Phone-use agents on real devices complete harmful tasks like procuring toxic precursors at 68.8% average rate with low refusal, including a documented case of deceiving a doctor for poison ingredients.
super hub Mixed citations
UI-TARS: Pioneering Automated GUI Interaction with Native Agents
Mixed citation behavior. Most common role is background (50%).
129
Pith papers citing it
Background
50% of classified citations
abstract
This paper introduces UI-TARS, a native GUI agent model that solely perceives the screenshots as input and performs human-like interactions (e.g., keyboard and mouse operations). Unlike prevailing agent frameworks that depend on heavily wrapped commercial models (e.g., GPT-4o) with expert-crafted prompts and workflows, UI-TARS is an end-to-end model that outperforms these sophisticated frameworks. Experiments demonstrate its superior performance: UI-TARS achieves SOTA performance in 10+ GUI agent benchmarks evaluating perception, grounding, and GUI task execution. Notably, in the OSWorld benchmark, UI-TARS achieves scores of 24.6 with 50 steps and 22.7 with 15 steps, outperforming Claude (22.0 and 14.9 respectively). In AndroidWorld, UI-TARS achieves 46.6, surpassing GPT-4o (34.5). UI-TARS incorporates several key innovations: (1) Enhanced Perception: leveraging a large-scale dataset of GUI screenshots for context-aware understanding of UI elements and precise captioning; (2) Unified Action Modeling, which standardizes actions into a unified space across platforms and achieves precise grounding and interaction through large-scale action traces; (3) System-2 Reasoning, which incorporates deliberate reasoning into multi-step decision making, involving multiple reasoning patterns such as task decomposition, reflection thinking, milestone recognition, etc. (4) Iterative Training with Reflective Online Traces, which addresses the data bottleneck by automatically collecting, filtering, and reflectively refining new interaction traces on hundreds of virtual machines. Through iterative training and reflection tuning, UI-TARS continuously learns from its mistakes and adapts to unforeseen situations with minimal human intervention. We also analyze the evolution path of GUI agents to guide the further development of this domain.
hub tools
citation-role summary
background 16
baseline 12
dataset 1
method 1
citation-polarity summary
claims ledger
- abstract This paper introduces UI-TARS, a native GUI agent model that solely perceives the screenshots as input and performs human-like interactions (e.g., keyboard and mouse operations). Unlike prevailing agent frameworks that depend on heavily wrapped commercial models (e.g., GPT-4o) with expert-crafted prompts and workflows, UI-TARS is an end-to-end model that outperforms these sophisticated frameworks. Experiments demonstrate its superior performance: UI-TARS achieves SOTA performance in 10+ GUI agent benchmarks evaluating perception, grounding, and GUI task execution. Notably, in the OSWorld bench
authors
co-cited works
representative citing papers
iOSWorld is a new open-source benchmark for personally intelligent phone agents featuring connected personal data across 26 iOS apps and 133 tasks in three difficulty categories.
MacArena is a new macOS GUI agent benchmark with 421 tasks showing inverted model rankings and a 26% performance drop on native tasks versus ported ones.
GUIGuard-Bench is a new benchmark with annotated GUI screenshots that measures privacy recognition, planning fidelity under protection, and utility impact for trajectory-based GUI agents.
SmoothAgent introduces lookahead context engineering to eliminate transformation overhead in LLM agents, reducing TTFT by up to 11.9x through proactive KV cache preparation.
PreAct compiles successful agent executions into verifiable state-machine programs for 8.5-13x faster replay on repeated tasks, with an independent evaluator check before storing each program.
ProCUA-SFT is a 3.1M-sample SFT dataset from 93K verified synthetic trajectories that lifts UI-TARS 7B OSWorld score from 26.3% to 45%.
Proposes COM-as-Action paradigm for deterministic software manipulation, introduces ComCADBench benchmark and ComActor agent that achieves SOTA performance over GUI baselines.
HiViG is a test-time critic that combines macro-action history summarization with visual grounding of execution coordinates to reduce short-sighted and visually erroneous actions in long-horizon GUI agents.
DPAgent is an agentic framework that detects 90.98% of AI-groomed deceptive samples and repairs 77% of deceptive interfaces while exploring 80% of pattern types with 10% of baseline page visits.
Introduces LivingScreen benchmark for living-screen-native GUI agents on short-video platforms; frontier models fail to match human cost-accuracy due to over- and under-observation.
