Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
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:2602. 01962v2 Announce Type: replace-cross Abstract: Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions.
arXiv:2606. 00414v1 Announce Type: new Abstract: When many reinforcement-learning policies achieve near-optimal return, a post-hoc auditor may have to distinguish among many behaviorally distinct but return-equivalent policies.
arXiv:2603. 02650v2 Announce Type: replace-cross Abstract: Diffusion planners are a strong approach for offline reinforcement learning, but they can fail when value-guided selection favours trajectories that score well yet are locally inconsistent with the environment dynamics, resulting in brittle execution.
arXiv:2606. 00059v1 Announce Type: cross Abstract: Informative excitation signals are critical for accurate system identification of mechatronic systems, yet classical system identification (SI) approaches require expert knowledge and hand-crafted signal design to respect hardware safety constraints, limiting their generalizability.
arXiv:2606. 00862v1 Announce Type: cross Abstract: Surrogate-assisted evolutionary algorithms (SAEAs) have been widely used for expensive black-box optimization problems.
arXiv:2606. 01861v1 Announce Type: new Abstract: Self-play, a type of training algorithm that enables a model to self-improve, has recently shown promising empirical results in the context of formal theorem proving using Large Language Models (LLMs).
arXiv:2606. 02578v1 Announce Type: cross Abstract: Recent multimodal large language models have demonstrated strong reasoning ability, yet their reliability as automated evaluators remains limited by a critical weakness: when visual evidence conflicts with textual cues, MLLM judges tend to reward plausible narratives over perceptually correct answers.
arXiv:2604. 17456v2 Announce Type: replace Abstract: Large language model (LLM) agents have shown strong capabilities in long-horizon reasoning, tool use, and decision-making in digital environments, yet extending them to physically grounded systems remains challenging.
arXiv:2606. 01599v1 Announce Type: new Abstract: Reinforcement learning (RL) for visual reasoning needs scalable, verifiable, and controllable training signals.
arXiv:2606. 00680v1 Announce Type: new Abstract: Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets.
arXiv:2606. 01162v1 Announce Type: new Abstract: Workflow scheduling in cloud computing demands the intelligent allocation of dynamically arriving, graph-structured workflows with varying deadlines onto ever-changing virtual machine resources.
arXiv:2606. 00017v1 Announce Type: new Abstract: Training language model agents for multi-agent strategic interaction presents a core difficulty: the quality of any action may depend on future events that never materialize, on moves that violate game rules, or on decisions made by other players.
arXiv:2606. 01830v1 Announce Type: new Abstract: Recent LLM search agents use reinforcement learning with verifiable rewards (RLVR) to learn search-augmented reasoning from outcome rewards.
arXiv:2606. 00083v1 Announce Type: cross Abstract: Reinforcement learning relies on accurate reward functions, which are often hand-crafted or even unavailable in real-world applications, such as robotics.
arXiv:2606. 00313v1 Announce Type: cross Abstract: Robust deployment of deep reinforcement learning (DRL) policies on real robots remains challenging due to discrepancies between simulation and real-world dynamics.
arXiv:2606. 00780v1 Announce Type: cross Abstract: Offline meta-reinforcement learning leverages static datasets to enable agents to generalize to unseen environments by combining offline efficiency with meta-learning adaptability, yet it faces key challenges from context and policy distribution shifts.
arXiv:2606. 01811v1 Announce Type: cross Abstract: Measuring the diversity of creative outputs is central to evaluating post-training mode collapse, comparing decoding strategies, and quantifying creative behavior in both AI and human writing.
arXiv:2603. 12109v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a de facto paradigm for building LLM-based agents that act, interact, and reason over extended task horizons.
arXiv:2510. 01167v2 Announce Type: replace-cross Abstract: Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single objective.