arXiv:2602. 14344v2 Announce Type: replace-cross Abstract: We study instruction following in multi-task reinforcement learning, where an agent must zero-shot execute novel tasks not seen during training.
By Mathias Jackermeier, Mattia Giuri, Jacques Cloete, Alessandro Abate
The paper introduces PIVOT, a dual-level learning framework designed to improve visually-grounded multimodal reasoning in large vision-language models. PIVOT employs a self‑calibrated experience replay mechanism to selectively reuse valuable visual reasoning trajectories, and a vision‑guided advantage allocation scheme that assigns extra rewards to tokens with strong visual support. Experiments on multiple benchmarks show that PIVOT enhances the multimodal reasoning performance of these models.
By Xinxin Song, Siyuan Li, Tingxiong Xiao, Jinli Suo
arXiv:2602. 06746v2 Announce Type: replace Abstract: We study multi-task reinforcement learning (RL), a setting in which an agent learns a single, universal policy capable of generalising to arbitrary, possibly unseen tasks.
By Alessandro Abate, Giuseppe De Giacomo, Mathias Jackermeier, Jan Kret\'insk\'y, Maximilian Prokop, Christoph Weinhuber
arXiv:2608. 15509v1 Announce Type: cross Abstract: Task guided agents demonstrate strong performance in a wide range of complex tasks.
By Hao Zhang, Zhangli Zhou, Zhen Kan
arXiv:2606. 16122v1 Announce Type: new Abstract: Visual thinking should not only sound right; it should show its evidence.
By Junkai Zhang, Yihe Deng, Kai-Wei Chang, Wei Wang
arXiv:2606. 31599v1 Announce Type: cross Abstract: Vision-language models (VLMs) combining reinforcement learning (RL) ignite remarkable progress in multimodal reasoning, yet still struggle with medical images, which typically exhibit extremely sparse visual evidence to inform clinical decision-making.
By Kaitao Chen, Weiqian Zhao, Jiamin Wu, Qihao Zheng, Shangquan Sun, Chunfeng Song, Xiaosong Wang, Mu Zhou, Mianxin Liu