Skip to content
Book Open access

HERO: Hypothesis-Centered Root-Cause Analysis for Microservice Incidents

Oct 2026 · Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering · pp. 2703-2715 · 0 citations · 56 references

TL;DR

Hero is presented, a hypothesis-centered RCA framework that formulates diagnosis as controlled discrimination among competing hypotheses via bounded hypothesis-space instantiation, explicit belief-state tracking, and ambiguity-guided evidence acquisition to suggest that explicitly controlling competing hypotheses is an effective and practically promising abstraction for microservice RCA.

Abstract

Root-cause analysis (RCA) in cloud-native microservice systems is challenging because it requires integrating heterogeneous observability signals and deciding what to inspect next under limited diagnosis budgets. Existing large language model (LLM)-based RCA agents either rely heavily on predefined workflows, whose effectiveness is constrained by incomplete Standard Operating Procedure (SOP) coverage, or adopt open-ended diagnosis, which remains brittle when multiple plausible root-cause hypotheses are consistent with the observed evidence. We present Hero, a hypothesis-centered RCA framework that formulates diagnosis as controlled discrimination among competing hypotheses via bounded hypothesis-space instantiation, explicit belief-state tracking, and ambiguity-guided evidence acquisition. We evaluate Hero on OpenRCA and a real-world industrial incident dataset against representative workflow-based and open-ended baselines. On OpenRCA with DeepSeek-V3, Hero achieves an SR of 79.77, outperforming the strongest ReAct-style baseline by 23.20 points while using 1.04 fewer actions on average. On the industrial dataset, it reaches an SR of 85.00 and remains the best-performing method. These results suggest that explicitly controlling competing hypotheses is an effective and practically promising abstraction for microservice RCA, especially in real-world, production-style incidents with incomplete workflow coverage and high diagnostic ambiguity.

Read PDF

Similar papers

Preprint Oct 2026

CloudIR-Bench: A Benchmark for Root Cause Analysis and Mitigation of Cloud Incidents

CloudIR-Bench is introduced, the first publicly available benchmark providing a dataset and evaluation framework for incident report-based RCA and mitigation prediction, and results reveal the capabilities and limitations of existing LLMs in this domain.

Hoang Tran, Huong Ha, T. Dang et al. · 0 citations
Book Open access Oct 2026

OpsLens: Runbook-Free Root Cause Analysis via Multi-agent Collaboration and Tool Management

Root Cause Analysis (RCA) is critical for cloud service reliability, requiring correlation of multi-modal observability data (i.e., traces, logs, and metrics) to identify failure causes. Current LLM-based RCA approaches face two key limitations: over-reliance on system-specific artifacts (e.g., runbooks), limiting tran...

Hai-Yu Huang, Jiewei Lyu, Gou Tan et al. · 0 citations

Where Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents

This work presents an end-to-end diagnostic study of an Autonomous Adversary system with orchestrator, executor, and validator LLMs in enterprise-like lateral-movement scenarios and uses comparative LLM-as-a-Judge analysis to identify planning deficiencies.

Saeedeh Lohrasbi, Mohammad Mamun, Ahmad Yehia et al. · 0 citations
Conference Open access Oct 2026

Dual-Axis Benchmark and Preventive Scaffold: Surfacing and Mitigating Silent Risks in LLM Data Preparation

Large language model (LLM) agents working on raw, heterogeneous data may fail silently when they act on upstream assumptions that turn out to be wrong. Existing evaluations rarely surface this risk, benchmarking on clean, pre-identified inputs; agentic frameworks respond by layering self-critique or multi-agent debate...

Ming-Song Chen, S. Arifuzzaman · 0 citations
Oct 2026

HALAS: On-Demand and AoI-Guided Explainability for Real-Time XR Analytics.

Understanding user behavior in extended reality (XR) is often performed through post-hoc pipelines that log complete sessions and invoke large language models (LLMs) offline. Such pipelines incur substantial latency, bandwidth overhead, and unnecessary LLM inference costs, limiting continuous in session analytics. We p...

Bo-Yan Li, Chong-Li Zhang, Chun-Sheng Wang et al. · 0 citations
Book Open access Oct 2026

OpenStack-RCA-Bench: A Reproducible IaaS Root Cause Analysis Dataset

We present OpenStack-RCA-Bench, an open dataset of 64 chaos-engineering incidents for benchmarking RCA methods in OpenStack IaaS. It features a 9-phase pipeline integrating four fault injection methods (service stop, port block, process kill, config corruption), automated log collection via Loki, and ground truth defin...

I. Bogomolov, O. Borisenko · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.