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.
hub
Gui-r1: A generalist r1-style vision-language action model for gui agents
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
years
2026 18roles
background 1polarities
background 1representative citing papers
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.
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.
OS-SPEAR is a new evaluation toolkit that tests 22 OS agents and identifies trade-offs between efficiency and safety or robustness.
RiskWebWorld is the first realistic interactive benchmark for GUI agents in e-commerce risk management, revealing a large gap between generalist and specialized models plus RL gains.
ToolCUA introduces a trajectory scaling pipeline and staged RL to optimize GUI-tool switching, reaching 46.85% accuracy on OSWorld-MCP for a 66% relative gain over baseline.
Mobile world models in text, image, and code modalities reach state-of-the-art on their benchmarks and improve downstream GUI agent performance, with code best for in-distribution accuracy and text more robust for out-of-distribution use.
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.
BAMI mitigates precision and ambiguity biases in GUI grounding via coarse-to-fine focus and candidate selection, raising accuracy on ScreenSpot-Pro without training.
ROSE delivers 1.2-3.3x higher end-to-end throughput for agentic RL by safely co-using underutilized serving GPUs for rollouts while meeting serving SLOs.
AutoGUI-v2 is a new benchmark exposing that VLMs handle basic GUI grounding but struggle with complex interaction logic and state prediction.
QuantClaw dynamically routes precision in agent workflows to cut cost by up to 21.4% and latency by 15.7% while keeping or improving task performance.
ReRec uses reinforcement fine-tuning with dual-graph reward shaping, reasoning-aware advantage estimation, and online curriculum scheduling to improve LLM reasoning and performance in recommendation tasks.
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%).
HalluClear supplies a taxonomy, calibrated evaluation, and lightweight post-training mitigation that reduces hallucinations in GUI agents using only 9K samples.
LAMO uses role-oriented data synthesis and two-stage training (perplexity-weighted supervised fine-tuning plus reinforcement learning) to create scalable lightweight GUI agents that support both single-model and multi-agent orchestration.
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 interventions.
The paper surveys the conceptual foundations, methodological innovations, challenges, and future directions of agentic reinforcement learning frameworks that embed cognitive capabilities like meta-reasoning and self-reflection into LLM-based agents.
citing papers explorer
-
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.
-
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.
-
AutoGUI-v2: A Comprehensive Multi-Modal GUI Functionality Understanding Benchmark
AutoGUI-v2 is a new benchmark exposing that VLMs handle basic GUI grounding but struggle with complex interaction logic and state prediction.
-
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%).