Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2607. 19367v1 Announce Type: new Abstract: Calibration is the primary criterion for evaluating LLM confidence, but it is insufficient: it admits trivially incoherent estimators, depends on the evaluation distribution, and does not test the extent to which the estimation can be interpreted as a consistent, underlying probability function.
arXiv:2607. 19854v1 Announce Type: new Abstract: We study horizon-free regret minimization for finite-horizon time-homogeneous tabular Markov decision processes with $S$ states, $A$ actions, horizon $H$, and per-trajectory total reward bounded by $1$.
arXiv:2510. 05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios.
arXiv:2607. 20011v1 Announce Type: cross Abstract: Traffic-utilisation measurements for network monitoring are corrupted by additive noise and statistical drift: time-dependent change in the signal's mean, variance, distributional shape, or tail behaviour.
arXiv:2607. 19985v1 Announce Type: new Abstract: Dynamic manufacturing environments require multi-agent systems to coordinate effectively under frequent operational disturbances such as machine failures, urgent job arrivals, and processing time variations.
arXiv:2607. 20166v1 Announce Type: cross Abstract: Large Audio Language models (LALMs) have made rapid progress on acoustic understanding, yet they still struggle with fine-grained audio reasoning (e.
arXiv:2507. 10142v2 Announce Type: replace Abstract: Multi-Agent Reinforcement Learning (MARL) has achieved strong performance in simulated benchmarks, yet real deployments often violate the assumptions under which algorithms are designed and evaluated.
arXiv:2607. 19824v1 Announce Type: new Abstract: LLM preference alignment aims to optimize models toward human preferences across diverse user instructions.
arXiv:2607. 20152v1 Announce Type: cross Abstract: Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within a single variational principle.
arXiv:2607. 19935v1 Announce Type: new Abstract: Large metal-organic framework (MOF) databases support simulation, screening, and machine learning through crystallographic information files (CIFs).
arXiv:2607. 19395v1 Announce Type: cross Abstract: Small language models are attractive backbones for interactive agents, but direct distillation from strong teacher trajectories often turns rich multi-turn behavior into one-shot imitation targets.
arXiv:2510. 10057v2 Announce Type: replace Abstract: The three-dimensional bin packing problem (3D-BPP) is widely applied in logistics and warehousing.
arXiv:2607. 19609v1 Announce Type: cross Abstract: In this paper, we study an unmanned aerial vehicle (UAV)-assisted integrated sensing and communication (ISAC) system, where a UAV enhances the sensing capability of a base station (BS) towards a target while ensuring reliable communication towards a downlink user.
arXiv:2607. 19809v1 Announce Type: cross Abstract: In multi-agent reinforcement learning (MARL), inter-agent communication is effective for improving performance under partial observability.
arXiv:2607. 17572v2 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences.
arXiv:2607. 20399v1 Announce Type: cross Abstract: Full-sized humanoid robot capabilities have grown exponentially in recent years, aiming towards general-purpose deployment in human environments.
arXiv:2607. 20005v1 Announce Type: new Abstract: In modern IT operations (IT-Ops), the cost of an incorrect repair often exceeds the cost of no action at all.
arXiv:2607. 19389v1 Announce Type: cross Abstract: As AI-driven Decision Makers (ADMs) influence our socioeconomic reality, their roles in both enhancing efficiency and amplifying the social biases have drawn attention.
Offline goal-conditioned reinforcement learning (RL) holds the promise of learning general-purpose policies from static datasets. However, scaling these methods to long-horizon tasks remains a challenge due to the curse of horizon, where value estimation errors can compound through long chains of bootstrapped Bellman backups.
Large language models increasingly rely on long-form reasoning for complex tasks, yet their reasoning traces may drift away from the supplied context when evidence is sparse, noisy, or in conflict with parametric knowledge. Existing grounding methods either attach citations after generation or encourage evidence retrieval inside the trace, but they often do not ensure that cited content is sufficient for the local inference and final answer.