Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2605. 12410v2 Announce Type: replace-cross Abstract: We propose and analyze a model-based bootstrap for transition kernels in finite controlled Markov chains (CMCs) with possibly nonstationary or history-dependent control policies, a setting that arises naturally in offline reinforcement learning (RL) when the behavior policy generating the data is unknown.
arXiv:2607. 05711v1 Announce Type: new Abstract: Diffusion models have become a dominant paradigm for high-quality generative modeling, while post-training is essential for adapting them to diverse downstream applications.
arXiv:2607. 06175v1 Announce Type: cross Abstract: Large language models (LLMs) can generate BPMN process models from natural-language descriptions, yet supervised fine-tuning (SFT) limits their output quality to the patterns present in the training data.
arXiv:2502. 15631v2 Announce Type: replace-cross Abstract: Large language models have demonstrated remarkable progress in mathematical reasoning, leveraging chain-of-thought and reinforcement learning.
arXiv:2605. 24709v2 Announce Type: replace Abstract: Streaming reinforcement learning has emerged as an online learning paradigm that conforms to the restrictions of natural learning agents that process data incrementally, i.
arXiv:2607. 05458v1 Announce Type: cross Abstract: Large language model (LLM) agents are usually improved by changing prompts, models, or hand-written workflows, while the execution harness around the model is treated as fixed infrastructure.
arXiv:2607. 05773v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into autonomous agents, traditional static evaluation fails to capture multi-step decision-making.
arXiv:2511. 06229v3 Announce Type: replace Abstract: This paper focuses on dynamic origin-destination matrix estimation (DODE), a crucial calibration process necessary for the effective application of microscopic traffic simulations.
arXiv:2506. 09276v4 Announce Type: replace-cross Abstract: This paper presents a state representation framework for Markov decision processes (MDPs) that can be learned solely from state trajectories, requiring neither reward signals nor the actions executed by the agent.
arXiv:2607. 02998v2 Announce Type: replace-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. 05794v1 Announce Type: new Abstract: Long-term user memory is essential for personalized conversational agents, yet many memory systems still expose memory through passive retrieval interfaces, making the model a consumer of pre-selected evidence.
arXiv:2607. 05609v1 Announce Type: cross Abstract: The Continual Learning (CL) literature has long been driven by the goal of mitigating catastrophic forgetting.
arXiv:2607. 05904v1 Announce Type: new Abstract: Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness.
arXiv:2607. 05541v1 Announce Type: cross Abstract: Reinforcement Learning is commonly used to train large language models using environmental feedback.
arXiv:2607. 06401v1 Announce Type: new Abstract: World models -- internal simulators that learn the structure and dynamics of an environment -- have become one of the most actively debated concepts in AI.
We present FootsiesGym, an open-source environment for learning in a non-trivial two-player, zero-sum, imperfect-information game. Built on HiFight's minimalist 2D fighting game Footsies, it isolates the cyclic, non-transitive strategic interactions of fighting game neutral play while remaining simple enough for efficient analysis.
World models -- internal simulators that learn the structure and dynamics of an environment -- have become one of the most actively debated concepts in AI. From model-based reinforcement learning and video generation to embodied robotics and ultimately, physical AI, researchers across AI subfields are building systems that they call "world models", yet there is no consensus on what a world model fundamentally is, what it should predict, or how it should be built.
Large language model (LLM) agents require post-training methods that can improve long-horizon decision making from environment feedback. However, existing agentic post-training pipelines often treat data curation as a fixed preprocessing step, focusing mainly on data augmentation while neglecting filtering, refinement, and adaptation to downstream failures.
Compositional Zero-Shot Learning (CZSL) aims to combine known attributes and objects as primitives for recognizing previously unseen attribute-object pairs. Prior works either predict attributes and objects independently, missing their strong contextual dependency, or use unidirectional conditional modeling (e.
arXiv:2602. 17658v3 Announce Type: replace-cross Abstract: Reward modeling is central to alignment pipelines such as RLHF, RLAIF, and PPO-based policy optimization, yet its reliability is constrained by limited and heterogeneous human preference data that are expensive to collect at scale.