Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2512. 15765v3 Announce Type: replace Abstract: Data valuation is a natural framework for understanding which preference datasets matter most when aligning a Large Language Model (LLM) using multiple sources.
arXiv:2607. 03903v1 Announce Type: new Abstract: Multi-task offline safe reinforcement learning (RL) promises to learn a shared optimal safe policy from offline data across multiple tasks.
arXiv:2607. 02781v1 Announce Type: cross Abstract: Inference-time alignment steers a frozen language model during decoding using auxiliary reward signals, avoiding the cost of repeated weight updates.
arXiv:2601. 07376v2 Announce Type: replace Abstract: We introduce \textsc{OpenTinker}, an open infrastructure for training large language model (LLM) agents with many LoRA-backed policies over shared execution resources.
arXiv:2607. 05199v1 Announce Type: new Abstract: Physics reasoning fails structurally in small language models: an error at any step propagates forward, corrupting every inference that follows.
arXiv:2601. 21523v2 Announce Type: replace Abstract: To promote cooperation in Multi-Agent Reinforcement Learning, the reward signals of all agents can be aggregated together, forming global rewards that are commonly known as the fully cooperative setting.
arXiv:2607. 02998v1 Announce Type: cross Abstract: Controllable generative models of 3D medical images can synthesize volumes with specified clinical attributes, but this demands samples that are simultaneously high-fidelity, natively 3D, and faithful to the requested conditioning.
arXiv:2607. 04616v1 Announce Type: cross Abstract: Linear-deformable manipulation remains challenging due to the complex deformations of objects such as cables and ropes.
arXiv:2607. 04096v1 Announce Type: new Abstract: Current agentic workflows usually involve decomposing user requests into sequences of tool calls with correctly resolved parameters, the results of which are processed through reasoning traces in the language model's context window.
arXiv:2607. 04710v1 Announce Type: new Abstract: Inducing cooperation among distributed agents is still a difficult problem in the field of multi-agent reinforcement learning (MARL), particularly in social dilemma situations.
arXiv:2607. 03176v1 Announce Type: new Abstract: Understanding how households consume electricity in response to socioeconomic and climatic drivers is important for decision-makers designing energy policies in a changing climate and under geopolitical tensions.
arXiv:2607. 04383v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) reason fluently about sound yet struggle to localize precisely when events occur, while classical Sound Event Detection attains frame-level precision only over a closed label set.
arXiv:2607. 03248v1 Announce Type: cross Abstract: The alignment of large language models with human preferences is commonly achieved through Reinforcement Learning from Human Feedback or Direct Preference Optimization.
Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because the target model must generate many rollouts during training. As models scale, post-training itself becomes a bottleneck.
Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we identify verification, the ability to determine the correctness of a solution, as a new scaling axis.
Occupancy ratios correct distribution shift in offline reinforcement learning and are central to off-policy evaluation. Existing primal-dual and minimax methods typically estimate these ratios by enforcing occupancy-balance moments over a critic class.
Inference serving systems must balance throughput and latency under bursty, heterogeneous workloads, yet the industry standard remains static batching policies that require manual tuning and cannot adapt to shifting traffic. We investigate whether reinforcement learning (RL) can learn adaptive batching and routing policies that outperform these heuristics, training REINFORCE and PPO agents on a discrete-event simulator validated against queuing theory and production traces (Azure Functions, BurstGPT).
Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-text LLM built on Nemotron-Cascade-2-30B-A3B, a strong text-only MoE LLM.
In this paper, we introduce Claim-Level Rubric Rewards (CuRe), a structured reward framework designed to address the reward-design bottleneck in reinforcement learning for dense video captioning. Existing reward designs generally fall into two categories: holistic response-level judgment across heterogeneous criteria, or alignment-based evaluation against reference captions.
Reinforcement Learning (RL) is the dominant paradigm for training Large Language Model (LLM) agents on long-horizon tasks. However, sparse and delayed rewards often lead to trajectory neglect, in which agents lose focus on the task goal and interaction history at intermediate steps.