HLL is a new benchmark that evaluates eight frontier multimodal agents on closed-loop interactive CAPTCHA solving, showing sharp performance drops under realism stressors and trace validation.
AndroidDaily supplies 350 verifiable tasks on 94 closed-source Android apps evaluated by GRADE (87.37% human agreement), with the strongest model achieving 62% success.
ScaleWoB generates 100+ synthetic interactive GUI environments and 1000+ verifiable tasks as web pages, releasing a 120-task mobile benchmark where state-of-the-art agents achieve 27.92% success (17.82% on long-horizon tasks) versus 92.08% for humans, with synthetic results generalizing to real apps
PANDO introduces an online skill-distillation method with a structured library, reflection, demotion, routing, compression, and cache-aware prompting that reaches 58.3% success on 910 VisualWebArena tasks using 58-61% fewer tokens than prior methods.
CutVerse benchmark evaluates GUI agents on 186 complex media post-production tasks in seven apps and reports 36% success rate for existing models.
PAGER achieves 4.1x higher task success in point-precise geometric GUI control by combining topology-aware planning with precision-aligned reinforcement learning on the new PAGE Bench dataset of 4,906 problems.
UI traces of actions and timings from LLM browser agents enable identification of the underlying model with up to 96% F1 across 14 models and multiple tasks.
BBCritic reframes GUI critique as continuous semantic alignment via contrastive learning in an affordance space, outperforming larger binary SOTA models on a new four-level hierarchical benchmark without extra annotations.
MMSkills packages multimodal procedural knowledge into state-conditioned skills with text, state cards, and multi-view keyframes, generated from public trajectories via an agentic process and used at inference via branch-loaded inspection to improve visual agents on GUI and game benchmarks.
Presents CUActSpot benchmark and renderer-LLM data synthesis that lets a 4B model outperform larger open-source models on complex computer interactions.
ActGuide-RL uses human action data as plan-style guidance in mixed-policy RL to overcome exploration barriers in LLM agents, matching SFT+RL performance on search benchmarks without cold-start training.
VLATIM benchmark reveals large VLMs excel at high-level planning in physics puzzles but struggle with precise visual grounding and mouse control, so they lack human-like problem-solving capabilities.
GUI grounding in VLMs is bottlenecked by prefill-stage candidate selection that decoding cannot fix, so Re-Prefill uses attention to extract and re-inject target tokens for up to 4.3% gains on ScreenSpot-Pro.
citing papers explorer
-
Benchmarking Living-Screen-Native GUI Agents on Short-Video Platforms
Introduces LivingScreen benchmark for living-screen-native GUI agents on short-video platforms; frontier models fail to match human cost-accuracy due to over- and under-observation.
-
AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applications
AndroidDaily supplies 350 verifiable tasks on 94 closed-source Android apps evaluated by GRADE (87.37% human agreement), with the strongest model achieving 62% success.
-
CutVerse: A Compositional GUI Agents Benchmark for Media Post-Production Editing
CutVerse benchmark evaluates GUI agents on 186 complex media post-production tasks in seven apps and reports 36% success rate for existing models.
-
Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
Presents CUActSpot benchmark and renderer-LLM data synthesis that lets a 4B model outperform larger open-source models on complex computer interactions.
-
What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs
GUI grounding in VLMs is bottlenecked by prefill-stage candidate selection that decoding cannot fix, so Re-Prefill uses attention to extract and re-inject target tokens for up to 4.3% gains on ScreenSpot-Pro.
-
Benchmarking and Improving GUI Agents in High-Dynamic Environments
DynamicUI improves GUI agent performance in high-dynamic environments by processing interaction videos with frame clustering, action-conditioned refinement, and reflection, outperforming prior approaches on the new DynamicGUIBench spanning ten applications.
-
MolmoWeb: Open Visual Web Agent and Open Data for the Open Web
Open 4B and 8B visual web agents achieve state-of-the-art results on browser benchmarks by predicting actions from screenshots and instructions, outperforming similar open models and some closed larger-model agents, with full release of data and code planned.
-
Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning
VIGA introduces a training-free interleaved multimodal reasoning loop that improves vision-as-inverse-graphics accuracy over one-shot baselines on BlenderGym, SlideBench, and new BlenderBench.
-
GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents
GUI-R1 uses reinforcement fine-tuning with GRPO on a small curated dataset to create a generalist vision-language action model that outperforms prior GUI agent methods across mobile, desktop, and web benchmarks using only 0.02% of the data.
