arXiv:2602. 09761v2 Announce Type: replace-cross Abstract: In this work we address the problem of training a Reinforcement Learning agent to follow multiple temporally-extended instructions expressed in Linear Temporal Logic in sub-symbolic environments.
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.
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.
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.
arXiv:2608. 15509v1 Announce Type: cross Abstract: Task guided agents demonstrate strong performance in a wide range of complex tasks.
arXiv:2606. 16122v1 Announce Type: new Abstract: Visual thinking should not only sound right; it should show its evidence.
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.
arXiv:2606. 29984v1 Announce Type: new Abstract: Reinforcement Learning (RL) is an important paradigm for improving the reasoning capabilities of Vision-Language Models (VLMs).
arXiv:2607. 04517v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are commonly treated as end-to-end action policies conditioned on natural-language task descriptions.
arXiv:2604. 16557v2 Announce Type: replace Abstract: Current post-training methodologies for adapting Large Vision-Language Models (LVLMs) generally fall into two paradigms: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL).
arXiv:2606. 00083v1 Announce Type: cross Abstract: Reinforcement learning relies on accurate reward functions, which are often hand-crafted or even unavailable in real-world applications, such as robotics.
arXiv:2609.39168v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet existing...
arXiv:2511. 07403v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial reasoning.