How Far Can Root Cause Analysis Go on Real-World Telemetry Data?

• URL: http://arxiv.org/abs/2607.13548v1
• Date: Wed, 15 Jul 2026 07:54:46 GMT
• Title: How Far Can Root Cause Analysis Go on Real-World Telemetry Data?
• Abstract summary: We show that classical causal discovery methods and existing LLM-based multi-agent systems fail to reliably identify root causes.<n>We present a Structured Multi-Agent RCA pipeline that substantially outperforms existing LLM-based and classical baselines.
• Score: 0.8594140167290097
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Identifying root causes in production microservice failures requires reasoning over large-scale, multimodal telemetry spanning metrics, logs, and traces, a problem that has proved resistant to both classical and LLM-based approaches. The OpenRCA dataset exemplifies these challenges: it is large-scale, multimodal, and lacks detailed domain knowledge, and yields consistently low accuracy across all existing methods. We show that classical causal discovery methods and existing LLM-based multi-agent systems fail to reliably identify root causes on this benchmark, and present a Structured Multi-Agent RCA pipeline that substantially outperforms existing LLM-based and classical baselines, supporting both domain-knowledge and knowledge-free operating modes. To diagnose where failures originate, we introduce a reverse reasoning agent that, given the correct answer, identifies which signals in the extracted anomalies support it and determines whether Stage~1 had access to those signals, classifying each failure as Reasoning Gap (evidence present but unused) or Data Ambiguity (evidence genuinely absent). This analysis reveals that the required evidence is present in the vast majority of failures: the bottleneck is not data access but the agent's ability to reason over it correctly. We further introduce an automated rule mining pipeline that systematically extracts discrimination rules from reverse reasoning reports, reducing reliance on manual knowledge curation. Across all configurations, model reasoning capability and domain knowledge are the primary constraints: stronger models embed more domain expertise, and explicit knowledge injection partially compensates for this gap. Reasoning performance remains practically bounded even when evidence extraction is perfect: scaffold engineering and better data pipelines alone cannot close this gap; progress requires improvements at the model level.

Related papers

• LogSemFuse: Semantic Evidence Fusion for Explainable Log Anomaly Detection [6.950497660953971]
  LogSemFuse is an evidence-guided plug-in framework that enhances existing backbone detectors without replacing their original pipelines.<n>We evaluate LogSemFuse on HDFS, BGL, and Liberty using DeepLog, LogAnomaly, LogBERT, and NeuralLog as backbones.
  arXiv  Detail & Related papers  (2026-07-03T20:50:07Z)
• Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting [95.24017293537025]
  Causal Ensemble Agent (CEA) is a novel framework that aggregates structural insights from statistical discovery experts across different graph levels.<n>CEA achieves the strongest overall performance across a wide range of causal discovery methods.
  arXiv  Detail & Related papers  (2026-06-09T09:09:07Z)
• Anomaly Detection and Root Cause Analysis for Microservice Systems [0.0]
  Microservice systems are widely used to build cloud applications, yet their complexity makes failures inevitable.<n>This thesis advances automated anomaly detection and root cause analysis for microservice failures.
  arXiv  Detail & Related papers  (2026-06-08T00:50:43Z)
• VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems [79.51005192758262]
  Large language model-driven multi-agent systems excel at complex tasks.<n>However, unreliable agents remain a key bottleneck to system-level reliability.<n>We propose a hypothesis verification framework for agent failure attribution.
  arXiv  Detail & Related papers  (2026-05-17T14:09:35Z)
• Use What You Know: Causal Foundation Models with Partial Graphs [97.91863420927866]
  Recently proposed Causal Foundation Models (CFMs) promise a more unified approach by amortising causal discovery and inference in a single step.<n>We bridge this gap by introducing methods to condition CFMs on causal information, such as the causal graph or more readily available ancestral information.
  arXiv  Detail & Related papers  (2026-02-16T17:56:37Z)
• Stalled, Biased, and Confused: Uncovering Reasoning Failures in LLMs for Cloud-Based Root Cause Analysis [5.532586951580959]
  We present a focused empirical evaluation that isolates an LLM's reasoning behavior.<n>We produce a labeled taxonomy of 16 common RCA reasoning failures and use an LLM-as-a-Judge for annotation.
  arXiv  Detail & Related papers  (2026-01-29T18:23:26Z)
• Think Locally, Explain Globally: Graph-Guided LLM Investigations via Local Reasoning and Belief Propagation [5.191980417814362]
  LLM agents excel when environments are mostly static and the needed information fits in a model's context window.<n>ReAct-style agents are especially brittle in this regime.<n>We propose EoG, a framework in which an LLM performs bounded local evidence mining and labeling (cause vs symptom) while a deterministic controller manages, state, and belief propagation to compute a minimal explanatory frontier.
  arXiv  Detail & Related papers  (2026-01-25T17:27:19Z)
• Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMs [50.075587392477935]
  We conduct the first large-scale empirical study of 705 real-world failures from the open-source DeepSeek, Llama, and Qwen ecosystems.<n>Our analysis reveals a paradigm shift: white-box orchestration relocates the reliability bottleneck from model algorithmic defects to the systemic fragility of the deployment stack.
  arXiv  Detail & Related papers  (2026-01-20T06:42:56Z)
• Hypothesize-Then-Verify: Speculative Root Cause Analysis for Microservices with Pathwise Parallelism [19.31110304702373]
  SpecRCA is a speculative root cause analysis framework that adopts a textithypothesize-then-verify paradigm.<n>Preliminary experiments on the AIOps 2022 demonstrate that SpecRCA achieves superior accuracy and efficiency compared to existing approaches.
  arXiv  Detail & Related papers  (2026-01-06T05:58:25Z)
• Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics [89.1999907891494]
  We present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox.<n>Our evaluation of 25 state-of-the-art models reveals systematic weaknesses across all architectures.<n>We develop an agentic workflow, EvidenceLoop, that explicitly targets the challenges our benchmark identifies.
  arXiv  Detail & Related papers  (2025-10-01T07:59:03Z)
• Multi-modal Causal Structure Learning and Root Cause Analysis [67.67578590390907]
  We propose Mulan, a unified multi-modal causal structure learning method for root cause localization. We leverage a log-tailored language model to facilitate log representation learning, converting log sequences into time-series data. We also introduce a novel key performance indicator-aware attention mechanism for assessing modality reliability and co-learning a final causal graph.
  arXiv  Detail & Related papers  (2024-02-04T05:50:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.