Pith. sign in

REVIEW 17 cited by

Aria-UI: Visual Grounding for GUI Instructions

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.16256 v2 pith:LAXBKK4R submitted 2024-12-20 cs.HC cs.AI

classification cs.HCcs.AI
keywords aria-uigroundinginstructionsacrossagentsdatainputsmodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Digital agents for automating tasks across different platforms by directly manipulating the GUIs are increasingly important. For these agents, grounding from language instructions to target elements remains a significant challenge due to reliance on HTML or AXTree inputs. In this paper, we introduce Aria-UI, a large multimodal model specifically designed for GUI grounding. Aria-UI adopts a pure-vision approach, eschewing reliance on auxiliary inputs. To adapt to heterogeneous planning instructions, we propose a scalable data pipeline that synthesizes diverse and high-quality instruction samples for grounding. To handle dynamic contexts in task performing, Aria-UI incorporates textual and text-image interleaved action histories, enabling robust context-aware reasoning for grounding. Aria-UI sets new state-of-the-art results across offline and online agent benchmarks, outperforming both vision-only and AXTree-reliant baselines. We release all training data and model checkpoints to foster further research at https://ariaui.github.io.

Discussion (0). Sign in to comment.

Forward citations

Cited by 17 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models

    cs.LG 2026-04 conditional novelty 7.0 of 10

    GUI-Perturbed shows that GUI grounding models suffer systematic accuracy collapse under relational instructions and visual changes such as 70% zoom, with even augmented fine-tuning worsening results.

  2. Grounding Computer Use Agents on Human Demonstrations

    cs.LG 2025-11 conditional novelty 7.0 of 10

    GroundCUA, a 3.56M-element human-annotated desktop grounding dataset, and GroundNext models achieve strong UI grounding with less than one-tenth the SFT data of prior work.

  3. GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

    cs.LG 2026-02 conditional novelty 6.0 of 10

    Action-weighted SFT plus KL-regularized GRPO on a curated 81K reasoning dataset lifts open-source GUI agents by 11–22 points on online task-completion benchmarks.

  4. SparkUI-Parser: Enhancing GUI Perception with Robust Grounding and Parsing

    cs.AI 2025-09 conditional novelty 6.0 of 10

    An end-to-end GUI-perception MLLM that uses a token router and continuous coordinate decoder to simultaneously ground and parse interface elements, achieving SOTA on several grounding benchmarks and a new parsing benchmark.

  5. Learning Active Perception via Self-Evolving Preference Optimization for GUI Grounding

    cs.CV 2025-09 conditional novelty 6.0 of 10

    LASER uses self-evolving preference optimization to teach GUI models to crop and zoom before clicking, reaching 55.7% on ScreenSpot-Pro with a 7B model.

  6. UItron: Foundational GUI Agent with Advanced Perception and Planning

    cs.CV 2025-08 conditional novelty 6.0 of 10

    UItron, trained with multi-stage SFT and curriculum RL on a new 1M-step Chinese app dataset, beats prior GUI agents on perception, grounding, planning, and especially Chinese mobile app scenarios.

  7. GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

    cs.CL 2025-06 conditional novelty 6.0 of 10

    An attention-based action head with multi-patch supervision outperforms coordinate-generation baselines on GUI grounding, and a verifier further improves accuracy.

  8. ZeroGUI: Automating Online GUI Learning at Zero Human Cost

    cs.AI 2025-05 conditional novelty 6.0 of 10

    ZeroGUI uses VLM-generated tasks and VLM-estimated rewards with two-stage GRPO to improve GUI agent success rates on OSWorld and AndroidLab without human annotations.

  9. TransBench: Breaking Barriers for Transferable Graphical User Interface Agents in Dynamic Digital Environments

    cs.HC 2025-05 conditional novelty 6.0 of 10

    TransBench is a new benchmark of 1,459 screenshots and 22,000 grounding instructions for measuring how well GUI agents transfer across app versions, platforms, and applications.

  10. Enhancing Trustworthy GUI Grounding via Self-Critiqued Reinforcement Learning

    cs.CV 2025-10 conditional novelty 5.0 of 10

    HyperClick trains GUI grounding models with GRPO to output clicks plus confidence scores, jointly rewarding correct clicks and Brier-calibrated confidence, and reports SOTA accuracy on six of seven benchmarks with bet...

  11. Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills

    cs.AI 2025-06 conditional novelty 5.0 of 10

    Mirage-1 combines a hierarchical multimodal skill memory with a skill-augmented Monte Carlo tree search to outperform prior GUI agents on Android and web online benchmarks.

  12. GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior

    cs.AI 2025-06 conditional novelty 5.0 of 10

    GUI-Reflection trains an 8B multimodal GUI agent to recognize mistakes, undo incorrect actions, and retry, improving AndroidWorld success rate from 14.58% (filtered BC baseline) to 34.72% with reflection data and onli...

  13. ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

    cs.CV 2025-05 conditional novelty 5.0 of 10

    ARPO combines GRPO reinforcement learning with a replay buffer of successful GUI trajectories and task filtering, improving UI-Tars to 29.9% on OSWorld.

  14. GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents

    cs.CL 2025-05 conditional novelty 5.0 of 10

    GUI-G1-3B shows that for GUI grounding, removing reasoning chains, regularizing box size in the reward, and reweighting GRPO by difficulty yields 90.3% on ScreenSpot and 37.1% on ScreenSpot-Pro.

  15. Building a Stable Planner: An Extended Finite State Machine Based Planning Module for Mobile GUI Agent

    cs.AI 2025-05 conditional novelty 5.0 of 10

    A hand-authored EFSM planning module boosts Qwen2.5-VL-72B on AndroidWorld from 35.0% to 63.8% task success.

  16. Uncertainty-Aware GUI Agent: Adaptive Perception through Component Recommendation and Human-in-the-Loop Refinement

    cs.AI 2025-08 conditional novelty 4.0 of 10

    A GUI agent that trims UI input with a recommendation module and asks users when decisions are ambiguous reports state-of-the-art success rates, though the interaction module is not benchmarked.

  17. GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding

    cs.LG 2025-07 conditional novelty 4.0 of 10

    Modeling GUI elements as Gaussian distributions instead of binary targets yields 92.0% (ScreenSpot), 93.3% (ScreenSpot-v2), and 47.5% (ScreenSpot-Pro) for a 7B model, outperforming UI-TARS-72B by a relative 24.7% on t...

Pith tools