Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2607. 16028v1 Announce Type: new Abstract: This paper presents our system for Task 3 of the CLEF 2026 FinMMEval Lab, which requires daily long, flat, or short trading decisions for Bitcoin (BTC) and Tesla (TSLA) using news and historical market data.
arXiv:2607. 16074v1 Announce Type: cross Abstract: The post-training of Vision-Language-Action (VLA) models is essential due to the diversity of simulators, robot embodiments, and task objectives.
arXiv:2607. 16004v1 Announce Type: cross Abstract: Increases in photovoltaic generation, charging of electric vehicles and heat-pump demand challenge operating limits in low-voltage distribution grids.
arXiv:2510. 01475v2 Announce Type: replace-cross Abstract: Model Predictive Control (MPC) has demonstrated significant performance improvements over today's control methods for residential Heating, Ventilation, and Air Conditioning (HVAC), but deploying MPC often requires substantial engineering effort.
arXiv:2607. 15577v1 Announce Type: cross Abstract: Causal bandits exploit structural relationships among variables to share information across interventions and accelerate the identification of high-reward decisions.
arXiv:2502. 00345v2 Announce Type: replace-cross Abstract: The critical role of division of labor (DOL) in enhancing cooperation is well-recognized in real-world applications.
arXiv:2605. 15422v3 Announce Type: replace Abstract: Modern RL post-training methods such as GRPO and DAPO train on N response sequences of R tokens sampled from a shared prompt of P tokens, but standard FlashAttention replicates all P prompt tokens N times across both forward and backward passes -- duplicating compute and memory on identical hidden states.
arXiv:2607. 16062v1 Announce Type: cross Abstract: Model merging is promoted as a substitute for joint multi-task training, yet in the reinforcement-learning setting this substitution is essentially never tested against the baseline it claims to replace: methods merge independently released agents precisely because a joint model is unavailable.
arXiv:2607. 15660v1 Announce Type: new Abstract: While LLM agents demonstrate strong reasoning abilities in compact and well-defined scenarios, they struggle to maintain robustness and effectiveness when faced with large-scale, diverse, and dynamic real-world environments that demand seamless tool integration.
arXiv:2607. 15942v1 Announce Type: cross Abstract: Remote sensing vision-language models are increasingly expected to support open-ended reasoning over Earth Observation data and a variety of tasks.
arXiv:2607. 16131v1 Announce Type: cross Abstract: Multimodal Scientific Claim Verification (MSCV) requires models to verify scientific claims using visually grounded evidence from papers, including figures, tables, charts, and textual context.
arXiv:2607. 15740v1 Announce Type: cross Abstract: As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important for fair and trustworthy generative AI.
arXiv:2607. 15901v1 Announce Type: new Abstract: Despite strong capabilities in data understanding and decision-making, autonomous data science agents still heavily rely on trial-and-error workflows that involve expensive computation.
arXiv:2605. 04539v4 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators or LLM judges exhibit a systematic verbosity bias that rewards fluency over logical correctness.
arXiv:2607. 15552v1 Announce Type: cross Abstract: Generating personalized trip itineraries is a complex planning task and involves a tension between hard combinatorial feasibility and soft latent desirability.
arXiv:2607. 16177v1 Announce Type: new Abstract: Reinforcement learning (RL) has recently emerged as a promising feedback control strategy for nonlinear and complex dynamical systems.
arXiv:2607. 15810v1 Announce Type: new Abstract: Rollout generation is a major bottleneck in Reinforcement Learning (RL) for Mixture-of-Experts (MoE) Large Language Models, motivating low-precision rollout acceleration such as FP8.
arXiv:2310. 07211v2 Announce Type: replace Abstract: Regularization is a cornerstone of modern reinforcement learning.
arXiv:2607. 14180v1 Announce Type: cross Abstract: World models are widely used in offline reinforcement learning (RL) to improve sample efficiency and generate experience beyond a fixed dataset.
arXiv:2607. 14361v1 Announce Type: cross Abstract: We address fundamental challenges in representing and computing $\mathbb{R}^{d}$-valued predictable square-integrable processes over $[0,T]$, collected in the space $\mathcal{H}^2_T(\mathbb{R}^{d})$.