Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2607. 28647v1 Announce Type: cross Abstract: This paper presents ConnectED, a human-centered AI system that supports the full instructional lifecycle in Vietnamese education by linking curriculum-aligned lesson design, interactive student learning, and feedback-driven refinement.
arXiv:2607. 29419v1 Announce Type: cross Abstract: In reinforcement learning, exploration with sparse and delayed rewards presents a significant challenge due to the limited feedback available for guiding the learning process.
arXiv:2607. 28990v1 Announce Type: new Abstract: Large language model agents have shown promising capabilities in data-driven scientific discovery tasks, where an agent interacts with an execution environment and produces a statistical claim.
arXiv:2607. 29559v1 Announce Type: new Abstract: Reinforcement Learning (RL) systems are typically trained using a single, well-specified scalar reward function.
arXiv:2607. 28916v1 Announce Type: cross Abstract: Multistep credit assignment is critical for sample-efficient reinforcement learning, yet managing off-policy bias in Q-learning remains a fundamental challenge.
arXiv:2607. 29172v1 Announce Type: cross Abstract: While robot foundation models are growing increasingly capable, the strongest models are typically trained on proprietary data and remain closed-source, limiting downstream users' ability to adapt them to new tasks, embodiments, and deployment settings.
arXiv:2603. 25464v2 Announce Type: replace-cross Abstract: Zero-shot reinforcement learning (RL) algorithms aim to learn a family of policies from a reward-free dataset, and recover optimal policies for any reward function directly at test time.
arXiv:2607. 29375v1 Announce Type: cross Abstract: Organizations increasingly rely on sequential experimentation to improve decision-making.
arXiv:2607. 21106v2 Announce Type: replace Abstract: Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging.
arXiv:2407. 04521v3 Announce Type: replace-cross Abstract: This paper studies the continuous-time q-learning in mean-field jump-diffusion models in a setting where the environment simulator does not provide direct access to the population distribution.
arXiv:2607. 28663v1 Announce Type: cross Abstract: Artificial Intelligence (AI) systems often perform well on isolated tasks but struggle under continual learning conditions, where training on new tasks can overwrite previously acquired knowledge, a failure mode known as catastrophic forgetting.
arXiv:2307. 10524v3 Announce Type: replace Abstract: We study the tradeoff between consistency and robustness in the context of a single-trajectory time-varying Markov Decision Process (MDP) with untrusted machine-learned advice.
arXiv:2607. 29398v1 Announce Type: new Abstract: Diffusion models have revolutionized generative tasks but incur high latency due to iterative denoising.
arXiv:2605. 02906v3 Announce Type: replace Abstract: In the field of software operations, Large Language Models (LLMs) have attracted increasing attention.
arXiv:2607. 29246v1 Announce Type: new Abstract: Modern large language models (LLMs) are expected not just to answer correctly, but to adapt their behavior to different human values and use cases.
arXiv:2607. 28692v1 Announce Type: new Abstract: Large language model (LLM) agents have been increasingly adopted in scientific research for organizing and invoking specialized computational tools.
arXiv:2607. 28457v1 Announce Type: cross Abstract: Scaling test-time computation can improve language-model reasoning, but uniform budgets waste computation on easy inputs, while verifier-guided refinement relies on external feedback.
arXiv:2607. 28638v1 Announce Type: cross Abstract: As large language model (LLM) agents increasingly learn from experience, they primarily rely on trajectory-level reflection to extract insights.
arXiv:2605. 17877v2 Announce Type: replace Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks.
arXiv:2607. 29294v1 Announce Type: new Abstract: We present HBPI-UCRL, a model-based algorithm for hierarchical reinforcement learning (HRL) that learns high-level and low-level policies in parallel.