z tags: ["ai-agents"] reading_time: 11 upvotes: 1 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST **[Hugging Face](https://daily.dev/sources/huggingface)** · 11 min read · 1 upvotes · 0 comments ## Summary IBM Research and UC Berkeley applied MAST (Multi-Agent System Failure Taxonomy) to ITBench—an enterprise benchmark for SRE, Security, and FinOps automation—to diagnose why LLM-based agents fail in real-world IT workflows. By annotating 310 execution traces across Gemini-3-Flash, Kimi-K2, and GPT-OSS-120B, they found that stronger frontier models fail cleanly with ~2.6 failure modes per trace, while weaker open models cascade with up to 5.3. The most universally fatal failure is FM-3.3 (Incorrect Verification)—agents declaring success without checking ground truth. Kimi-K2 struggles with termination awareness, while GPT-OSS-120B suffers from memory loss and reasoning-action mismatch. Practical fixes include externalizing verification via tool-mediated evidence, implementing finite state machines for termination control, and aggressive context hygiene for models prone to cascading failures. Prompt engineering alone yields only ~15% improvement; architectural interventions like Summarizer Agents or State Machines can yield up to 53%. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM](https://daily.dev/posts/itbench-aa-frontier-models-score-below-50-on-the-first-benchmark-for-agentic-enterprise-it-tasks--inm3wceim) · Hugging Face · 1 upvotes · 0 comments - [Three Years of Building Agents in Production \(Part 1\)](https://daily.dev/posts/three-years-of-building-agents-in-production-part-1--d2wjasjzx) · Mabl Engineering Blog · 3 upvotes · 1 comments - [Why Your Multi-Agent System is Failing: Escaping the 17x Error Trap of the “Bag of Agents”](https://daily.dev/posts/why-your-multi-agent-system-is-failing-escaping-the-17x-error-trap-of-the-bag-of-agents--ukjhzfgyn) · Towards Data Science · 2 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents) [View this post on daily.dev](https://daily.dev/posts/ibm-and-uc-berkeley-diagnose-why-enterprise-agents-fail-using-it-bench-and-mast-k5a0ez19y)