Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2510. 21084v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown strong potential for clinical decision support through their advanced language understanding and reasoning capabilities.
arXiv:2608. 05080v1 Announce Type: new Abstract: Critic-free group-based reinforcement learning has become a scalable approach for post-training large language models.
arXiv:2608. 04962v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training improves the reasoning capabilities of large language models, but autoregressive rollout generation remains a major efficiency bottleneck.
arXiv:2511. 15669v3 Announce Type: replace-cross Abstract: Does Chain-of-Thought (CoT) reasoning genuinely improve Vision Language Action (VLA) models, or does it merely add overhead?
arXiv:2604. 00513v3 Announce Type: replace-cross Abstract: With the rapid growth of e-commerce, exploring general representations rather than task-specific ones has attracted increasing attention.
arXiv:2608. 04124v1 Announce Type: cross Abstract: Video question answering requires models to ground language queries in visual evidence and, when necessary, reason over that evidence across time.
arXiv:2508. 04780v2 Announce Type: replace-cross Abstract: The increasing frequency of extreme weather events, such as hurricanes, highlights the urgent need for efficient and equitable power system restoration.
arXiv:2508. 18066v2 Announce Type: replace-cross Abstract: Controlling high-dimensional and nonlinear musculoskeletal models of the human body is a foundational scientific challenge.
arXiv:2601. 12401v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning large-scale generative models, such as diffusion and flow models, to align with complex human preferences and user-specified tasks.
arXiv:2510. 20748v2 Announce Type: replace-cross Abstract: This paper demonstrates how reinforcement learning can explain two puzzling empirical patterns in household consumption behavior during economic downturns.
arXiv:2508. 13661v4 Announce Type: replace Abstract: Centralized Training with Decentralized Execution (CTDE) is the dominant paradigm in multi-agent reinforcement learning (MARL), enabling agents to act independently at test time while leveraging additional information during training.
arXiv:2608. 04334v1 Announce Type: cross Abstract: Contemporary model-free reinforcement learning algorithms can achieve very high performance, but have low sample efficiency and are not robust to changes in the environment.
arXiv:2408. 05885v3 Announce Type: replace Abstract: Generative Flow Networks (GFlowNets) have been shown effective to generate combinatorial objects with desired properties.
arXiv:2608. 04999v1 Announce Type: cross Abstract: Analog circuit design automation using reinforcement learning (RL) has emerged as a promising approach for reducing manual effort.
arXiv:2511. 07322v3 Announce Type: replace-cross Abstract: While LLMs have shown great success in financial tasks like stock prediction and question answering, their application in fully automating Equity Research Report generation remains uncharted territory.
arXiv:2503. 10367v2 Announce Type: replace-cross Abstract: Edge devices host domain-specific small language models (SLMs) with limited resources, while private clouds offer larger LLMs.
arXiv:2608. 02087v2 Announce Type: replace Abstract: Post-training Large Language Models (LLMs) with Reinforcement Learning (RL) has become an important tool for improving model capabilities, but the LLM action-space structure introduces challenges distinct from classical RL, with implications for inducing exploration.
arXiv:2608. 04333v1 Announce Type: new Abstract: Large language model (LLM) configuration evaluation is challenging due to limited evaluation budgets, varying costs, and multiple competing objectives.
arXiv:2608. 05102v1 Announce Type: new Abstract: Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer.
Long-horizon reasoning in recent LLMs demands that the model switch between distinct skills inside a reasoning chain, such as first doing a math derivation, then using the result to plan a schedule. We call such problems cross-skill long-horizon tasks: multi-step tasks whose steps require different reasoning skills and depend on earlier outputs.