已审阅并标注「无需训练的方法」的研究与资产。
条目依据已审阅标签归类，同一主题不表示资源之间存在依赖关系。日期保留来源精度，注释保留原语言。
Studies repeated rejected edits while optimizing a screenshot-only GUI agent, contrasting static probes with reached loop states and testing how rejection wording changes subsequent edit proposals.
Introduces ExpActivator, which matches the current GUI state to relevant historical states before supplying past actions as guidance. A separate activation rule decides whether a recurring user intent is warranted by the current time and situation or should be withheld.
EvoSkill-GUI revises reusable skill files from execution feedback through an executor–critic loop. It studies how training-free updates to localization, recovery and procedure information help subsequent mobile and desktop tasks.
TRACE orders screenshot evidence for monotonic visual-token reduction using layout priors, instruction relevance and feature novelty. Spatial token reserves and incremental KV contraction aim to preserve useful evidence for future GUI targets without repeatedly encoding retired frames.
An online skill-evolution framework turns GUI interaction traces and evaluator feedback into a versioned library of reusable procedures without updating model parameters. Controlled OSWorld comparisons examine both the benefits of shared procedural memory and its domain-dependent instability under repeated revision.
Introduces LocalLSTC, a training-free control architecture that maintains persistent task state and uses it to form short execution commitments. Outcomes feed back into that state for progress checks, recovery, and termination in locally deployed desktop agents.
Uses failed computer-use trajectories to diagnose failure modes and generate inference-time agent code patches, with light human verification. An OSWorld study evaluates this failure-driven improvement loop without additional model training.
The Agent-Computer Observation Interface separates continuous perception from discrete computer actions using captured frames, audio transcription and persistent visual narration. DynaCU-Bench tests these components on dynamic browser tasks and static controls, with model-specific ablations showing that additional observations can also hurt.
WebChallenger builds a hierarchical DOM-derived page representation for selective observation, reusable site maps and compound actions. The framework combines these mechanisms without model fine-tuning and evaluates generalization across multiple web-agent benchmarks.
STaR-KV compresses GUI-agent KV caches by calibrating visual-token importance across attention subspaces and interaction time. Its training-free scoring combines spatial specialization, temporal redundancy and an adaptive temperature, evaluated at matched cache budgets.
DRS-GUI searches screenshot regions through focus, shift and scatter operations selected by a tree-search planner. A region-quality reward guides this training-free perceptual search before final GUI grounding.
Re-Prefill adds an attention-guided second prefill pass that revisits candidate screen regions before coordinate generation. The study evaluates this training-free intervention across GUI-grounding models and benchmarks.
Presents AutoFocus, a training-free grounding method that turns sampled coordinates and token uncertainty into spatial region proposals. Shape-aware crops and visual comparison select a target while retaining surrounding interface context.
Introduces UI-Zoomer, a training-free grounding method that uses candidate agreement and token confidence to decide when to crop and retry. Prediction variance determines a separate crop radius for each uncertain interface target.
PixelPrune removes pixel-redundant patches before the vision encoder, reducing both encoding and downstream language-model work. The training-free method evaluates lossless and controlled-lossy compression on document and GUI tasks.
GUIDE retrieves relevant software tutorials through subtitle-based video search, then infers planning and grounding knowledge from consecutive annotated keyframes. It inserts that knowledge into existing GUI-agent modules without parameter updates and evaluates the plug-in on OSWorld.
Presents ZoomUI, a training-free grounding method that expresses instructions as visual element descriptions and uses model attention to zoom progressively into relevant interface regions. Evaluation examines instruction-to-element localization on GUI benchmarks.
Trifuse combines attention-based localization with OCR text cues and icon captions to ground GUI instructions. Its fusion procedure favors cross-modal agreement and sharp location peaks, and is evaluated without task-specific fine-tuning.
Darwinian Memory splits GUI trajectories into reusable units and updates the memory by retaining useful paths and pruning poor ones. It evaluates this training-free memory mechanism on long multi-application tasks.
MVP addresses unstable GUI coordinates by predicting across several attention-guided cropped views. It clusters the resulting coordinates and selects the densest cluster centroid, evaluating this training-free inference method across grounding models.
ZoomClick uses repeated zooming and context adjustment to improve GUI grounding without training. The paper studies zoom depth, crop sizes, and related choices and introduces GUIZoom-Bench to evaluate how grounding models respond to zoomed views.
Chain-of-Ground uses iterative visual reasoning and reference feedback to refine GUI localization without additional training. It evaluates on ScreenSpot-Pro and introduces TPanel-UI to probe grounding on industrial control panels with visual distortions.
GUI-KV compresses vision-language agents’ attention caches using visual-token saliency and redundancy between screenshot frames. The method requires no retraining and evaluates how cache budgets affect GUI action accuracy and computational cost.
Studies the gap between latent visual grounding and explicit coordinate output in general vision-language models. Three zero-shot methods add axes, grids, or labeled intersections to GUI screenshots so models can express spatial locations without fine-tuning.
GUI-RC aggregates multiple grounding predictions into spatial voting grids to choose a consensus region. GUI-RCPO then turns agreement with that region into a reward for test-time policy updates on unlabeled GUI screenshots.
Introduces LaSM, a training-free defense that selectively scales attention and MLP components to improve alignment with task-relevant screen regions. It evaluates the approach against pop-up-based GUI injection attacks.
Introduces a finer-grained taxonomy of GUI localization errors and a logit-based Peak Sharpness Score for analyzing coordinate-prediction uncertainty. A context-aware cropping method refines the visual input without retraining the grounding model.
Introduces recursive criticism and improvement prompting for language-model agents performing computer tasks, evaluated on MiniWoB++ with a small number of demonstrations per task.
Studies few-shot prompting of a single language model for four mobile-UI interaction tasks, aiming to support conversational interface use without a separate trained model for each task.
A MiniWoB++ agent that uses explicit and implicit recursive criticism-and-improvement prompts to refine action plans and ground actions to browser state.
Grounding and evaluation code that aggregates a pretrained vision-language model’s attention maps to localize requested interface elements without fine-tuning.
通过主题导出清单获取完整记录和证据。克隆目录后，可将主题记录直接交给标准 RAG 与引用导出工具。
