Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2606. 03077v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a standard post-training paradigm for large language models (LLMs), extending beyond preference alignment to complex reasoning and multi-turn agentic behaviors.
arXiv:2601. 12186v3 Announce Type: replace-cross Abstract: Multi-domain thinking verifiers trained via Reinforcement Learning with Verifiable Rewards (RLVR) are a cornerstone of modern post-training.
arXiv:2602. 06219v2 Announce Type: replace-cross Abstract: World models offer a promising avenue for more faithfully capturing complex dynamics, including contacts and non-rigidity, as well as complex sensory information, such as visual perception, in situations where standard simulators struggle.
arXiv:2507. 21638v2 Announce Type: replace Abstract: The development of reinforcement learning (RL) algorithms has been largely driven by ambitious challenge tasks and benchmarks.
arXiv:2604. 27660v3 Announce Type: replace Abstract: Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge.
arXiv:2506. 21129v2 Announce Type: replace-cross Abstract: Autonomous unmanned aerial vehicles (UAVs) increasingly rely on reinforcement learning (RL) for navigation.
arXiv:2606. 03201v1 Announce Type: cross Abstract: Reinforcement learning from expert videos across visually distinct domains is challenging due to the absence of reward signals and the presence of domain gaps.
Diffusion large language models (dLLMs) generate responses by iteratively unmasking and revising many positions in parallel. This process leaves a rich denoising trace depicting which tokens become confident, which remain unstable, and when commitments form.
Large Language Models (LLMs) show promise in psychological counseling, yet existing benchmarks rely heavily on highly cooperative simulated clients. We observe a critical counselor-following phenomenon: these clients often rapidly shift from resistance to compliance after only a few turns, creating an illusion of therapeutic progress and inflating scores under current evaluation protocols through superficial empathy.
The framework of robust Markov decision processes (RMDPs) allows the design of reinforcement learning agents that satisfy performance guarantees under worst-case transition dynamics. Traditional RMDPs consider discrete-time dynamics and recently, sample-efficient policy gradient algorithms have been considered in this context.
Reward models (RMs) provide critical feedback signals for LLM post-training, notably in reinforced fine-tuning (RFT) and reinforcement learning (RL) pipelines. However, current reward evaluation relies on heterogeneous criteria such as rule-based verifiers, ground-truth references, procedural checklists, and complex rubrics, where a unified mechanism to integrate all types of evidence remains unexplored.
Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward. Yet, modern applications such as language model fine-tuning or scientific discovery demand diversity.
To improve the real-world applicability of reinforcement learning (RL), the field of adversarially robust RL studies how to train agents under adversarial environment perturbations. In this setting, a protagonist agent optimizes a policy under environmental perturbations from an adversary, resulting in a zero-sum Markov game.
While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data. Current alignment techniques, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), typically apply coarse-grained optimization at the sequence level.
While Proximal Policy Optimization (PPO) demonstrates strong performance in stationary settings, we show that its standard optimization paradigm struggles in continual and non-stationary environments. The failure does not stem from insufficient model capacity or overly restrictive clipping.
arXiv:2511. 09190v2 Announce Type: replace Abstract: Hyperparameter Optimization (HPO) can lift the burden of tuning hyperparameters (HPs) of neural networks.
arXiv:2606. 01160v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used with formal interactive theorem provers such as Lean 4.
arXiv:2606. 00135v1 Announce Type: cross Abstract: Tool-calling is a central component of modern large language model (LLM) agents, equipping them with skills beyond their parametric knowledge.
arXiv:2606. 01159v1 Announce Type: new Abstract: We study two-player zero-sum games (TPZSGs) with bandit feedback under fairness constraints requiring every action to be played with probability at least $\alpha/m$.
arXiv:2606. 00739v1 Announce Type: new Abstract: Large language models hallucinate even when the answer lies within their parameters.