Pith. sign in

REVIEW 31 cited by

Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning

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 2505.12370 v2 pith:VPHUVQIW submitted 2025-05-18 cs.AI

Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning

classification cs.AI
keywords groundingreinforcementaccuracyagentscomplexdatadiverseenhancing
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Graphical User Interface (GUI) agents have made substantial strides in understanding and executing user instructions across diverse platforms. Yet, grounding these instructions to precise interface elements remains challenging, especially in complex, high-resolution, professional environments. Traditional supervised finetuning (SFT) methods often require large volumes of diverse data and exhibit weak generalization. To overcome these limitations, we introduce a reinforcement learning (RL) based framework that incorporates three core strategies: (1) seed data curation to ensure high quality training samples, (2) a dense policy gradient that provides continuous feedback based on prediction accuracy, and (3) a self evolutionary reinforcement finetuning mechanism that iteratively refines the model using attention maps. With only 3k training samples, our 7B-parameter model achieves state-of-the-art results among similarly sized models on three grounding benchmarks. Notably, it attains 47.3\% accuracy on the ScreenSpot-Pro dataset, outperforming much larger models, such as UI-TARS-72B, by a margin of 24.2\%. These findings underscore the effectiveness of RL-based approaches in enhancing GUI agent performance, particularly in high-resolution, complex environments.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 31 Pith papers

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

  1. Do GUI Agents Believe Their Eyes? Diagnosing State-Belief Reliance on Pixels versus Structure

    cs.AI 2026-07 accept novelty 7.0

    Across five models, textual GUI state beliefs defer to conflicting structure despite near-ceiling image-only perception, yielding a positive Perception-Fusion Gap that propagates into wrong actions.

  2. Do GUI Agents Believe Their Eyes? Diagnosing State-Belief Reliance on Pixels versus Structure

    cs.AI 2026-07 accept novelty 7.0

    Across four open-weight models and three OpenAI models, textual state beliefs of GUI agents follow a conflicting structured value on 30–75% of probes where the same model reads the pixels correctly, so agent state bel...

  3. ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning

    cs.AI 2026-06 unverdicted novelty 7.0

    ReSum trains LLMs via RLVR to self-summarize reasoning trajectories, yielding 4% average performance gains and 18.6% shorter rollouts through contrastive rollout branches.

  4. What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs

    cs.CV 2026-05 conditional novelty 7.0

    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.

  5. Faithful Mobile GUI Agents with Guided Advantage Estimator

    cs.AI 2026-05 unverdicted novelty 7.0

    Faithful-Agent raises Trap SR in GUI agents from 13.88% to 80.21% via faithfulness-oriented SFT and GuAE-enhanced RFT with consistency rewards while retaining general performance.

  6. Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding

    cs.AI 2026-05 unverdicted novelty 7.0

    GUI-SD is the first on-policy self-distillation framework for GUI grounding that adds privileged bounding-box context and entropy-guided weighting to outperform GRPO methods on six benchmarks in accuracy and efficiency.

  7. Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding

    cs.AI 2026-05 accept novelty 7.0

    GUI-SD introduces on-policy self-distillation with visually enriched privileged context and entropy-guided weighting, outperforming GRPO and naive OPSD on six GUI grounding benchmarks while improving training efficiency.

  8. Benchmarking and Improving GUI Agents in High-Dynamic Environments

    cs.CV 2026-04 conditional novelty 7.0

    DynamicUI improves GUI agent performance in high-dynamic environments by using video-based dynamic perception, action-conditioned refinement, and reflection, outperforming prior agents on the new DynamicGUIBench while...

  9. Benchmarking and Improving GUI Agents in High-Dynamic Environments

    cs.CV 2026-04 unverdicted novelty 7.0

    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 Dy...

  10. OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents

    cs.CL 2026-04 unverdicted novelty 7.0

    OS-SPEAR is a new evaluation toolkit that tests 22 OS agents and identifies trade-offs between efficiency and safety or robustness.

  11. Grounding Computer Use Agents on Human Demonstrations

    cs.LG 2025-11 conditional novelty 7.0

    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.

  12. GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots

    cs.AI 2026-06 unverdicted novelty 6.0

    GUICrafter uses curriculum learning on unannotated GUI screenshots for visual grounding followed by RL calibration on limited labels to match or exceed prior GUI agents with far less annotation.

  13. ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning

    cs.AI 2026-06 conditional novelty 6.0

    ReSum's contrastive RL branching on self-summarization points improves LLM math reasoning accuracy by about 4% and shortens rollouts by about 18.6% across tested backbones.

  14. GUI-AC: Enhancing Continual Learning in GUI Agents

    cs.CV 2026-06 conditional novelty 6.0

    Grounding-certainty-guided Adaptive Advantage and Dynamic Clipping improve continual GUI grounding over RFT baselines on ScreenSpot-V1/V2/Pro.

  15. LiteGUI: Distilling Compact GUI Agents with Reinforcement Learning

    cs.AI 2026-05 unverdicted novelty 6.0

    LiteGUI trains 2B/3B-scale GUI agents via SFT-free guided on-policy distillation and multi-solution dual-level GRPO to reach SOTA lightweight performance and compete with larger models.

  16. BAMI: Training-Free Bias Mitigation in GUI Grounding

    cs.CV 2026-05 unverdicted novelty 6.0

    BAMI mitigates precision and ambiguity biases in GUI grounding via coarse-to-fine focus and candidate selection, raising accuracy on ScreenSpot-Pro without training.

  17. AutoFocus: Uncertainty-Aware Active Visual Search for GUI Grounding

    cs.CV 2026-05 unverdicted novelty 6.0

    AutoFocus converts token perplexity into an anisotropic Gaussian uncertainty field to drive region proposals and shape-aware zooming for improved GUI grounding in VLMs.

  18. Zoom Consistency: A Free Confidence Signal in Multi-Step Visual Grounding Pipelines

    cs.CV 2026-04 unverdicted novelty 6.0

    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.

  19. UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding

    cs.CV 2026-04 unverdicted novelty 6.0

    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.

  20. Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection

    cs.CR 2026-04 unverdicted novelty 6.0

    Semantic-level UI Element Injection distracts GUI agents by overlaying safety-aligned UI elements, achieving up to 4.4x higher attack success rates that transfer across models and create persistent attractors.

  21. RISK: A Framework for GUI Agents in E-commerce Risk Management

    cs.AI 2025-09 unverdicted novelty 6.0

    RISK introduces a dataset, benchmark, and R1-style RL fine-tuning for GUI agents that achieve 6.8-8.8% offline gains and 70.5% online task success in e-commerce risk management using 7.2% of baseline parameters.

  22. GTA1: GUI Test-time Scaling Agent

    cs.AI 2025-07 unverdicted novelty 6.0

    GTA1 combines test-time scaling for action plan selection with RL-based grounding to achieve SOTA results on GUI agent benchmarks.

  23. Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

    cs.AI 2026-07 conditional novelty 5.5

    A real-device-centric foundation GUI agent with hybrid GUI+CLI batched actions, AutoResearch data flywheel, online RL, and a proactive harness reaches SOTA mobile and competitive desktop/web scores.

  24. GUI-C$^2$: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning

    cs.CV 2026-05 unverdicted novelty 5.0

    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.

  25. SE-GA: Memory-Augmented Self-Evolution for GUI Agents

    cs.LG 2026-05 unverdicted novelty 5.0

    SE-GA combines Test-Time Memory Extension for dynamic context retrieval with Memory-Augmented Self-Evolution training to reach 89.0% on ScreenSpot and 75.8% on AndroidControl-High.

  26. DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding

    cs.AI 2026-05 unverdicted novelty 5.0

    DRS-GUI introduces a dynamic region search method with Focus/Shift/Scatter actions and MCTS-based planning that improves GUI grounding accuracy by 14% on ScreenSpot-Pro for both general and GUI-specific MLLMs without ...

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

    cs.CV 2025-10 conditional novelty 5.0

    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...

  28. GUI-AC: Enhancing Continual Learning in GUI Agents

    cs.CV 2026-06 unverdicted novelty 4.0

    GUI-AC stabilizes RFT for non-stationary GUI data by down-weighting noisy advantages and relaxing clipping bounds via a grounding certainty term.

  29. Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability

    cs.CL 2026-05 unverdicted novelty 4.0

    The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment inter...

  30. Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward

    cs.MA 2026-02 conditional novelty 4.0

    Agent skills are the emerging standard for giving LLM agents specialized procedures, but the reported 26.1% vulnerability rate in community skills argues for provenance-based, tiered trust governance.

  31. Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward

    cs.MA 2026-02 unverdicted novelty 4.0

    The paper surveys agent skills for LLMs across architecture, acquisition, deployment, and security, proposing a four-tier Skill Trust and Lifecycle Governance Framework to address vulnerabilities in community skills.