Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2610.27632v1 Announce Type: new Abstract: A learned scientific controller can outperform a misspecified planner without benefiting from feedback. We audit two synthetic voltage-clamp tasks with...
arXiv:2610.27936v1 Announce Type: new Abstract: Unmanned aerial vehicles (UAVs) enable fast, flexible last-mile and emergency delivery, but their routing remains challenging as the number of clients...
arXiv:2610.27467v1 Announce Type: cross Abstract: On-policy learning is central to post-training: training on a model's own generations limits distribution shift and helps preserve existing capabilit...
arXiv:2610.28586v1 Announce Type: cross Abstract: Agentic on-policy distillation (OPD) trains a student agent on its own trajectories while a teacher scores every token. A natural explanation of wher...
arXiv:2508.20784v3 Announce Type: replace Abstract: Bus bunching remains a challenge for urban transit due to stochastic traffic and passenger demand. Traditional solutions rely on multi-agent reinfo...
arXiv:2512.23067v3 Announce Type: replace Abstract: Personalized alignment from preference data has focused primarily on improving personal reward model (RM) accuracy, with the implicit assumption th...
arXiv:2609.34575v2 Announce Type: replace Abstract: Offline goal-conditioned reinforcement learning (GCRL) learns goal-directed policies from reward-free data, but in long-horizon tasks, goal-conditi...
arXiv:2610.25496v2 Announce Type: replace Abstract: In many human-AI systems, candidate actions are not executed directly but are first evaluated by another decision-making entity under a potentially...
arXiv:2601.21669v2 Announce Type: replace-cross Abstract: Many reinforcement learning (RL) problems admit multiple terminal solutions of comparable quality, where the goal is not to identify a single...
arXiv:2603.00889v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have exhibited remarkable reasoning capabilities, largely enabled by supervised fine-tuning (SFT)- and reinforce...
arXiv:2610.25916v2 Announce Type: replace-cross Abstract: As coding models and agent harnesses become more capable, reliable security verification is becoming a central bottleneck. Improving secure c...
arXiv:2610.25946v2 Announce Type: replace-cross Abstract: Developing coordination policies for complex multi-agent systems relies on either labor-intensive algorithm design or opaque task-specific re...
arXiv:2610.27575v1 Announce Type: new Abstract: Model-based reinforcement learning in partially observable environments requires inferring hidden states, learning latent dynamics, and planning under...
arXiv:2610.27623v1 Announce Type: new Abstract: Reinforcement learning for long-horizon language agents requires identifying whether intermediate actions make eventual task success more or less likel...
arXiv:2610.28027v1 Announce Type: new Abstract: Practitioners use reinforcement learning methods for language models through training frameworks, so a method that a framework includes is one configur...
arXiv:2610.27606v1 Announce Type: cross Abstract: Offline reinforcement learning is fundamentally limited by the coverage of the available data, while collecting additional trajectories through onlin...
arXiv:2610.28360v1 Announce Type: cross Abstract: In reinforcement learning, one presumes the action set to be known ahead of time, and, thus, one must know if any state-action pairs are not permissi...
arXiv:2605.14978v3 Announce Type: replace Abstract: Speculative decoding accelerates LLM inference by having a lightweight draft model propose speculative windows of candidate tokens for parallel ver...
arXiv:2610.27341v1 Announce Type: new Abstract: Vision-language models (VLMs) have advanced rapidly in multimodal reasoning, yet they remain limited on tasks requiring fine-grained understanding of s...
arXiv:2601.07823v2 Announce Type: cross Abstract: Video world models have emerged as promising candidates for high-fidelity world models, offering the potential to synthesize high-quality videos capt...