Evaluating language-guided mobile agents has recently shifted from rule-based to model-based approaches to achieve scalable and automated assessments. However, existing holistic evaluation paradigms process entire trajectories at once, leading to substantial context overload. Moreover, they primarily focus on task completion while overlooking operational safety. To address these limitations, we introduce CRATE, a novel two-stage VLM-as-judge framework for automated mobile agent evaluation that is compatible with both open- and closed-source models. Leveraging a step-level consequence reasoning mechanism, CRATE independently extracts task-relevant visual clues and infers action-conditioned state changes at each step. The resulting step-level textual evidence is then synthesized through trajectory-level aggregation to deliver an evidence-grounded evaluation of task completion. Building upon this evaluation scheme, we further extend CRATE to CRATE-S for operational safety assessment. Extensive experiments validate the effectiveness and robustness of both CRATE and CRATE-S. Powered by Qwen2.5-VL-72B-Instruct, CRATE achieves an F1-score of 0.833 on AndroidWorld (outperforming SPA-Bench by 20%), while CRATE-S reaches an F1-score of 0.697 on MobileRisk, demonstrating strong alignment with benchmark ground truths. Code is available at https://anonymous.4open.science/r/CRATE-D580.
Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API. We define behavioral safety and introduce ActBench, a self-evolving benchmark that evaluates such behavior risk from execution trajectories rather than final responses. Each case pairs a benign task with an adversarial variant that preserves its instruction, configuration, initial state, rating model, and trusted records while injecting a task-reachable payload. ActBench contains 600 cases from 213 scenarios, spanning 15 risk behaviors, six execution spaces, and 48 web-service APIs.To move beyond static payloads, we propose a reward-guided beam search method that jointly optimizes attack effectiveness and task utility, while reflection diagnoses failed execution checkpoint and guides payload revision. Besides, we propose a dual evidence verification mechanism that verifies agent execution safety and utility through log evidence and LLM-based trajectory evidence.We evaluate 15 LLMs and 6 open-source cowork agents over 24,000 trajectories. Under a fixed harness, attack success rates ranges from 10.1% to 94.4% across models, while under a fixed base model, they range from 73.7% to 94.4% across agents.These results show greater variation across models than agent harness, while attacks remain highly successful across all tested harnesses.Our benchmark is released at: https://github.com/zjuicsr/ActBench.
Hwanhee Kim, Jaehyun Jang, Seungmin Cha +3cs.RO cs.CV
Vision-based embodied agents executing multi-step natural language instructions require feedback mechanisms that assess task progress over complete trajectories. Conventional approaches based on final-frame matching or continuous embedding similarity may overlook intermediate transitions that are necessary for determining whether an instruction has been completed. We propose ALVA (Action- and Language-Conditioned Video Assessment), a trajectory evaluator that conditions its assessment on visual observations, the executed action sequence, and the natural language instruction. The method uses a pre-trained vision-language model (VLM) in two stages: it first summarizes frame-to-frame visual transitions conditioned on the executed actions and then assesses the generated summary with respect to the instruction to produce a discrete trajectory-level progress score. In simulated 3D household environments, ALVA exhibits a conservative assessment pattern with near-zero false-positive rates. When used as terminal feedback for closed-loop policy optimization, it provides more effective feedback than the evaluated static image and embedding-based visual baselines and reduces the performance gap to a ground-truth oracle. These results support action- and language-conditioned video assessment as an interpretable feedback mechanism for the evaluated simulated embodied-control tasks.
Qiushi Sun, Kanzhi Cheng, Yian Wang +20cs.AI cs.CL cs.CV
Computer-using agents (CUAs) are advancing rapidly across the digital world. A CUA trajectory records the agent's actions, states, and reasoning. Verifying whether it fulfilled the task instruction is central to CUA evaluation, data curation, and reinforcement learning. Neither human-written verifiers nor human annotators can provide such verification at scale, so the field increasingly turns to vision-language models (VLMs) as judges of CUA trajectories. But a fundamental question has long gone unexamined: are these VLM judges reliable enough? To study it systematically, we introduce OSReward, a realistic, high-quality benchmark that evaluates VLM judges on CUA trajectories. The trajectories come from diverse agent backbones executing human-verified instructions across platforms, then rigorously labeled with ground-truth verdicts through multi-stage human annotation. Building on it, we derive OSReward-Hard, a challenge set concentrating genuinely hard cases, and OSReward-Multi for fine-grained efficiency and alignment scoring. The most comprehensive evaluation of VLM judges to date finds even state-of-the-art models fall short of an ideal judge, sharing a systematic leniency bias that mislabels failed runs as successes. The few reliable enough to trust are too expensive to run at scale, while affordable open models trail far behind. To close this gap, we construct and release OS-Shepherd-100K, an open corpus of reasoning-annotated trajectory judgments for the CUA community. On it, we train OS-Shepherd (9B and 35B), open reward models that supply low-cost, stable, and reliable reward signals, matching commercial judges at 30-60% lower cost than the frontier. Extensive analyses further inform the design of reliable CUA reward at scale. Our code, benchmark, dataset, and model checkpoints are available at https://os-copilot.github.io/OSReward-Home/.
We present AgentLens, a production-assessed benchmark for interactive code agents. Most code-agent benchmarks reduce a run to a single bit -- did the task pass? -- but the people who actually use these agents experience the entire trajectory: how the agent follows instructions, uses its tools, verifies its own work, recovers from mistakes, and talks to them along the way. AgentLens evaluates that whole trajectory. It pairs formal verification, where an objective check exists, with LLM-written trajectory reviews and side-by-side comparisons, so that each run yields a readable explanation of why the score is what it is. This makes AgentLens useful for more than ranking models: we use it to diagnose model behavior, compare successive versions of our own agent, and catch product regressions in a nightly evaluation pipeline. We release the benchmark as open source at https://github.com/agent-lens/agent-lens-bench.
Reward models play a pivotal role in reinforcement learning (RL) and multi-modal trajectory selection for autonomous driving. However, acquiring such rewards typically relies on hand-crafted rule-based objectives or perception ground truth, which hinders generalization for data-scaling. While Vision-Language Models (VLMs) have demonstrated feasibility as reward models in other domains, their effectiveness in driving tasks remains underexplored. In this work, we bridge this gap by (1) introducing DriveReward, a reasoning trajectory evaluation dataset rigorously labeled via temporally-grounded visual guidance, and augmented with counterfactual driving behaviors., (2) alongside a specialized Vision-Language Reward Model. To address the scarcity of failure cases in conventional datasets, we propose a counterfactual data annotation scheme to construct cases encompassing diverse driving styles and erroneous behaviors. Evaluations on our proposed benchmark reveal that even leading open-source and proprietary VLMs fail to excel across all tasks, highlighting significant room for improvement in existing models. Building on these findings, we subsequently tailor a specialized 1B reward model that outperforms larger VLMs on task-specific reward alignment. Finally, we validate our reward model's effectiveness by integrating it into RL finetuning and multi-modal trajectory scoring across multiple baselines, achieving performance comparable to rule-based reward calculations in both open-loop and closed-loop evaluation.