Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2607. 21831v1 Announce Type: new Abstract: We present a traffic-signal control interface in which a shared graph neural network assigns scores to individual traffic movements.
arXiv:2607. 21971v1 Announce Type: new Abstract: Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains.
arXiv:2607. 21653v1 Announce Type: new Abstract: Agentic reinforcement learning research is constant algorithm modification, new estimators, new pipeline stages, new rollout schemes, and in mainstream frameworks each change threads through layers of trainer, distributed backend, and rollout glue: the cost lands on the researcher at every iteration.
arXiv:2607. 21637v1 Announce Type: new Abstract: This paper explores the efficacy of quasi-Monte Carlo (QMC) weight initialization for meta-reinforcement learning within modern benchmark environments.
arXiv:2607. 22012v1 Announce Type: new Abstract: Off-Policy Evaluation and Learning (OPE/L) in contextual bandits is rapidly gaining popularity in real systems because new policies can be evaluated and learned securely using only historical logged data.
arXiv:2607. 21627v1 Announce Type: cross Abstract: End-to-end reinforcement learning can improve the accuracy of compound LLM systems, but it does not constrain how modules divide labor internally.
arXiv:2603. 05789v5 Announce Type: replace-cross Abstract: Repeated multi-agent interactions require evaluation metrics that capture not only payoff distributions but also their temporal organization.
arXiv:2607. 21876v1 Announce Type: new Abstract: We investigate a decentralized reinforcement learning problem involving multiple agents that interact with the same Markov Decision Process (MDP).
arXiv:2601. 09825v3 Announce Type: replace Abstract: We establish a lower bound on the eluder dimension of generalised linear model classes, showing that standard eluder dimension-based analysis cannot lead to first-order regret bounds.
arXiv:2607. 22465v1 Announce Type: cross Abstract: Routing to select large language models (LLMs) with different cost-quality trade-offs has become a fundamental deployment feature of enterprise AI.
arXiv:2607. 22356v1 Announce Type: new Abstract: In recent years, the growing complexity of last-mile pickup operations has increased the need for fast and accurate decision-making on logistics platforms.
arXiv:2607. 21610v1 Announce Type: cross Abstract: Schema graphs are an upstream bottleneck of schema-grounded information extraction and knowledge graph construction, yet most extraction systems assume the schema is already available.
arXiv:2601. 17454v2 Announce Type: replace-cross Abstract: Centralized value learning underlies a broad class of multi-agent reinforcement learning methods, but its claimed advantage is typically evaluated in settings that confound coordination structure with function approximation and partial observability.
Reinforcement Learning with Verifiable Rewards (RLVR) has driven recent progress in reasoning-oriented large language models (LLMs) by enabling large-scale optimization. However, its applicability remains largely limited to domains such as mathematics and coding, where correctness can be deterministically verified.
Pathological diagnosis is inherently multi-scale, requiring the integration of global tissue architecture at low magnification with cellular morphology at higher magnification. However, existing pathology benchmarks and vision-language models (VLMs) are still largely developed under single-scale settings, limiting their ability to learn clinically meaningful multi-magnification reasoning.
Safe quadrotor navigation in cluttered and dynamic environments depends not only on instantaneous geometric perception, but more critically on anticipating collision risks induced by relative motion. Conventional modular pipelines frequently suffer from perception latency, while end-to-end learning methods relying on implicit scalar rewards often struggle to extract reliable spatio-temporal features without physics-grounded supervision.
abbel-fig { display: block; text-align: center; margin: 2. 4em 0; line-height: 1.
Text-to-image diffusion models expose many inference-time sampling parameters, including prompts, negative prompts, classifier-free guidance scales, and noise schedules. These parameters are typically manually chosen once and then held fixed across prompts and denoising timesteps, even though different prompts and stages of generation can benefit from different parameter values.
This paper develops an online, off-policy policy-iteration framework for reinforcement learning (RL), based on sparse Gaussian-mixture-model Q-functions (S-GMM-QFs). The framework reconciles streaming, non-stationary data with the Riemannian structure of the parameter space while handling distributional mismatch through experience replay.
Group Relative Policy Optimization (GRPO) is the dominant reinforcement learning algorithm for training reasoning capabilities in large language models, notably adopted by DeepSeek-R1. The recent improvement Dr.