Autoregressive vision language models unify heterogeneous perception tasks but are highly susceptible to compounding errors. On-policy distillation (OPD) bridges the training-inference mismatch by training students on their own rollouts. However, unreliable student predictions, especially early in training, can derail the trajectory and degrade the quality of teacher supervision. While recent interleaved distillation methods allow the teacher to verify and replace student tokens, they primarily rely on rigid ranking metrics rather than exact teacher confidence, and they overlook how intervention decisions can inform token-level supervision. To address this, we introduce Confidence-Aware On-Policy Distillation (CA-OPD), a framework that couples reliable rollout construction with adaptive supervision. CA-OPD utilizes teacher confidence to selectively correct unreliable student transitions, gradually transferring rollout control to the student via a strict-to-relaxed schedule. Crucially, CA-OPD aligns knowledge transfer with these intervention decisions: corrected positions receive direct cross-entropy supervision from the teacher's prediction, while retained positions benefit from the teacher's full predictive distribution. Evaluated in a multi-teacher setting for GUI grounding and optical character recognition, CA-OPD substantially improves the Qwen3.5-0.8B baseline across all six target benchmarks, including gains of $9.50$ points on ScreenSpot-Pro and $6.72$ points on OCRBench-v2 English. Controlled studies further show that the gains depend on intervention placement, progressive rollout control, and intervention-aligned supervision, rather than intervention frequency alone.
Computer-use agents ground natural-language instructions in screenshots to locate interface elements, yet existing benchmarks do not isolate whether models bind relational language to the correct element. We introduce GUI-Primitives, a 994-item benchmark of contrastive instruction pairs over seven spatial relations in graphical user interfaces (left/right, above/below, containment, alignment, proximity, list ordinal, occlusion). Each pair holds the screenshot and anchor fixed while changing the relation expression, so the correct target moves between two designated candidates. Five annotators validate a 196-item subset ($κ= 0.94$ well-formedness; $κ= 0.79$ target selection). Nineteen vision-language models reach at most $32\%$ strict point-in-box accuracy. Because models emit unconstrained coordinates, we classify each prediction by the candidate region it falls within. Predictions fall outside both candidates on $60-92\%$ of items. Conditional on falling within a candidate region, target selection reaches 0.82-0.90 for horizontal position, vertical position, proximity, and list ordinal, but does not differ significantly from 0.50 for containment and occlusion: most failures reflect candidate localization rather than relation understanding. Across ten models, benchmark accuracy correlates with ScreenSpot-Pro accuracy (Spearman $ρ= +0.74$), an exploratory association at this sample size. Marking the two designated candidates raises selection accuracy by 35--57 percentage points, an oracle diagnostic that supplies the candidate set rather than a deployable method. We release the benchmark, predictions, and code.
GUI grounding evaluations that expose UI elements as text metadata often treat high instruction-element embedding similarity as evidence of semantic grounding. Across three mobile and web benchmarks, we show that this interpretation is frequently confounded by visible-label recovery. Lexical baselines remain competitive at top-1, label-poor targets remain weak for text-only methods, and encoder top-1 hits are predictable from lexical rank, candidate-pool size, and label type. We evaluate each action as a same-screen ranking task, comparing five off-the-shelf single-vector encoders with lexical baselines. Encoders recover some lexical misses, but deployable fusion gains are much smaller than target-aware oracle gains. These findings show that embedding-based evaluations can conflate visible-label recovery with semantic GUI grounding. Embedding-based evaluations should therefore report lexical baselines, label-type stratification, and deployable-fusion diagnostics. Our released repository provides analysis scripts and detexted per-step panels: https://github.com/qijia123/lexical-coupling-release.
