SCA: Spatial Credit Assignment for Reinforcement Learning of GUI Agents

arXiv:2609.36939 · cs.AI · Submitted 2026-09-29 · Read on arXiv

cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Credit assignment — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization
• RSGround-R1: Rethinking Remote Sensing Visual Grounding through Spatial Reasoning
• PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning
• GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents
• AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Learning from All-Failed Groups via First-Visit Coverage in Long-Horizon Agentic Tasks
• SRPO: Setwise Relative Policy Optimization for Multi-Agent Systems

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
• Agents' Last Exam
• 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