GSAR: Goal-State-Anchor Rewards for Mobile GUI Agents with Self-Evolving Data Synthesis
cs.AI
Submitted: 2026-08-24
Updated: 2026-11-03
Terminology
Sources
- DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
- Qwen2.5-VL Technical Report
- STEP: Success-Rate-Aware Trajectory-Efficient Policy Optimization
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Group-in-Group Policy Optimization for LLM Agent Training
- On Designing Effective RL Reward at Training Time for LLM Reasoning
- LoRA: Low-Rank Adaptation of Large Language Models
- Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
- AndroidGen: Building an Android Language Agent under Data Scarcity
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- GUI-ReWalk: Massive Data Generation for GUI Agent via Stochastic Exploration and Intent-Aware Reasoning
- InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners
- GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices
- GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents
- Training language models to follow instructions with human feedback
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
- Android in the Wild: A Large-Scale Dataset for Android Device Control
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents