arXiv:2603. 18464v3 Announce Type: replace Abstract: Reinforcement learning (RL) for large-scale Vision-Language-Action (VLA) models is severely bottlenecked by synchronization barriers and the high cost of environment data acquisition.
arXiv:2609.13243v1 Announce Type: cross Abstract: We present GzDRL, a novel single-process reinforcement learning (RL) framework for Gazebo that overcomes longstanding bottlenecks in scalable, reprod...
MAI-Gym is an open, all-in-one platform that unifies GUI agent evaluation, data collection, and online reinforcement learning training across mobile, computer, and web environments. It supports ten established benchmarks, scales to 20,000 parallel environment instances, and enables automated synthesis of diverse GUI applications and tasks with execution-validated verifiers. Using this platform, the authors trained a 9B-parameter agent, MAI-Gym-9B, achieving state‑of‑the‑art performance on MobileWorld and OSWorld-Verified, and demonstrated that training on a mocked train‑ticketing app improves real‑world task success from 28.8% to 48.1% on a physical phone.
RL-VLA$^3$ is a fully asynchronous distributed reinforcement learning framework designed for Vision‑Language‑Action (VLA) model training. It allows fine‑grained asynchronous interaction between simulation, inference, and training via dynamic batching schedulers and flexible environment sharding, addressing the variable, resource‑intensive latencies of physical simulators. Experiments across multiple simulation backends, VLA architectures, and RL algorithms show throughput gains of up to 85.2% over synchronous baselines while preserving sample efficiency, and the system scales from 8 to 256 GPUs.
Vision-Language Models (VLMs) based GUI agents stand to benefit significantly from online reinforcement learning (RL). However, their training is bottlenecked by two fundamental issues: current data s...
arXiv:2608.22847v1 Announce Type: new Abstract: Vision-Language Models (VLMs) based GUI agents stand to benefit significantly from online reinforcement learning (RL). However, their training is bottl...
The paper introduces an online reinforcement learning framework for UI navigation on live iOS apps, separating the agent into a Planning component and a UI Grounding model. It employs an LLM-as-a-Judge to supply dense step-level and terminal rewards, and uses PPO with a novel GiGPPO value estimation to stabilize training. Large-scale infrastructure enables concurrent virtual device training, and experiments on UINavBench, iOSWorld, and AndroidWorld show the approach outperforms supervised fine-tuning and terminal-only RL, achieving significant generalization gains and matching state‑of‑the‑art models on real iOS tasks.
WebHarbor is a collection of 153 dockerized website environments that faithfully replicate real-world web services, offering 3,518 tasks that include multi-step and post-authentication workflows. Built through task-driven human-agent collaboration, the suite ensures deterministic control, visual fidelity, and functional correctness. The platform enables reliable evaluation and cost-efficient reinforcement learning, with a Qwen 4B-level GUI agent trained in WebHarbor generalizing well to unseen tasks and matching leading open-source agents on four benchmarks.
arXiv:2608.22167v1 Announce Type: new Abstract: Reinforcement learning (RL) has become an effective way to improve the tool-use ability of large language models (LLMs), but most existing RL framework...
arXiv:2606. 02031v1 Announce Type: cross Abstract: Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites.
AgentVQA is an offline benchmark designed to evaluate vision‑language models on realistic agentic scenarios across five domains: Web Agents, Robotics, Egocentric Videos, Games, and Spatial Planning. It comprises 1,000 carefully selected real‑world examples drawn from 23 source datasets, enabling reliable comparisons without costly online simulations. The benchmark reveals that current models achieve only 58.5% accuracy, with most errors stemming from difficulties in grounding and tracking evolving visual states rather than from task misunderstanding or reasoning.
LoongSage is a lightweight, fully asynchronous reinforcement learning framework designed for large language models that perform agentic tasks. It integrates with Megatron for distributed training and SGLang for high‑throughput inference, centralizing orchestration in a single controller and using Ray actors for GPU components. The framework introduces AgentFlow for unified execution of white‑box and black‑box agents, sliding‑window strategies to limit trajectory staleness, TransferMesh for efficient weight synchronization, and a memory‑efficient Teacher Manager that supports multi‑teacher on‑policy distillation. Experiments across four training runs show steady reward improvement, controlled train‑inference gaps, and sustained hardware utilization by eliminating synchronous idle periods.