Current evaluation of computer-use agents is split between long-horizon workflow benchmarks and atomic GUI-grounding tests. This leaves an under-instrumented middle layer: realistic component-centered interactions (e.g., toggle a button set) that are short enough to diagnose and rich enough to capture the burdens of modern interfaces. We present ComponentBench, a benchmark and diagnostic pipeline for component-level evaluation of computer-use agents on modern web UIs. ComponentBench is organized around a library-agnostic ontology of 97 canonical UI components instantiated as 2,910 programmatically verified tasks across widely used component libraries, paired with cleaned human reference trajectories that enable evaluation of both task success and interaction efficiency. Beyond task collection, we introduce a scalable pipeline for auditing realized structural difficulty after implementation and synthesizing structured failure analyses across tasks and component families. Evaluating seven models -- GPT-5.4, Gemini 3 Flash, GPT-5.4 mini, GPT-5 mini, Gemini 3.1 Flash-Lite, Qwen3-VL-235B, and UI-TARS-1.5-7B -- across four observation and action spaces, we show that these design choices critically impact performance. Within a single shared harness, changing only the observation and action space shifts task success by more than 30% for the same model: GPT-5 mini falls from 83.1% with accessibility-tree observations to 48.9% with coordinate-only Pixel control. Moreover, even the fastest configuration takes 3.7x as long as the matched human reference, and spatial manipulations that are trivial for humans continue to challenge current agents.
GUI Visual Grounding is a fundamental capability for GUI agents. Existing models typically freeze their parameters after deployment, limiting their ability to adapt to unseen interfaces. Although recent methods attempt to adapt models via test-time reinforcement learning, they cannot reflect upon failed exploration. To overcome this, we propose a Test-Time Self-Evolving framework that enables models to improve after deployment without human-annotated ground truth. It constructs a closed-loop of Exploration, Evaluation, Reflection, and Internalization. Specifically, the agent first explores unseen interfaces by predicting grounding coordinates for given instructions. To evaluate these explorations, we introduce an MLLM-based Reflector to assess the generated results and provide the corresponding reasoning reflections. To internalize reflection knowledge into the model weights, we propose Reflection-Guided On-Policy Self-Distillation, which translates high-level reasoning into dense token-level supervision via a conditioned self-teacher. Furthermore, we design a Contrastive Calibration method to prevent incorrect auto-regressive prefixes from corrupting the supervisory signals during failed explorations. Extensive experiments across six benchmarks demonstrate our framework's effectiveness, achieving an average accuracy improvement of 7.4% over the base model. To the best of our knowledge, this is the first work to successfully exploit on-policy self-distillation for test-time adaptation in GUI visual grounding. By filling the gap in post-deployment adaptation, our framework completes the self-evolving capability of GUI agents. The code will be released.
Recent graphical user interface (GUI) grounders have significantly advanced single-shot accuracy on standard benchmarks, yet their performance degrades sharply on small targets, densely packed controls and out-of-distribution interfaces. We attribute this gap to a paradigmatic limitation shared by existing approaches: none of them treats a produced coordinate as a hypothesis to be reflected upon and revised under new visual evidence. This manifests as three coupled issues: 1) Lack of post-hoc reflection. The prediction is frozen at the moment of emission, leaving no internal mechanism to challenge or refine it. 2) Visual evidence decoupled from the prediction. The auxiliary visual evidence is gathered to support the upcoming coordinate rather than to scrutinise the one already committed to. 3) Refinement over views, not over predictions. The iterative zoom-in refines the inspected region instead of inheriting a previous coordinate as a spatial prior to be corrected. In this paper, we propose LookAgain, a closed-loop GUI grounder driven by post-prediction visual reflection. LookAgain reformulates grounding as a multi-turn predict-look-again-refine process with two primitives: "locate" posts a coordinate hypothesis, renders a marker on the image and appends a local patch of the predicted region. It anchors the next reasoning step to the previous prediction as a spatial prior; "confirm" accepts or reject the hypothesis and terminates the procedure. We train the LookAgain grounder with SFT on constructed reflective trajectories as a cold start, followed by GRPO with terminal grounding correctness as the sole reward. Extensive experiments show that LookAgain consistently improves performance on both refusal-aware and general GUI grounding benchmarks, achieving state-of-the-art results. Comprehensive ablations further verify the effectiveness of the proposed framework.
