From General Agents to RCA Experts: A Self-Evolving Harness for Root Cause Analysis

arXiv:2608.25661 · cs.SE, cs.AI · Submitted 2026-08-26 · Read on arXiv

cs.SE, cs.AI

Submitted: 2026-08-26

Updated: 2026-08-26

Code: https://github.com/sst/opencode

Terminology

• Accuracy — 23× in this paper · explained in 1 episode
• Verification — 17× in this paper · explained in 2 episodes
• Benchmark — 15× in this paper · explained in 2 episodes
• Agent Harness — 5× in this paper · explained in 1 episode
• Trace — 5× in this paper · explained in 2 episodes
• Causal Inference — 2× in this paper · explained in 4 episodes
• Core — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Progressive Disclosure — 2× in this paper · explained in 2 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Diagnostic Tools — 1× in this paper · explained in 2 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Multi-Agent System — 1× in this paper · explained in 5 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes

Sources

• Failure Diagnosis in Microservice Systems: A Comprehensive Survey and Analysis
• Automatic Root Cause Analysis via Large Language Models for Cloud Incidents
• RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models
• Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysis
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
• RCAEval: A Benchmark for Root Cause Analysis of Microservice Systems with Telemetry Data
• Xpert: Empowering Incident Management with Query Recommendations via Large Language Models
• Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models
• Assess and Summarize: Improve Outage Understanding with Large Language Models
• Automated Root Causing of Cloud Incidents using In-Context Learning with GPT-4
• Cognitive Architectures for Language Agents
• Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
• MemGPT: Towards LLMs as Operating Systems
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• ExpeL: LLM Agents Are Experiential Learners
• GLM-5: from Vibe Coding to Agentic Engineering
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• AutoTSG: Learning and Synthesis for Incident Troubleshooting
• Mining Root Cause Knowledge from Cloud Service Incident Investigations for AIOps
• A Survey on In-context Learning

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties