# Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes arXiv: https://arxiv.org/abs/2603.06847 ยท HTML: https://mlsanity.com/paper/2603.06847/ ## Key facts - Cited by 12 papers in the map (data through 14 Oct 2026). - Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. - Builds on 16 of its 53 references that are in the map. - First posted on arXiv 6 Mar 2026. ## Placed in - LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/) - LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/) ## Builds on (most cited first, 16 of 16) - [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023) - [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016) - [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023) - [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025) - [Where LLM Agents Fail and How They can Learn From Failures](https://mlsanity.com/paper/2509.25370/) (2025) - [LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation](https://mlsanity.com/paper/2409.20550/) (2024) - [Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistant](https://mlsanity.com/paper/2502.01390/) (2025) - [LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions](https://mlsanity.com/paper/2509.18970/) (2025) - [AgentOps: Enabling Observability of LLM Agents](https://mlsanity.com/paper/2411.05285/) (2024) - [Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks](https://mlsanity.com/paper/2508.13143/) (2025) - [Bugs in Machine Learning-based Systems: A Faultload Benchmark](https://mlsanity.com/paper/2206.12311/) (2022) - [An Empirical Study of Testing Practices in Open Source AI Agent Frameworks and Agentic Applications](https://mlsanity.com/paper/2509.19185/) (2025) - [Bug Characterization in Machine Learning-based Systems](https://mlsanity.com/paper/2307.14512/) (2023) - [Towards Enhancing the Reproducibility of Deep Learning Bugs: An Empirical Study](https://mlsanity.com/paper/2401.03069/) (2024) - [Towards Understanding the Impact of Data Bugs on Deep Learning Models in Software Engineering](https://mlsanity.com/paper/2411.12137/) (2024) - [Are Multi-language Design Smells Fault-prone? An Empirical Study](https://mlsanity.com/paper/2010.14331/) (2020) ## Built on by (most cited first, 12 of 12) - [Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures](https://mlsanity.com/paper/2607.28802/) (2026) - [CUADebug: Diagnosing and Repairing Computer-Use Agent Failures](https://mlsanity.com/paper/2608.02643/) (2026) - [Understanding Agent-Reactive Bugs at the Model-Harness Boundary: An Empirical Study of LLM Agent Issue Reports](https://mlsanity.com/paper/2607.15684/) (2026) - [Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems](https://mlsanity.com/paper/2608.25920/) (2026) - [Beyond State Machines: Executing Network Procedures with Agentic Tool-Calling Sequences](https://mlsanity.com/paper/2605.02584/) (2026) - [Do Agent Benchmarks Do What They Say? An Executable-Contract Audit of Tool-Using Agent Environments](https://mlsanity.com/paper/2609.37315/) (2026) - [The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project](https://mlsanity.com/paper/2603.21354/) (2026) - [SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution](https://mlsanity.com/paper/2608.05573/) (2026) - [Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning](https://mlsanity.com/paper/2609.38147/) (2026) - [Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems](https://mlsanity.com/paper/2605.27492/) (2026) - [LLM Serving in the Wild: An Empirical Study of Frameworks, Methods, and System Designs](https://mlsanity.com/paper/2608.03036/) (2026) - [Explaining AI Agents Through Execution Traces](https://mlsanity.com/paper/2609.06063/) (2026) ## Abstract (arXiv) Agentic AI systems combine LLM-based reasoning, orchestration, tool invocation, and interaction with external environments. These systems introduce faults that are difficult to characterize using existing taxonomies. To address this gap, we present an empirical study of faults in agentic AI systems. We collected 13,602 issues and pull requests from 40 repositories and, using stratified sampling, selected 385 faults for analysis. Through grounded theory, we derived taxonomies of fault types, symptoms, and root causes. We then used Apriori-based association rule mining to identify relationships among faults, symptoms, and root causes, and validated the taxonomy through a developer study with 145 practitioners. Our analysis produced a taxonomy of 34 fault types, organized into four architectural dimensions. These faults manifested as failures in structured-output interpretation, tool calls, runtime execution, and exception handling, with root causes including data schema mismatches, dependency drift, state management complexity, and model interface instability. Furthermore, association rules showed recurring cross-component propagation, linking structured data, dependency, and state management faults to their symptoms and root causes. Practitioners considered the taxonomy representative of agentic AI failures and suggested refinements related to multi-agent coordination and observability. These findings provide an empirical basis for diagnosing faults and improving reliability in agentic AI systems.