GUI agents are shifting from metadata-dependent large language models to purely visual multimodal large language models (MLLMs) that operate directly on screenshots. The core task, GUI grounding, requires translating abstract user instructions into precise element coordinates. This task faces a persistent dual obstacle: conventional grounding models lack the semantic richness to interpret abstract instructions, while end-to-end MLLMs suffer from coordinate hallucinations caused by deficient fine-grained perception. We propose a regression-free framework where a frozen MLLM performs instruction parsing and a dedicated grounding model handles precise localization without learning any coordinate regression. A frozen MLLM first elaborates the abstract instruction into a structured visual description rich in layout cues. These descriptions are then fed to a novel Layout-Aware GUI Grounding Model, which performs regression-free localization by matching against layout-prior candidates, inherently suppressing hallucinations and avoiding expensive fine-tuning. The grounding model is trained with only Text/Icon binary labels, requiring no coordinate regression parameters. On ScreenSpot-Pro, our method achieves over 20% improvement in grounding accuracy over end-to-end systems; on Mind2Web, it raises success rate and element selection rate by more than 15%. These results demonstrate that decoupling instruction understanding from layout-aware localization effectively resolves the core challenges of GUI interaction.
Recent GUI visual grounding models generate screen coordinates as sequences of digit tokens that are parsed into numerical values and mapped to executable clicks. The security implications of this coordinate generation process have been largely overlooked. We observe that each coordinate digit is predicted as a categorical token, yet after parsing, changing a hundreds-place digit by one changes the corresponding numerical coordinate component by 100 units, which can induce a large displacement of the executed click. This observation motivates attack objectives that account for the numerical and place-value structure of coordinate outputs rather than treating them as ordinary text. Moreover, untargeted and targeted attacks impose different success conditions--displacing the click outside the correct region versus into an attacker-specified region--and therefore benefit from different objectives. We propose MissClick, a simple and effective white-box adversarial attack with two goal-specific objectives: MissClick-U maximizes soft-coordinate displacement for untargeted disruption, while MissClick-T minimizes a place-weighted target-digit loss for targeted hijacking. Compared with existing attacks against GUI grounding models on OS-Atlas and UGround across desktop, web, and mobile platforms, MissClick-U achieves untargeted success rates of 75.07\% and 72.93\% (+16.62 and +30.72 pp), and MissClick-T achieves targeted success rates of 44.86\% and 62.67\% (+31.73 and +47.06 pp). Attack objective comparison further shows that soft-coordinate displacement yields the highest untargeted attack success rate, whereas place-weighted target-digit optimization yields the highest targeted attack success rate, revealing distinct objective preferences for the two attack goals.
GUI grounding maps natural-language instructions to click locations and is essential for reliable GUI agents. The task remains difficult on high-resolution, densely populated interfaces because a vision-language model (VLM) may recognize a requested control without locating it precisely enough for interaction. Most existing methods provide various forms of localization assistance, but still rely on a direct click prediction, allowing visual ambiguity or an inaccurate initial estimate to propagate to the final result. In this paper, we introduce GUI-Lens, a coarse-to-fine grounding framework that allows a general-purpose VLM to determine the target through active visual observations. Specifically, GUI-Lens extracts OCR text and detected UI components from the screenshot and presents their positions as coordinate references. Using the instruction, the current view, and these references, the VLM selects the region and scale of the next view, which is cropped and enlarged to provide finer visual details. This process continues over successively focused views until the target is determined. Proposed crops and clicks are checked against the instruction throughout the process, and the final local position is mapped back to the original screen coordinates. Experiments on four GUI grounding benchmarks and three general-purpose VLM backends show that GUI-Lens improves overall grounding accuracy by up to 24.9 percentage points and achieves state-of-the-art performance with GPT-5.5.
Vision-language models often use descriptions of earlier visual states to make decisions about the current scene. When the scene changes, stale language can redirect an otherwise correct visual judgment toward an outdated answer. We study this failure as visual lock-in in a controlled grounding setting where only the verbalized prior varies. Across models, stronger lock-in accompanies smaller changes in the model representation before the final answer. This reversal suggests that lock-in depends not on how far this representation moves, but on how that movement is organized. In models that are harder to correct, prior-induced changes concentrate along a compact set of directions that repeatedly appear across examples. We call these recurrent axes the Prior Directions. They recur on held-out examples, while a descriptive four-model comparison associates greater concentration with stronger lock-in. Controlled interventions show that removing the component aligned with the Prior Directions restores visual grounding, whereas removing an equally large orthogonal component has little effect. Prior control thus arises when prior-induced changes form a coherent and reusable pattern in the representation used to produce the answer. This account explains why the same prior remains revisable in one model yet becomes dominant in another.
