# Why Do AI Agents Systematically Fail at Cloud Root Cause Analysis?

arXiv: https://arxiv.org/abs/2602.09937 · HTML: https://mlsanity.com/paper/2602.09937/

## Key facts

- Cited by 9 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 6 of its 12 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 6 of 6)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [Human-In-the-Loop Software Development Agents](https://mlsanity.com/paper/2411.12924/) (2024)
- [RCAEval: A Benchmark for Root Cause Analysis of Microservice Systems with Telemetry Data](https://mlsanity.com/paper/2412.17015/) (2024)
- [Beyond Context: Large Language Models' Failure to Grasp Users' Intent](https://mlsanity.com/paper/2512.21110/) (2025)

## Built on by (most cited first, 9 of 9)

- [Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model](https://mlsanity.com/paper/2608.13867/) (2026)
- [CUJBench: Benchmarking LLM-Agent on Cross-Modal Failure Diagnosis from Browser to Backend](https://mlsanity.com/paper/2604.23455/) (2026)
- [What a Pooled Leaderboard Does Not Say: Auditing the Scope and Provenance of Method Comparisons in Microservice RCA Benchmarks](https://mlsanity.com/paper/2606.29159/) (2026)
- [RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough](https://mlsanity.com/paper/2608.07583/) (2026)
- [OpsLLM: Construction of Large Language Model for Software Operations with Multi-stage Learning](https://mlsanity.com/paper/2605.02906/) (2026)
- [Auditable Graph-Guided Root Cause Analysis for Kubernetes Incidents](https://mlsanity.com/paper/2606.08590/) (2026)
- [Beyond Fault Localization: A Trajectory-Level Study of LLM Agents for Microservice Root Cause Analysis](https://mlsanity.com/paper/2608.21310/) (2026)
- [EviRCA: Decoupling Evidence Extraction from Reasoning for Microservice Root-Cause Analysis](https://mlsanity.com/paper/2609.19825/) (2026)
- [Agentic RCA for Internet-Scale Services Using Constrained Creativity](https://mlsanity.com/paper/2610.08622/) (2026)

## Abstract (arXiv)

Failures in large-scale cloud systems incur substantial financial losses, making automated Root Cause Analysis (RCA) essential for operational stability. Recent efforts leverage Large Language Model (LLM) agents to automate this task, yet existing systems exhibit low detection accuracy even with capable models, and current evaluation frameworks assess only final answer correctness without revealing why the agent's reasoning failed. This paper presents a process level failure analysis of LLM-based RCA agents. We execute the full OpenRCA benchmark across five LLM models, producing 1,675 agent runs, and classify observed failures into 12 pitfall types across intra-agent reasoning, inter-agent communication, and agent-environment interaction. Our analysis reveals that the most prevalent pitfalls, notably hallucinated data interpretation and incomplete exploration, persist across all models regardless of capability tier, indicating that these failures originate from the shared agent architecture rather than from individual model limitations. Controlled mitigation experiments further show that prompt engineering alone cannot resolve the dominant pitfalls, whereas enriching the inter-agent communication protocol reduces communication-related failures by up to 15 percentage points. The pitfall taxonomy and diagnostic methodology developed in this work provide a foundation for designing more reliable autonomous agents for cloud RCA.