← Back to all news
arXiv AI By Abdulhamid M. Mousa, Jinhui Pang, Rakhmonberdi Khajiev, Jalaledin M. Azzabi, Abdulkarim M. Mousa, Peng Yong, Yunusa Haruna, Ming Liu

MOSAIC: A Universal Agent-Level Interface for Cross-Paradigm Agent Mixing and Human-AI Collaboration

Read the original on arXiv AI →

MOSAIC is an open‑source platform that allows agents from different decision‑making paradigms—such as reinforcement learning policies, large language models, vision‑language models, and human operators—to operate together in shared reinforcement learning environments. It achieves this through an IPC‑based worker protocol that isolates each agent’s training and inference logic, an operator abstraction that maps any agent to a minimal universal interface, and a deterministic evaluation framework offering both manual lock‑step and automated script modes for reproducible experiments.

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 AI.

Related stories

arXiv AI
Jun 12

LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories

arXiv:2606. 13578v1 Announce Type: cross Abstract: Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach.

By Baochang Ren, Xinjie Liu, Xi Chen, Yanshuo Liu, Chenxi Li, Daqi Gao, Zeqin Su, Jintao Xing, Zirui Xue, Rui Li, Xiangyu Zhao, Shuofei Qiao, Minting Pan, Wangmeng Zuo, Lei Bai, Dongzhan Zhou, Ningyu Zhang, Huajun Chen
diffusionroboticsmultimodalbenchmarks
More like this →
arXiv AI
2d ago

WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents

arXiv:2609.36887v1 Announce Type: new Abstract: Recent efforts to scale tool-use post-training have largely centered on the synthesis of executable environments, which constitute only one component o...

By Bo Mao, Hang He, Linting Wang, Lizhi Lin, Maosen Zhou, Guanming Liu, Jinxiu Liu, Tianyu Huai, Chaoyun Zhang, Bingxuan Li, Kepeng Lei, Guanting Dong, Zhou Shao, Rui Zheng, Hang Yan, Jie Zhou, Chengcheng Wan, Tao Gui, Liang He, Xipeng Qiu
agentsbenchmarks
More like this →
arXiv AI
Jun 17

MagicSim: A Unified Infrastructure for Executable Embodied Interaction

arXiv:2606. 17511v1 Announce Type: cross Abstract: Robot learning and embodied agents now require simulation to serve as a shared execution substrate linking control, skills, and planning, not only as a renderer, controller testbed, or fixed task environment.

By Haoran Lu, Songling Liu, Yue Chen, Guo Ye, Mutian Shen, Shuyang Yu, Yu Xiao, Jihai Zhao, Shang Wu, Jianshu Zhang, Xiangtian Gui, Chuye Hong, Yuran Wang, Maojiang Su, Jiayi Wang, Ruihai Wu, Zhaoran Wang, Han Liu
agentsreinforcement-learningroboticsmultimodalbenchmarks
More like this →
arXiv AI
Sep 18

UnifiedPlayers: Enhance Tool-Integrated Reasoning in Agentic Reinforcement Learning

UnifiedPlayers is a cooperative framework that jointly adapts planning, execution, and evaluation for tool-integrated reinforcement learning agents. It consists of a Planning Player that generates tasks, an Execution Player that creates multi-turn trajectories with Python tool calls, and an Evaluation Player that builds executable verifiers, all coordinated by role‑specific rewards under GRPO. The approach outperforms prior baselines on mathematical and general reasoning benchmarks and yields a verifier with high adversarial detection accuracy and more discriminative reward signals.

By Wenjie Liao, Liangjie Zhao, Zehong Cao
agentsreinforcement-learningbenchmarkssafety
More like this →