MLLM-based GUI grounding methods commonly formulate target localization as autoregressive coordinate generation, enabling models to leverage the strong instruction-following and semantic understanding capabilities of MLLMs. However, this formulation requires the model to retain region-level target evidence while decoding coordinate tokens with the spatial precision demanded by GUI clicking. Our diagnostic analysis reveals that target-region awareness emerges in intermediate decoder layers but is neither retained nor translated into the final coordinate prediction. Existing ZoomIn-style methods address this issue through an external crop-and-rerun pass, which improves localization but increases end-to-end latency and computational cost. To retain the accuracy benefits of two-pass zooming without this extra cost, we propose InnerZoom, a single-forward framework for cross-layer evidence bridging. InnerZoom transforms target-related cues from the original forward pass into a compact cross-layer evidence state, then preserves, refines, and reinjects this state throughout later decoding layers to guide coordinate prediction. Extensive experimental results suggest that InnerZoom-4B achieves state-of-the-art performance on all six GUI grounding benchmarks, obtaining 64.7 on OSWorld-G, 40.2 on UI-Vision, 73.1 on OSWorld-GR, and 87.6 on MMBench-GUI, surpassing the previous best results by 4.1, 3.2, 2.9, and 2.3 points, respectively. Under a controlled 4B setting, InnerZoom improves the same SFT+RL baseline by 5.3 points on average and outperforms two-pass ZoomIn by 1.3 points on average, while reducing end-to-end latency by up to 31.8% and TFLOPs by about 29%. Code and models will be publicly available.
Small ($\sim$2B) GUI-grounding agents are attractive for on-device deployment, accessibility tooling, and low-cost iteration, but at this scale they face two open recipe questions: how to obtain bounding-box training data without expensive human annotation, and how to combine supervised fine-tuning with reinforcement learning. We address both, with the explicit goal of pushing small-model performance rather than scaling up. WinDOM is a $54{,}425$-record grounding corpus harvested by driving an open-source Windows 11 web reimplementation under headless Playwright, with bounding boxes read directly off the DOM and no OCR or human annotation. Self-Family Distillation (SFD) is a single rejection-sampling cold-start parameterised only by the teacher choice: either an EMA of the student (no external model) or a frozen larger same-family teacher. We then treat the saturation depth of the SFD cold-start as an explicit GRPO hyperparameter. On a Qwen3.5-2B student, the under-saturated cold-start is a better GRPO initialiser than the converged one: SFD-4B with Early-init RL gains $+5.4$ OOD-mean ($+3.5$ ScreenSpot-Pro, $+7.0$ OSWorld-G, $+5.8$ ScreenSpot-V2) over the base. The same-size EMA mode lands within roughly one OOD-mean point of the cross-size $4$B variant ($65.2$ vs $66.3$) without an external teacher.
Divake Kumar, Sina Tayebati, Devashri Naik +5cs.LG cs.AI cs.CL cs.CV
Computer-use agents turn vision-language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejection, calibration, miss-severity ranking, and spatial safety regions. Yet evidence on post-hoc uncertainty quantification (UQ) for these agents is fragmented across isolated model and dataset pairs, leaving it unclear whether UQ rankings stay stable when the agent, benchmark, or observable interface changes. We present Argus, a cross-regime benchmark for post-hoc UQ in single-step executable GUI grounding: a 27-method open-weight matrix over 4 VLM agents and 4 datasets, plus an 8-method closed-source matrix across 3 frontier vendors where logits, hidden states, and attention maps are unavailable. Evaluated methods span logit-based scores, sampling and consistency measures, hidden-state and density estimators (Mahalanobis, SAPLMA), attention-based scores, P(True) and verbalised-confidence prompting, and split-conformal prediction. The main finding is selective transfer: UQ rankings are stable across datasets for a fixed model, but degrade across model classes and observable interfaces. Hidden-state and density methods are the most stable open-weight family, while CoCoA-1MCA, Focus, sampling-based scores, and verbalised self-assessment win in specific regimes. Within-model ranking transfer is strong (Spearman rho up to 0.969), but cross-tier transfer to closed-source vendors averages only +0.08, so closed-source UQ should be reranked on the target rather than extrapolated. Conformal click regions show score-level discrimination is not enough for deployment: locally weighted disks shrink radii by 40-60% when the plug-in UQ is calibrated, but coverage degrades under calibration-test or interface mismatch. We release per-item records, calibration/test splits, UQ scores, and analysis scripts for regime-aware UQ selection in GUI agents.
