How Benchmarks Mis-Score Computer-Use Agents

• URL: http://arxiv.org/abs/2607.28367v1
• Date: Thu, 30 Jul 2026 15:29:42 GMT
• Title: How Benchmarks Mis-Score Computer-Use Agents
• Abstract summary: We organize problems into a reliability framework spanning task construction, trajectory observation, scoring, and reporting.<n>We audit 150 public failure-scored trajectories from five web, enterprise-workflow, and desktop-control benchmarks.<n>For genuine failures, a three-tier diagnostic taxonomy shows that verification/feedback and planning failures dominate execution/grounding errors.
• Score: 12.455546989850227
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Computer-use agents (CUA) are being deployed to browse the web and operate desktop software, yet their benchmark scores are still commonly produced by brittle scripted oracles. A score is the output of a pipeline in which tasks can be stale, trajectories can omit decisive visual evidence, evaluators can reject valid alternatives, and aggregate reports can hide the cause of failure. We organize these problems into a reliability framework spanning task construction, trajectory observation, scoring, and reporting. We then audit 150 public failure-scored trajectories from five web, enterprise-workflow, and desktop-control benchmarks, find that 15.3\% of FAIL verdicts are wrong: 10.7\% are evaluator false negatives and 4.7\% are broken tasks. For genuine failures, a three-tier diagnostic taxonomy shows that verification/feedback and planning failures dominate execution/grounding errors, while a single scalar success rate can not explain. We connect these findings to newer long-horizon CUA benchmarks and derive stage-specific design rules for CUA evaluation.

Related papers

• Trace Integrity for LLM Data Agents: A Vision for Auditable Structured Reasoning in Real-World Systems [0.519554837386174]
  In structured-data tasks, a benchmark-correct answer can be produced by an invalid trace.<n>This paper introduces Trace Integrity, a deployment reliability criterion for evaluating whether the computation recorded behind an answer is explicit.<n>We also introduce CAIT (Correct Answer / Invalid Trace) Rate, which measures how often answer-only evaluation counts computationally unsupported outputs as successes.
  arXiv  Detail & Related papers  (2026-08-26T17:15:24Z)
• ClawProBench: Trace-Aware Evaluation of AI Agents with Runtime Coverage and Frozen Workplace-Style Holdouts [0.0]
  Agent benchmarks often evaluate only final answers even when agents run on stateful runtimes.<n>We present ClawProBench, a trace-aware benchmark for runtime-native agent evaluation instantiated on OpenClaw.
  arXiv  Detail & Related papers  (2026-08-23T17:09:02Z)
• Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions? [3.9561795512466413]
  Current benchmarks primarily measure end-task success or single-frame grounding.<n>This is difficult because inference, remote input, app rendering, and screenshot capture are asynchronous.<n>We introduce Desktop-Delta Bench (DDB), an offline step-level benchmark with 2,013 human-verified instances from novel, multi-app Linux trajectories.
  arXiv  Detail & Related papers  (2026-07-28T17:49:51Z)
• Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories [51.22051230894794]
  Evaluation based on final answers shows whether an agent succeeds, but not which parts of the trajectory make the answer unreliable.<n>We collect 2,790 real trajectories from two agent frameworks, three backbone models, and three benchmarks, convert raw logs into semantic spans, and annotate harmful error spans through expert review.<n>We propose DRIFT, a claim-centric auditing framework that tracks agent claims, checks their support in trajectory evidence, and marks spans where unsupported or conflicting claims affect the answer path.
  arXiv  Detail & Related papers  (2026-06-01T10:50:26Z)
• ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents [4.908588441456849]
  ProcCtrlBench is a benchmark for execution-process evaluation in LLM coding agents.<n>It organizes recurrent execution defects into a reusable ontology covering 11 defect types in 4 categories.<n>It evaluates agent trajectories through standardized process evidence rather than final outcomes alone.
  arXiv  Detail & Related papers  (2026-05-18T08:34:48Z)
• Can Agent Benchmarks Support Their Scores? Evidence-Supported Bounds for Interactive-Agent Evaluation [8.049844623361725]
  Interactive agent benchmarks map an agent run to a binary outcome through outcome checks.<n>These checks rely on surface level signals or fail to capture the agent's actual action path.<n>We introduce an outcome evidence reporting layer for existing benchmarks.
  arXiv  Detail & Related papers  (2026-05-11T12:20:15Z)
• Evaluating Agentic AI in the Wild: Failure Modes, Drift Patterns, and a Production Evaluation Framework [0.0]
  We present a taxonomy of seven failure modes unique to production agentic systems.<n>Standard metrics fail to detect four of the seven failure modes entirely.<n>We propose PAEF, a five-dimension evaluation framework with an open-source reference implementation.
  arXiv  Detail & Related papers  (2026-05-02T21:02:08Z)
• When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents [50.5814495434565]
  This work makes the first effort to define and study misaligned action detection in computer-use agents (CUAs)<n>We identify three common categories in real-world CUA deployment and construct MisActBench, a benchmark of realistic trajectories with human-annotated, action-level alignment labels.<n>We propose DeAction, a practical and universal guardrail that detects misaligned actions before execution and iteratively corrects them through structured feedback.
  arXiv  Detail & Related papers  (2026-02-09T18:41:15Z)
• Process-Level Trajectory Evaluation for Environment Configuration in Software Engineering Agents [71.85020581835042]
  Large language model-based agents show promise for software engineering, but environment configuration remains a bottleneck.<n>Existing benchmarks assess only end-to-end build/test success, obscuring where and why agents succeed or fail.<n>We introduce Enconda-bench, which provides process-level trajectory assessment of fine-grained agent capabilities during environment setup-planning.
  arXiv  Detail & Related papers  (2025-10-29T16:59:07Z)
• AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories [61.38499597241457]
  We propose AgentRewardBench, the first benchmark to assess the effectiveness of LLM judges for evaluating web agents.<n>Using our benchmark, we evaluate 12 LLM judges and find that no single LLM excels across all benchmarks.<n>We also find that the rule-based evaluation used by common benchmarks tends to underreport the success rate of web agents.
  arXiv  Detail & Related papers  (2025-04-11T19:49:22Z)
• Do Large Language Model Benchmarks Test Reliability? [66.1783478365998]
  We investigate how well current benchmarks quantify model reliability.<n>Motivated by this gap in the evaluation of reliability, we propose the concept of so-called platinum benchmarks.<n>We evaluate a wide range of models on these platinum benchmarks and find that, indeed, frontier LLMs still exhibit failures on simple tasks.
  arXiv  Detail & Related papers  (2025-02-05T18:58:19Z)
• PULL: Reactive Log Anomaly Detection Based On Iterative PU Learning [58.85063149619348]
  We propose PULL, an iterative log analysis method for reactive anomaly detection based on estimated failure time windows. Our evaluation shows that PULL consistently outperforms ten benchmark baselines across three different datasets.
  arXiv  Detail & Related papers  (2023-01-25T16:34:43Z)

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.