arXiv Machine Learning August 31, 2026 By Yida Xue, Mingjun Mao, Xiangyuan Ru, Yuqi Zhu, Baochang Ren, Shuofei Qiao, Mengru Wang, Shumin Deng, Xinyu An, Ningyu Zhang, Ying Chen, Huajun Chen

OceanGym: A Benchmark Environment for Underwater Embodied Agents

Read the original on arXiv Machine Learning →

OceanGym is the first comprehensive benchmark for underwater embodied agents, featuring eight realistic task domains and a unified agent framework powered by Multi‑modal Large Language Models (MLLMs). It challenges agents to process optical and sonar data, navigate complex environments, and achieve long‑horizon goals amid low visibility and dynamic currents. Experiments show significant performance gaps between current MLLM agents and human experts, underscoring the difficulty of perception, planning, and adaptability in ocean settings.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

4d ago

AquaWAM: A Dynamics-aware World Action Model for Underwater Embodied Agents

arXiv:2609.33299v2 Announce Type: replace-cross Abstract: World Action Models (WAMs) are becoming increasingly important and useful for embodied intelligence, as they enable robots to anticipate the...

By Cunhao Zhu, Yifeng Wang, Dongliang Xu, Yunzhong Hou, Yue Yao, Chi Harold Liu

agents robotics benchmarks

arXiv Machine Learning

Aug 3

ASVSim (AirSim for Surface Vehicles): A High-Fidelity Simulation Framework for Autonomous Surface Vehicle Research

arXiv:2506. 22174v3 Announce Type: replace-cross Abstract: The transport industry has recently shown significant interest in unmanned surface vehicles (USVs), specifically for port and inland waterway transport.

By Bavo Lesy, Siemen Herremans, Robin Kerstens, Jan Steckel, Walter Daems, Siegfried Mercelis, Ali Anwar

agents computer-vision reinforcement-learning safety

arXiv AI

Jun 3

Scaling Multi Agent Reinforcement Learning for Underwater Acoustic Tracking via Autonomous Vehicles

arXiv:2505. 08222v3 Announce Type: replace-cross Abstract: Autonomous vehicles (AVs) offer a cost-effective solution for scientific missions such as underwater tracking.

By Matteo Gallici, Ivan Masmitja, Mario Mart\'in

llms agents reinforcement-learning robotics

arXiv Computer Vision

Sep 18

Towards Scaling Marine Perception with Synthetic Data

The paper introduces an extension to the OceanSim underwater perception simulator, adding a Synthetic Data Generation pipeline that produces large, automatically labeled, photorealistic datasets with configurable scene and sensor settings. The authors evaluate this pipeline on a real-world sea urchin detection task, examining how different synthetic scene variations influence sim-to-real performance. They discuss the pipeline’s findings, limitations, and future directions for improving rendering fidelity, scene diversity, and sim-to-real generalization.

By Haoyu Ma, Onur Bagoren, Anja Sheppard, Elias Fandi, Ashrith Edukulla, Tanner Aslan, Natasha Sieh, Jingyu Song, Katherine A. Skinner

robotics

arXiv Machine Learning

Jun 9

Towards End to End Motion Planning and Execution for Autonomous Underwater Vehicles Using Reinforcement Learning

arXiv:2606. 08513v1 Announce Type: cross Abstract: Autonomous Underwater Vehicles (AUVs) traditionally rely on complex, heavily engineered pipelines for perception, path planning, and motion control.

By Elisei Shafer, Oren Gal

agents reinforcement-learning robotics

arXiv Computer Vision

Sep 22

ME-VLM:A Unified VLM for Embodied Cognition and Agent Coordination

arXiv:2609.24526v1 Announce Type: new Abstract: Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints and...

By Foundation Model, Li Auto Inc

llms agents reinforcement-learning robotics efficiency multimodal benchmarks