Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2606. 27472v1 Announce Type: cross Abstract: Large language model (LLM) agents operate over long, multi-session interactions in which facts change: a user moves, a price updates, a plan is revised.
arXiv:2606. 27483v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated strong capability in sequential decision-making, yet they remains fundamentally reactive in long-horizon tasks.
arXiv:2606. 27814v1 Announce Type: new Abstract: Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement.
arXiv:2606. 27721v1 Announce Type: new Abstract: Compositional generalization, the ability to solve complex problems by combining solutions to simpler sub-problems, is a fundamental capability of both natural and artificial intelligence, and a key mechanism underlying chain-of-thought reasoning.
arXiv:2606. 28166v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has significantly improved the reasoning capability of large language models, reaching expert or even superhuman performance in domains such as competition math.
arXiv:2603. 00374v2 Announce Type: replace Abstract: Offline learning of strategies takes data efficiency to its extreme by restricting algorithms to a fixed dataset of state-action trajectories.
arXiv:2606. 27939v1 Announce Type: cross Abstract: Protein language models are standard priors for biological sequence generation, but steering them toward explicit distributional design targets remains largely unexplored.
arXiv:2606. 27926v1 Announce Type: new Abstract: Geometry Problem Solving have increasingly adopt the neuro-symbolic paradigm, combining neural intuition with symbolic rigor.
arXiv:2511. 00609v4 Announce Type: replace Abstract: Personalized image preference assessment aims to evaluate an individual user's image preferences by relying only on a small set of reference images as prior information.
arXiv:2606. 27771v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training improves the reward alignment of flow-based generators, but often degrades perceptual quality in ways that are not captured by the reward proxy.
arXiv:2606. 27736v1 Announce Type: new Abstract: The rapid spread of fake news poses increasing threats to information ecosystems, especially as AI-generated misinformation under Generative Engine Optimization (GEO) poisoning allows adversarially crafted content to be systematically surfaced by retrieval systems, contaminating LLM reasoning.
arXiv:2606. 27652v1 Announce Type: new Abstract: We find that explicit reasoning does not necessarily translate into better multimodal emotion recognition (MER) accuracy, even though it makes predictions more interpretable.
arXiv:2606. 27580v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) in production does not always have a synchronous reward signal.
arXiv:2602. 09456v2 Announce Type: replace Abstract: We propose an algorithmic framework, Offline Estimation to Decisions (OE2D), that efficiently reduces contextual bandit learning with general reward function approximation to offline regression.
arXiv:2502. 06577v3 Announce Type: replace-cross Abstract: Causal knowledge can be used to support decision-making problems.
arXiv:2506. 10355v2 Announce Type: replace Abstract: Many real-world applications collect data in a streaming environment, where learning tasks are encountered sequentially.
arXiv:2506. 01442v2 Announce Type: replace Abstract: Reinforcement learning (RL) remains fundamentally limited by poor data efficiency and weak generalization.
arXiv:2606. 28152v1 Announce Type: new Abstract: We propose KL-Coupled Policy Regularization (KCPR), a policy coordination framework for Reward-Punishment Reinforcement Learning (RPRL).
arXiv:2606. 27922v1 Announce Type: cross Abstract: Current multimodal reflection mechanisms for long video understanding predominantly rely on closed-loop self-reflection within internal parameters.
arXiv:2507. 10005v2 Announce Type: replace Abstract: In recent years, graph-based machine learning techniques, such as reinforcement learning and graph neural networks, have garnered significant attention.