# CUADebug: Diagnosing and Repairing Computer-Use Agent Failures

arXiv: https://arxiv.org/abs/2608.02643 · HTML: https://mlsanity.com/paper/2608.02643/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 17 of 17)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents](https://mlsanity.com/paper/2405.14573/) (2024)
- [Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale](https://mlsanity.com/paper/2409.08264/) (2024)
- [Where LLM Agents Fail and How They can Learn From Failures](https://mlsanity.com/paper/2509.25370/) (2025)
- [Towards Trustworthy GUI Agents: A Survey](https://mlsanity.com/paper/2503.23434/) (2025)
- [BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism](https://mlsanity.com/paper/2505.20660/) (2025)
- [RAFFLES: Reasoning-based Attribution of Faults for LLM Systems](https://mlsanity.com/paper/2509.06822/) (2025)
- [Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation](https://mlsanity.com/paper/2602.02007/) (2026)
- [Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes](https://mlsanity.com/paper/2603.06847/) (2026)
- [Demystifying the Lifecycle of Failures in Platform-Orchestrated Agentic Workflows](https://mlsanity.com/paper/2509.23735/) (2025)
- [Visual Confused Deputy: Exploiting and Defending Perception Failures in Computer-Using Agents](https://mlsanity.com/paper/2603.14707/) (2026)
- [GUIDE: Interpretable GUI Agent Evaluation via Hierarchical Diagnosis](https://mlsanity.com/paper/2604.04399/) (2026)
- [SeeingEye: Agentic Information Flow Unlocks Multimodal Reasoning In Text-only LLMs](https://mlsanity.com/paper/2510.25092/) (2025)

## Built on by (most cited first, 4 of 4)

- [CatchBench: When Can an Agent Failure Be Caught?](https://mlsanity.com/paper/2608.22808/) (2026)
- [Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training](https://mlsanity.com/paper/2609.40111/) (2026)
- [GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution](https://mlsanity.com/paper/2610.00948/) (2026)
- [Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction](https://mlsanity.com/paper/2610.12984/) (2026)

## Abstract (arXiv)

Computer-use agents (CUAs) interact with graphical interfaces through screenshots and low-level mouse and keyboard actions, yet the causal error may precede the terminal failure. We present CUADebug, a framework for localizing root causes in CUA trajectories and guiding re-execution. CUADebug includes a five-category, 30-subtype taxonomy; CUAErrorBench, a benchmark of 204 failed OSWorld trajectories with human root-cause annotations; and CUADebugger, a ReAct-style agent for root-cause analysis (RCA). CUADebugger iteratively selects trajectory steps, inspects paired before/after screenshots and action traces, and submits a structured diagnosis containing the causal step, taxonomy label, grounded evidence, and correction. CUADebugger performs RCA without per-trajectory human intervention; human annotations are used to evaluate RCA predictions and, in controlled re-rollout comparisons, to fix restart points. Task reasoning and control is the largest annotated failure category (110/204). CUADebugger improves L2 and Tag+Step Exact across three debugger backbones on the Claude-agent split; with Gemini 2.5 Pro, Tag+Step Exact rises from 11.1% to 19.4%. Single re-execution improves failure recovery from 13.89% to 29.86% (overall 61.77% to 68.14%); controlled continual re-execution improves it from 12.50% to 25.69% (overall 61.22% to 66.48%). Project page: cuadebug.github.io.