On the Reliability of Computer Use Agents

• URL: http://arxiv.org/abs/2604.17849v1
• Date: Mon, 20 Apr 2026 05:59:04 GMT
• Title: On the Reliability of Computer Use Agents
• Abstract summary: We study the sources of unreliability in computer-use agents through three factors.<n> reliability depends on both how tasks are specified and how agent behavior varies across executions.
• Score: 47.20065484006984
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Computer-use agents have rapidly improved on real-world tasks such as web navigation, desktop automation, and software interaction, in some cases surpassing human performance. Yet even when the task and model are unchanged, an agent that succeeds once may fail on a repeated execution of the same task. This raises a fundamental question: if an agent can succeed at a task once, what prevents it from doing so reliably? In this work, we study the sources of unreliability in computer-use agents through three factors: stochasticity during execution, ambiguity in task specification, and variability in agent behavior. We analyze these factors on OSWorld using repeated executions of the same task together with paired statistical tests that capture task-level changes across settings. Our analysis shows that reliability depends on both how tasks are specified and how agent behavior varies across executions. These findings suggest the need to evaluate agents under repeated execution, to allow agents to resolve task ambiguity through interaction, and to favor strategies that remain stable across runs.

Related papers

• Measuring Cross-Task Behavioral Consistency in Language Model Agents [0.0]
  We argue that behavioral consistency across tasks is a distinct and measurable property.<n>We introduce the Behavioral Consistency Metric (BCM) to quantify it.<n>We find that consistency is not reducible to success rate, since systems with comparable success can differ sharply in consistency.
  arXiv  Detail & Related papers  (2026-07-31T18:37:11Z)
• AgentAbstain: Do LLM Agents Know When Not to Act? [19.223843408018997]
  Existing evaluations mostly focus on task success rather than whether agents know when to abstain.<n>We present the first systematic evaluation framework for agentic abstention: the calibrated ability of tool-using LLM agents to recognize when not to act.<n>AgentAbstain is a paired-task benchmark built on an agent-native taxonomy of 8 abstention scenarios across pre-execution reasoning and runtime discovery.
  arXiv  Detail & Related papers  (2026-07-11T00:57:36Z)
• From Question Answering to Task Completion: A Survey on Agent System and Harness Design [67.8241530947325]
  This survey examines LLM-based agents through a model-harness lens.<n>We first clarify the functional definition of agents and the implementation view of an LLM-based agent as a foundation model and an execution harness.<n>We then analyze the limits of model-centric scaling, trace four paradigms of agent engineering, and decompose the execution harness into six coupled runtime responsibilities.
  arXiv  Detail & Related papers  (2026-06-14T05:40:16Z)
• AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions [78.49000936275773]
  We introduce AgentHijack, a benchmark designed to evaluate the robustness of computer-use agents under common corruptions.<n>We evaluate a variety of desktop tasks that utilize MLLM-based agents and discover that even minor instances of corruption can result in substantial performance degradation.<n>We propose AgentHijack-Agent, a framework that integrates an action generator with enhanced grounding capabilities and an onlooker responsible for behavior summarization and environment checking.
  arXiv  Detail & Related papers  (2026-05-25T11:09:22Z)
• AgentSearchBench: A Benchmark for AI Agent Search in the Wild [21.739444037726418]
  We introduce AgentSearchBench, a large-scale benchmark for agent search in the wild.<n>The benchmark formalizes agent search as retrieval and reranking problems under both executable task queries and high-level task descriptions.<n>We show that lightweight behavioral signals, including execution-aware probing, can substantially improve ranking quality.
  arXiv  Detail & Related papers  (2026-04-24T10:53:54Z)
• Agent Mentor: Framing Agent Knowledge through Semantic Trajectory Analysis [4.365760422569902]
  We introduce an analytics pipeline implemented as part of the Agent Mentor open-source library.<n>It monitors and incrementally adapts the system prompts defining another agent's behavior.<n>The pipeline improves performance by systematically injecting corrective instructions into the agent's knowledge.
  arXiv  Detail & Related papers  (2026-04-12T08:02:54Z)
• Persuasion Propagation in LLM Agents [23.64887423923855]
  We study how belief-level intervention can influence downstream task behavior.<n>Across web research and coding tasks, we find that on-the-fly persuasion induces weak and inconsistent behavioral effects.<n>When the belief state is explicitly specified at task time, belief-prefilled agents conduct on average 26.9% fewer searches and visit 16.9% fewer unique sources than neutral-prefilled agents.
  arXiv  Detail & Related papers  (2026-01-31T18:33:14Z)
• The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [63.61358761489141]
  Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering.<n>We propose a novel framework for textbfgeneral agentic attribution, designed to identify the internal factors driving agent actions regardless of the task outcome.<n>We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias.
  arXiv  Detail & Related papers  (2026-01-21T15:22:21Z)
• Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories [10.751728274263536]
  This paper presents an empirical study of agent trajectories, namely the execution traces capturing the steps agents take when attempting to resolve software issues.<n>We analyse trajectories from three state-of-the-art code agents (OpenHands, SWE-agent, and Prometheus) on the SWE-Bench benchmark, examining both successful and failed attempts.
  arXiv  Detail & Related papers  (2025-10-31T18:58:13Z)
• Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents [58.00130492861884]
  TraitBasis is a lightweight, model-agnostic method for systematically stress testing AI agents.<n>TraitBasis learns directions in activation space corresponding to steerable user traits.<n>We observe on average a 2%-30% performance degradation on $tau$-Trait across frontier models.
  arXiv  Detail & Related papers  (2025-10-06T05:03:57Z)
• XAgents: A Unified Framework for Multi-Agent Cooperation via IF-THEN Rules and Multipolar Task Processing Graph [14.273739638741139]
  XAgents is a unified multi-agent cooperative framework built on a multipolar task processing graph and IF-THEN rules.<n>XAgents consistently surpasses state-of-the-art single-agent and multi-agent approaches in both knowledge-typed and logic-typed question-answering tasks.
  arXiv  Detail & Related papers  (2025-09-12T08:40:58Z)
• Preventing Rogue Agents Improves Multi-Agent Collaboration [21.955058255432974]
  We propose to monitor agents during action prediction and intervene when a future error is likely to occur.<n>Experiments on WhoDunitEnv, code generation tasks and the GovSim environment for resource sustainability show that our approach leads to substantial performance gains.
  arXiv  Detail & Related papers  (2025-02-09T18:35:08Z)
• On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents [58.79302663733703]
  Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents.<n>The impact of clumsy or even malicious agents--those who frequently make errors in their tasks--on the overall performance of the system remains underexplored.<n>This paper investigates what is the resilience of various system structures under faulty agents on different downstream tasks.
  arXiv  Detail & Related papers  (2024-08-02T03:25:20Z)
• Explaining Reinforcement Learning Policies through Counterfactual Trajectories [147.7246109100945]
  A human developer must validate that an RL agent will perform well at test-time. Our method conveys how the agent performs under distribution shifts by showing the agent's behavior across a wider trajectory distribution. In a user study, we demonstrate that our method enables users to score better than baseline methods on one of two agent validation tasks.
  arXiv  Detail & Related papers  (2022-01-29T00:52:37Z)

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.