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%).
127
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
-
It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents
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.