Graphical user interface (GUI) grounding requires vision-language models (VLMs) to identify small target elements in high-resolution screenshots and predict precise screen coordinates. On-policy self-distillation (OPSD) is a promising post-training approach for this coordinate-sensitive task, since it provides dense token-level teacher signals beyond hard coordinate labels. However, naive OPSD is not well suited to GUI grounding: OPSD evaluates the teacher on student-generated prefixes, the quality of coordinate-token teacher signals can degrade when the prefix has already deviated from the target coordinate, leading to unreliable teacher signal. To mitigate this, We propose quality-aware self-distillation for VLM-based GUI grounding, which improves coordinate-token teacher-signal quality through soft correctness-aware gating and teacher-probability scaling. The soft correctness-aware gate checks whether the teacher's current coordinate-token prediction can still be completed into the ground-truth box under the student-generated prefix. If not, the corresponding teacher signal is down-weighted. Teacher-probability scaling then uses the teacher's confidence as a lightweight factor to further calibrate the strength of the gated supervision. A key empirical finding is that neither component alone improves overall performance, whereas combining them consistently improves performance. This suggests that the two mechanisms play complementary roles: correctness-aware gating suppresses unreliable coordinate-token supervision, while teacher-probability scaling calibrates the strength of the remaining signals. Experiments across six GUI grounding benchmarks show that our method consistently improves the base model and outperforms strong baselines.
When applying Group Relative Policy Optimization (GRPO) for GUI Grounding, rollouts are sampled from a single screenshot view; groups often become either all failures on difficult instances or all successes on easy ones, yielding no useful relative advantage. We propose VISTA (View-Consistent Self-Verified Training), a GRPO-based training framework that constructs each comparison group from multiple target-preserving views of the same GUI instance.Each view is generated by a crop that keeps the target element visible and remaps its box exactly, so model rollouts are compared across semantically equivalent but geometrically different inputs. To stabilize short coordinate generation without turning reinforcement learning into unconditional imitation, VISTA further adds a self-verified cross-view anchor: an oracle answer optimized with an advantage-weighted loss, excluded from the group baseline and activated only when the model has produced a maximum-reward rollout. Across five GUI-grounding benchmarks and multiple Qwen backbones, VISTA consistently improves grounding accuracy.On ScreenSpot-Pro, it raises Qwen3-VL 4B/8B/30B-A3B from 55.5/52.7/53.7 to 63.4/65.8/67.0. Robustness analyses further show higher worst-view accuracy and lower prediction flip rates.
Jaewoo Lee, Zaid Khan, Archiki Prasad +7cs.AI cs.CL cs.CV
Various test-time interventions for Computer Use Agents (CUAs), including critic models, have been developed to improve performance through pre-execution action evaluation in complex Graphical User Interface (GUI) environments. However, existing critics suffer from two key limitations: they (1) focus primarily on short-sighted decision loops (e.g., forgetting earlier actions) and (2) lack the visual grounding needed to detect flawed actions (e.g., clicking wrong UI elements). To address these, we introduce HiViG, a History-aware Visually Grounded test-time framework, built around a multimodal critic trained on real GUI trajectories to abstract past interactions into a compact record and to evaluate actions with visual grounding. At test time, HiViG integrates the critic into the policy decision loop to provide macro-action history, which summarizes the policy's completed achievements, and visually grounded critique, which verifies raw execution coordinates against the current screenshot to intercept errors before execution. Across web, mobile, and desktop benchmarks, HiViG consistently outperforms existing scalar and verbal critics, improving average success rates over the strongest baseline by 5.8% for Qwen3-VL-32B and 9.0% for Gemini-3-Flash, and demonstrates strong cross-platform generalization. Ablations show that macro-action history mitigates short-sighted planning and visually grounded critique reduces execution errors, with both components being critical for test-time scaling in long-horizon GUI tasks.
