Task-Adaptive Rubrics for GUI Reward Modeling

arXiv:2608.24174 · cs.AI · Submitted 2026-08-25 · Read on arXiv

cs.AI

Submitted: 2026-08-25

Updated: 2026-08-25

Terminology

• Verifier — 54× in this paper · explained in 2 episodes
• Verification — 50× in this paper · explained in 2 episodes
• Reinforcement Learning — 13× in this paper · explained in 4 episodes
• Accuracy — 11× in this paper · explained in 1 episode
• Benchmark — 8× in this paper · explained in 2 episodes
• Online Reinforcement Learning — 7× in this paper · explained in 2 episodes
• Trace — 7× in this paper · explained in 2 episodes
• Fidelity — 5× in this paper · explained in 2 episodes
• Test-time Scaling — 5× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• GRPO — 4× in this paper · explained in 6 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Benchmarking — 3× in this paper · explained in 4 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• Tokenization — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Abstention — 2× in this paper · explained in 1 episode
• Actor — 2× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• Visual Grounding — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Graphical User Interface — 1× in this paper
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• Verifiability — 1× in this paper · explained in 2 episodes

Sources

• DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
• Qwen3-VL Technical Report
• Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
• STEP: Success-Rate-Aware Trajectory-Efficient Policy Optimization
• Scaling Autonomous Agents via Automatic Reward Modeling And Planning
• Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction
• ProRe: A Proactive Reward System for GUI Agents via Reasoner-Actor Collaboration
• Mind2Web: Towards a Generalist Agent for the Web
• Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
• CARMO: Dynamic Criteria Generation for Context-Aware Reward Modelling
• Learning to Navigate the Web
• CogAgent: A Visual Language Model for GUI Agents
• OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use
• MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments
• AndroidGen: Building an Android Language Agent under Data Scarcity
• On the Effects of Data Scale on UI Control Agents
• OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards
• AutoGLM: Autonomous Foundation Agents for GUIs
• InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
• InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection