Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2602. 19327v3 Announce Type: replace Abstract: A significant portion of recent research on Large Language Model (LLM) alignment focuses on developing new policy optimization methods based on Group Relative Policy Optimization (GRPO).
arXiv:2604. 26269v2 Announce Type: replace-cross Abstract: In the era of large language models, creative writing quality lacks a computable theoretical anchor.
arXiv:2606. 05201v1 Announce Type: new Abstract: Reasoning language models do not distinguish tokens used for computation from tokens that constitute persistent state: once generated, all hidden thoughts remain in context and influence future predictions.
arXiv:2601. 09236v3 Announce Type: replace Abstract: Reward design remains a significant bottleneck in applying reinforcement learning (RL) to real-world problems.
arXiv:2606. 06096v1 Announce Type: new Abstract: Policy-gradient methods usually optimize expected return, but many real world applications care about distributional properties of returns: tail risk, outlier robustness, or best-of-K discovery.
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: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.
Robot manipulation alternates between low-risk transit phases that call for fast execution and high-risk contact stages that demand slow, precise motion. Yet existing Vision-Language-Action models (VLAs) only inherit a single fixed speed from training demonstrations.
arXiv:2606. 04328v1 Announce Type: cross Abstract: Future wireless networks demand rapid adaptation to highly heterogeneous environments and dynamic task configurations, necessitating a shift from conventional rule-based and optimization-driven radio resource management (RRM) toward artificial intelligence (AI)-driven RRM.
arXiv:2606. 04781v1 Announce Type: new Abstract: Agent Skills today consist largely of free-form prose requiring the agent to read, interpret, and re-derive how to act in every session.
arXiv:2606. 05152v1 Announce Type: cross Abstract: Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sample many responses and reward each with a single bit indicating whether the final answer is correct.
arXiv:2606. 04053v1 Announce Type: cross Abstract: The Boolean Task Algebra (BTA) provides a principled framework for zero-shot task composition in reinforcement learning by equipping goal-reaching tasks with Boolean operations.
arXiv:2606. 04634v1 Announce Type: new Abstract: Trust in a decision-making system requires both safety guarantees and the ability to interpret and understand its behavior.
arXiv:2606. 04188v1 Announce Type: cross Abstract: Offline goal-conditioned reinforcement learning requires both long-horizon reachability estimates and local action comparisons.
arXiv:2603. 10971v2 Announce Type: replace-cross Abstract: Reinforcement learning has achieved remarkable success in domains such as Atari games, navigation, and locomotion, where exploration can often be guided by novelty over states or dynamics.
arXiv:2601. 07036v2 Announce Type: replace-cross Abstract: Hybrid reasoning language models are commonly controlled through high-level Think/No-think instructions to regulate reasoning behavior, yet we found that such mode switching is largely driven by a small set of trigger tokens rather than the instructions themselves.
arXiv:2606. 04272v1 Announce Type: new Abstract: The standard LLM training pipeline applies reinforcement learning (RL) only after pre-training and supervised fine-tuning (SFT).
arXiv:2606. 04749v1 Announce Type: cross Abstract: Safe robot control requires maximizing return while satisfying safety constraints.
arXiv:2606. 04335v1 Announce Type: new Abstract: The framework of robust Markov decision processes (RMDPs) allows the design of reinforcement learning agents that satisfy performance guarantees under worst-case transition dynamics.
arXiv:2606. 05106v1 Announce Type: cross Abstract: We investigate whether methods of human mathematics pedagogy can guide the training of language models toward arithmetic reasoning.