Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2607. 18966v1 Announce Type: new Abstract: Language models trained with reinforcement learning may learn to optimize the grader's judgment rather than the intended objective.
arXiv:2603. 16410v2 Announce Type: replace-cross Abstract: Creative plot generation presents a fundamental challenge for language models: transforming a concise premise into a coherent narrative that sustains global coherence, character development, pacing, tone consistency, and emotional progression.
arXiv:2607. 18722v1 Announce Type: new Abstract: Asynchronous reinforcement learning improves throughput by decoupling rollout generation from optimization, but staleness is an inevitable byproduct compounded by policy lag, engine delays, and mixture-of-experts routing.
arXiv:2607. 19313v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models.
arXiv:2607. 18470v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback, where sampled rollouts can be compared within a group using task-provided correctness signals.
arXiv:2607. 18955v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models on tasks such as mathematical reasoning and code generation.
arXiv:2607. 19044v1 Announce Type: new Abstract: Leveraging large language models (LLMs) for molecular generation has shown remarkable potential in chemical and drug design.
arXiv:2511. 08436v2 Announce Type: replace-cross Abstract: How complex collective behavior emerges from individual interactions is a fundamental scientific question, but experimental cost and difficulty of simultaneous multi-brain recordings limit direct study in animals.
arXiv:2508. 14751v2 Announce Type: replace Abstract: We study goal-conditioned reinforcement learning in partially observable environments with sparse rewards and large, structured goal spaces.
arXiv:2607. 18830v1 Announce Type: cross Abstract: Model-Agnostic Meta-Learning (MAML) is a widely used framework for reinforcement learning (RL) that enables efficient transfer by learning global policy parameters that can be rapidly adapted to new tasks.
arXiv:2607. 19232v1 Announce Type: new Abstract: Hierarchical Reinforcement Learning (HRL) intends to separate strategic planning from primitive execution.
arXiv:2607. 18985v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in language understanding, reasoning, and world knowledge.
In RLHF pipelines, reward scoring blocks policy updates. Slow scoring bottlenecks the entire loop, since no update runs until every rollout gets a score.
Robots deployed in delivery, campus, and emergency-response settings often need to navigate from buildings to streets within a single continuous episode. Existing benchmarks usually evaluate indoor and outdoor navigation separately, and many abstract away robot execution, leaving exit finding, boundary traversal, adaptation, and kinodynamic failures underexplored.
Recent advances in multimodal generative models have enabled instruction-based image generation to move beyond semantic manipulation to knowledge-driven visual reasoning. However, these methods focus on explicit commonsense reasoning, shallow causal understanding, and direct knowledge recall, failing at knowledge-intensive generation.
Long audio-video reasoning is difficult for omnimodal LLMs because the decisive evidence is often sparse, cross-modal, and too expensive to preserve with uniformly high-fidelity inputs. We introduce OmniReasoner, a tool-use post-training framework for Thinking with Long Audio-Video: omni-modal LLMs learn, via supervised fine-tuning and reinforcement learning, to decide whether and where to call a zoom-in tool before answering.
Large language models (LLMs) have been widely applied to automated essay scoring (AES) and automated feedback generation (AFG). However, existing studies rely primarily on prompt engineering or supervised fine-tuning, while systematic research on reinforcement learning (RL) post-training and automated evaluation of feedback quality remains limited.
Large-scale online reinforcement learning (RL) is the predominant means of eliciting advanced abilities including long-term reasoning and agentic tool use in large language models (LLMs). However, continuing to scale it across vast task domains of interest remains challenging in both computational infrastructure and cost, especially when considering RL as merely a one-off learning stage.
Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to-image generation and instruction-based image editing.
Medical imaging is a cornerstone of diagnostics, yet automated chest X-ray report generation struggles with structural adherence, anatomical completeness, and semantic faithfulness. We introduce DobicVLM, a vision-language model combining supervised fine-tuning on MedGemma-4B with Group Relative Policy Optimization (GRPO) and clinically-grounded programmatic rewards.