Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2608. 09435v1 Announce Type: new Abstract: Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time.
arXiv:2411. 01302v2 Announce Type: replace Abstract: We study the convergence of $q$-learning and related algorithms introduced by Jia and Zhou (J.
arXiv:2608. 08604v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) is a powerful framework for solving complex collaborative tasks, but it relies heavily on well-defined global reward functions.
arXiv:2608. 09226v1 Announce Type: cross Abstract: Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression.
arXiv:2608. 07547v1 Announce Type: cross Abstract: Indoor scene layout generation is a challenging task in interior design.
arXiv:2608. 09128v1 Announce Type: cross Abstract: LLM agents are increasingly deployed in multi-agent social settings where they must cooperate, negotiate, and adapt to other agents.
arXiv:2605. 00754v4 Announce Type: replace-cross Abstract: Reward models (RMs) have become an indispensable fixture of the language model (LM) post-training playbook, enabling policy alignment and test-time scaling.
arXiv:2608. 09119v1 Announce Type: new Abstract: We introduce Motif 3, a decoder-only Mixture-of-Experts language model with 314 billion total parameters and 13.
arXiv:2608. 07870v1 Announce Type: new Abstract: Improving sample efficiency remains a core challenge in reinforcement learning (RL), especially in real-world settings like robotics, where data collection is costly.
arXiv:2608. 09138v1 Announce Type: cross Abstract: While learned robotic policies hold promise for advancing generalizable manipulation, their practical deployment is often hindered by suboptimal execution speeds.
arXiv:2608. 08219v1 Announce Type: cross Abstract: Video anomaly detection (VAD) is a critical yet challenging task due to the complex and diverse nature of real-world scenarios.
arXiv:2608. 07527v1 Announce Type: cross Abstract: Long-document understanding requires models to find and combine evidence across many pages, layouts, tables, figures, and charts.
arXiv:2605. 12991v3 Announce Type: replace-cross Abstract: LLM-based multi-agent pipelines flip from correct to incorrect answers under simulated peer disagreement at rates we term yield, a vulnerability widely attributed to RLHF-induced sycophancy.
arXiv:2608. 09217v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a central post-training paradigm for eliciting reasoning capabilities in large language models, yet uniform task sampling allocates compute without regard to differences in how tasks respond to optimization.
arXiv:2604. 23333v2 Announce Type: replace Abstract: Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability.
arXiv:2608. 08255v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) often suffers from delayed and sparse rewards in real-world environments.
arXiv:2608. 08878v1 Announce Type: cross Abstract: Transformer-based large language models (LLMs) achieve strong performance across many tasks, but their Key-Value (KV) cache grows linearly with sequence length, creating a severe memory bottleneck for long-context inference.
arXiv:2608. 08220v1 Announce Type: new Abstract: The overlapping disciplines of machine ethics and value alignment are concerned with designing artificial agents that are aligned with human values and that act in ethically acceptable ways.
arXiv:2608. 09453v1 Announce Type: cross Abstract: On--off cycling is the main cause of compressor wear in residential heat pumps, yet reinforcement learning (RL) controllers for buildings typically optimise only energy cost and thermal comfort, ignoring how much the learned policy cycles.
arXiv:2603. 07313v4 Announce Type: replace-cross Abstract: Robustness under latent distribution shift remains challenging in partially observable reinforcement learning.