Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2607. 13274v1 Announce Type: cross Abstract: Reinforcement learning is increasingly being considered for controlling real-world systems, from fusion plasma and autonomous vehicles to drug discovery and drinking water treatment, where reliability is essential and tuning budgets are limited.
arXiv:2604. 21688v2 Announce Type: replace-cross Abstract: The IC3 algorithm represents the state-of-the-art (SOTA) hardware model checking technique, owing to its robust performance and scalability.
arXiv:2607. 13394v1 Announce Type: cross Abstract: Generative Flow Networks (GFlowNets) offer a promising alternative to reward-maximizing reinforcement learning (RL) for large reasoning models, encouraging diverse reasoning paths by matching reward distributions rather than collapsing to dominant modes.
arXiv:2607. 13643v1 Announce Type: cross Abstract: Sampling multiple solutions and returning the majority answer is among the most reliable ways to improve the reasoning accuracy of large language models without labels, and a growing family of methods converts this consensus signal into training supervision.
arXiv:2607. 13160v1 Announce Type: cross Abstract: Active beyond-diagonal reconfigurable intelligent surfaces (BD-RISs) enables hybrid transmitting and reflecting mode to achieve effective signal amplification and full-space coverage, thus providing a promising solution for blockage-aware uplink offloading in heterogeneous mobile edge computing (MEC) systems.
arXiv:2607. 13498v1 Announce Type: new Abstract: Learning a compact model of the world from interaction data is central to sample-efficient deep reinforcement learning.
arXiv:2603. 13952v3 Announce Type: replace-cross Abstract: In existing Audio-Visual Speech Enhancement (AVSE) methods, objectives such as Scale-Invariant Signal-to-Noise Ratio (SI-SNR) and Mean Squared Error (MSE) are widely used; however, their correlation with perceived speech quality is often suboptimal and provides limited interpretability for optimization.
arXiv:2607. 13501v1 Announce Type: new Abstract: Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions.
arXiv:2502. 13467v2 Announce Type: replace Abstract: The $K$-Max combinatorial multi-armed bandit problem arises in applications such as recommendation and distributed decision making, where the reward is determined by the maximum outcome among $K$ selected arms.
arXiv:2607. 13054v1 Announce Type: cross Abstract: Environmental monitoring with unmanned aerial vehicles (UAVs) requires route planning methods that maximize covered area while handling energy limits, operational constraints, and geometric complexity.
arXiv:2607. 13558v1 Announce Type: new Abstract: Urban region profiling constitutes a core problem in urban computing, supporting applications such as population estimation, economic assessment, and environmental monitoring.
arXiv:2607. 13655v1 Announce Type: new Abstract: Explainable Reinforcement Learning (XRL) seeks to make Reinforcement Learning (RL) policies more transparent and interpretable, a key requirement in safety-critical and human-centric scenarios.
arXiv:2607. 13402v1 Announce Type: cross Abstract: In bandit problems, standard regret-minimizing algorithms treat exploration as an amortized cost, which can expose early participants to unfair ex-ante losses in settings such as clinical trials.
arXiv:2607. 13639v1 Announce Type: cross Abstract: We introduce OvisOCR2, a 0.
Vision Language Models (VLMs) demonstrate strong perceptual abilities but remain limited in tasks requiring analytical reasoning across multiple visual states, such as multi-image comparison, change detection, and multi-step visual inference. These capabilities are critical for real-world multimodal applications where reasoning must be grounded in systematic differences between visual contexts.
Reinforcement learning with verifiable rewards (RLVR) drives multimodal reasoning, but answer-level correctness does not guarantee that a vision-language model grounds its predictions in visual evidence. Existing visual-intervention methods contrast policy behavior on original and modified images, yet assign supervision by the type of intervention rather than its observed effect.
Feedback-driven loops support iterative improvement in large language models, reinforcement learning, and autonomous discovery, yet their gains often diminish under repeated internal feedback. We study why closed-loop knowledge systems saturate and what external information can move them beyond their current attractors.
In underwater covert cooperative missions, autonomous underwater vehicles (AUVs) often cannot rely on active sonar to continuously obtain complete information, since active sensing and frequent communications increase the risk of exposure. As a result, AUVs primarily rely on passive observation, an approach that yields incomplete local perception and limited task efficiency.
We study the contextual combinatorial semi-bandit (CCSB) problem with general reward function approximation. At each round, the learner observes a context, selects a combinatorial action consisting of a subset of basic arms, and receives the reward of each selected arm; the goal is to maximize the cumulative reward over time.
Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.