-
What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States
Introduces Active Task Driving Memory (ATMem) and STR-GRPO to move GUI agents from passive record storage to actively maintained task states, tested on a new mobile benchmark with progress and scope-aware metrics.
-
Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents
Failure-driven self-improvement raises OpenCUA-72B success rate on OSWorld from 42.3% to 48.9% via LLM diagnosis and inference-time code patches, without retraining.
-
One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding
InnerZoom bridges cross-layer evidence in one forward pass to achieve SOTA GUI grounding accuracy on six benchmarks while cutting latency up to 31.8% versus two-pass baselines.
-
Demo2Tutorial: From Human Experience to Multimodal Software Tutorials
Demo2Tutorial distills human screen recordings into hierarchical image-text tutorials that outperform human-authored ones on a documentation-derived benchmark and improve downstream human task speed and GUI-agent planning.
-
STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models
STaR-KV is a training-free KV cache compression framework for GUI VLMs that uses subspace-aware scoring, temporal stability discounts, and entropy-based temperature adaptation to outperform prior methods at matched budgets while reducing peak memory by ~40% at 20% cache size.
-
MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents
MementoGUI introduces a modular memory-control framework with working and episodic memory operators that improves long-horizon GUI agent performance over history-replay and text-only baselines.
-
BAMI: Training-Free Bias Mitigation in GUI Grounding
BAMI mitigates precision and ambiguity biases in GUI grounding via coarse-to-fine focus and candidate selection, raising accuracy on ScreenSpot-Pro without training.
-
Grounded Reinforcement Learning for Visual Reasoning
ViGoRL introduces visually grounded RL that anchors reasoning steps to image coordinates and uses multi-turn zooming to outperform standard RL and supervised baselines on spatial and GUI reasoning benchmarks.
-
AutoFocus: Uncertainty-Aware Active Visual Search for GUI Grounding
AutoFocus converts token perplexity into an anisotropic Gaussian uncertainty field to drive region proposals and shape-aware zooming for improved GUI grounding in VLMs.
-
Zoom Consistency: A Free Confidence Signal in Multi-Step Visual Grounding Pipelines
Zoom consistency provides a geometric, cross-model confidence signal in zoom-in grounding pipelines that correlates with prediction correctness and enables modest gains in specialist-generalist routing.
-
UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding
UI-Zoomer uses uncertainty quantification to trigger and size adaptive zoom-ins only on uncertain GUI grounding predictions, yielding up to 13.4% gains on benchmarks with no training.
-
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
InternVL3.5 advances open-source multimodal models with Cascade RL for +16% reasoning gains and ViR for 4x inference speedup, with the 241B model reaching SOTA among open-source MLLMs on multimodal, reasoning, and agentic tasks.
-
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
InternVL3-78B sets a new open-source SOTA of 72.2 on MMMU via native joint multimodal pre-training, V2PE, MPO, and test-time scaling while remaining competitive with proprietary models.
-
GUI-C$^2$: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning
GUI-C² pairs a difficulty-scoring data pipeline with an area-gated coarse-to-fine RL mechanism to improve GUI grounding accuracy and training stability.
-
CaptchaMind: Training CAPTCHA Solvers via Reinforcement Learning with Explicit Reasoning Supervision
Presents CaptchaBench benchmark and CaptchaMind RL solver achieving 82.9% success on benchmark tasks and 71% on real-world CAPTCHAs via explicit reasoning process supervision.
-
LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore)
The PhyScore challenge creates the first benchmark requiring metrics to jointly score video quality, physical realism, condition alignment, and temporal consistency while localizing physical anomalies in 1554 videos from seven generative models across text-to-2D, image-to-4D, and video-to-4D tracks.
-
Perceptual Flow Network for Visually Grounded Reasoning
PFlowNet decouples perception from reasoning, integrates multi-dimensional rewards with vicinal geometric shaping via variational RL, and reports new SOTA results on V* Bench (90.6%) and MME-RealWorld-lite (67.0%).
-
GUI-AC: Enhancing Continual Learning in GUI Agents
GUI-AC stabilizes RFT for non-stationary GUI data by down-weighting noisy advantages and relaxing clipping bounds via a grounding certainty term.
-
Seed1.5-VL Technical Report
Seed1.5-VL is a compact multimodal model that sets new records on dozens of vision-language benchmarks and outperforms prior systems on agent-style tasks.
-
X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction
Describes X-OmniClaw, a multimodal mobile agent architecture using Omni Perception, Memory, and Action modules with behavior cloning for Android task execution.
- Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents