Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2311. 07565v3 Announce Type: replace Abstract: We introduce exploration via linear loss perturbations (EVILL), a randomised exploration method for structured stochastic bandit problems that works by solving for the minimiser of a linearly perturbed regularised negative log-likelihood function.
arXiv:2605. 23415v2 Announce Type: replace Abstract: Reinforcement learning has long struggled with poor sample efficiency.
arXiv:2602. 16965v2 Announce Type: replace Abstract: We study the decentralized multi-player stochastic bandit problem over a continuous, Lipschitz-structured action space where hard collisions yield zero reward.
arXiv:2606. 05296v1 Announce Type: new Abstract: LLM agents operate in two distinct regimes: open-weight agents amenable to reinforcement learning (RL) and black-box agents whose behaviour must be controlled purely at test time.
arXiv:2605. 08253v2 Announce Type: replace Abstract: Distributional reinforcement learning (DRL) models the full return distribution, but existing finite-support or quantile-based methods rely on projections, while recent flow-based approaches can suffer from \emph{boundary mismatch} at the flow source or from \emph{high-variance} bootstrapping when current and successor noises are independent.
arXiv:2604. 26269v2 Announce Type: replace-cross Abstract: In the era of large language models, creative writing quality lacks a computable theoretical anchor.
arXiv:2602. 08503v2 Announce Type: replace-cross Abstract: Self-correction is essential for solving complex reasoning problems in vision-language models (VLMs).
arXiv:2512. 09706v2 Announce Type: replace Abstract: The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models.
arXiv:2602. 19373v3 Announce Type: replace Abstract: Deep reinforcement learning systems often suffer from unstable training dynamics due to non-stationarity, where learning objectives and data distributions evolve over time.
arXiv:2606. 05885v1 Announce Type: new Abstract: Long-horizon LLM agents require reinforcement learning methods that can assign credit to intermediate decisions under sparse and delayed rewards.
arXiv:2606. 05932v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (RLVR) improves reasoning even when the reward signal is spurious -- assigning credit to the group-plurality answer rather than a ground-truth verifier.
arXiv:2606. 05625v1 Announce Type: cross Abstract: Implicit reward hacking is hard to audit when a language model's chain of thought appears benign: a final answer may be anchored by a prompt shortcut while the written reasoning still resembles ordinary problem solving.
arXiv:2512. 20111v2 Announce Type: replace-cross Abstract: As the time horizons of sequential decision-making tasks grow, keeping full interaction histories in model context becomes increasingly costly.
arXiv:2511. 21667v4 Announce Type: replace Abstract: Training Large Language Models (LLMs) to reason often relies on Reinforcement Learning (RL) with task-specific verifiers.
arXiv:2606. 05208v1 Announce Type: cross Abstract: Reinforcement Learning (RL) has long been a powerful solution to various problems in communication networks.
arXiv:2606. 05376v1 Announce Type: new Abstract: Many human-centered tasks, including natural language inference (NLI) and emotion recognition (ER), have multiple plausible interpretations, leading to label ambiguity and challenging disagreements across human annotators.
arXiv:2606. 05253v1 Announce Type: new Abstract: Large language models (LLMs) have shown increasing promise in generating functionally correct register-transfer-level (RTL) hardware designs.
arXiv:2605. 25582v2 Announce Type: replace Abstract: Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces distribution mismatch that existing trust-region techniques mitigate primarily by enforcing conservative optimization, often leaving rich training signals underutilized.
arXiv:2605. 21557v2 Announce Type: replace-cross Abstract: Conventional wisdom holds that large-batch training is fundamentally incompatible with Reinforcement Learning (RL) - beyond a modest threshold, increasing batch sizes typically yields diminishing returns or performance degradation due to the inherent non-stationarity of the data distribution.
arXiv:2606. 06475v1 Announce Type: new Abstract: Recent advancements in reasoning language models have been driven by Reinforcement Learning (RL) fine-tuning.