Vision-Language Models (VLMs) have enabled autonomous GUI agents that translate natural language instructions into executable screen coordinates. However, grounding performance degrades in high-resolution interfaces, where dense layouts and small interactive elements expose a resolution gap between modern displays and model input constraints. Existing zoom-in strategies rely on fixed anchors, heuristic grids, or reinforcement learning, lacking a principled mechanism to adaptively determine where refinement is needed and how much spatial uncertainty should be explored. We propose AutoFocus, a training-free, uncertainty-aware active visual search framework for GUI grounding. Our key insight is that token-level perplexity in coordinate generation naturally reflects spatial uncertainty. Rather than committing to a single prediction, AutoFocus samples multiple coordinate hypotheses and converts their axial perplexities into an anisotropic gaussian spatial probability field, explicitly modeling directional uncertainty. Based on this field, we generate global and local region proposals and introduce Shape-Aware Zooming to balance tight localization with contextual preservation. A visual prompt-based aggregation step then selects the most consistent prediction via structured comparison. Extensive experiments on ScreenSpot-Pro and ScreenSpot-V2 demonstrate consistent improvements across both general-purpose and GUI-specialized VLMs.
Fengxian Ji, Jingpu Yang, Zirui Song +5cs.CV cs.DB
Despite the rapid progress of large vision-language models (LVLMs), fine-grained, state-conditioned GUI interaction remains challenging. Current evaluations offer limited coverage, imprecise target-state definitions, and an overreliance on final-task success, obscuring where and why agents fail. To address this gap, we introduce \textbf{FineState-Bench}, a benchmark that evaluates whether an agent can correctly ground an instruction to the intended UI control and reach the exact target state. FineState-Bench comprises 2,209 instances across desktop, web, and mobile platforms, spanning four interaction families and 23 UI component types, with each instance explicitly specifying an exact target state for fine-grained state setting. We further propose \textit{FineState-Metrics}, a four-stage diagnostic pipeline with stage-wise success rates: Localization Success Rate (SR@Loc), Interaction Success Rate (SR@Int), Exact State Success Rate at Locate (ES-SR@Loc), and Exact State Success Rate at Interact (ES-SR@Int), and a plug-and-play \textit{Visual Diagnostic Assistant} (VDA) that generates a Description and a bounding-box Localization Hint to diagnose visual grounding reason via controlled w/ vs.\ w/o comparisons. On FineState-Bench, exact goal-state success remains low: ES-SR@Int peaks at 32.8\% on Web and 22.8\% on average across platforms. With VDA localization hints, Gemini-2.5-Flash gains +14.9 ES-SR@Int points, suggesting substantial headroom from improved visual grounding, yet overall accuracy is still insufficient for reliable fine-grained state-conditioned interaction \href{https://github.com/FengxianJi/FineState-Bench}{Github.}
Graphical User Interface (GUI) element grounding (precisely locating elements on screenshots based on natural language instructions) is fundamental for agents interacting with GUIs. Deploying this capability directly on resource-constrained devices like mobile phones is increasingly critical for GUI agents requiring low latency. However, this goal faces a significant challenge, as current visual grounding methods typically employ large vision-language model (VLM) (more than 2.5B parameters), making them impractical for on-device execution due to memory and computational constraints. To address this, this paper introduces GoClick, a lightweight GUI element grounding VLM with only 230M parameters that achieves excellent visual grounding accuracy, even on par with significantly larger models. Simply downsizing existing decoder-only VLMs is a straightforward way to design a lightweight model, but our experiments reveal that this approach yields suboptimal results. Instead, we select an encoder-decoder architecture, which outperforms decoder-only alternatives at small parameter scales for GUI grounding tasks. Additionally, the limited capacity of small VLMs encourages us to develop a Progressive Data Refinement pipeline that utilizes task type filtering and data ratio adjustment to extract a high-quality 3.8M-sample core set from a 10.8M raw dataset. Training GoClick using this core set brings notable grounding accuracy gains. Our experiments show that GoClick excels on multiple GUI element grounding benchmarks while maintaining a small size and high inference speed. GoClick also enhances GUI agent performance when integrated into a device-cloud collaboration framework, where GoClick helps cloud-based task planners perform precise element localization and achieve higher success rates. We hope our method serves as a meaningful exploration within the GUI agent community.