arXiv:2606. 24622v1 Announce Type: new Abstract: Training safe Reinforcement Learning (RL) systems is inherently challenging, with no guarantee of avoiding unwanted behaviors.
By Andreas Chouliaras, Luke Connolly, Dimitris Chatzpoulos
arXiv:2607. 05773v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into autonomous agents, traditional static evaluation fails to capture multi-step decision-making.
By Akshay Arora, Ishan Nigam, Ashutosh Aggarwal, Shefali Bansal, Krishna Singh, Sweta Kumari, Nikhil Mittal, Shariq Farhan, Siddarth Malreddy
arXiv:2606. 24515v1 Announce Type: new Abstract: Computer-Use Agents (CUAs) execute high-level user goals by perceiving and acting directly within graphical user interfaces.
By Marta Sumyk, Oleksandr Kosovan
RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward functions. The underlying technique was developed as a step towards safe AI systems, but also applies to reinforcement learning problems with rewards that are hard to specify.
arXiv:2606. 19370v1 Announce Type: cross Abstract: Self-play reinforcement learning has recently emerged as a way to train driving policies without any human data.
By Daphne Cornelisse, Julian Hunt, Zixu Zhang, Wa\"el Doulazmi, Kevin Joseph, Jaime Fern\'andez Fisac, Eugene Vinitsky
arXiv:2607. 18314v1 Announce Type: new Abstract: Experiment trackers show how training is progressing, but changing a live run still usually requires trainer-specific code.
By Wentao Zhang, Xuanhe Pan, Han Zhou, Yang Lu, Yuntian Deng