Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2607. 22996v1 Announce Type: cross Abstract: Large language models (LLMs) deployed in educational settings often behave as direct answerers: they disclose target concepts in the opening turn instead of guiding students through progressive inquiry, as Socratic pedagogy prescribes.
arXiv:2607. 22766v1 Announce Type: cross Abstract: The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality.
arXiv:2607. 22561v1 Announce Type: new Abstract: LLM-as-a-judge has become the standard for automated evaluation, but it suffers from high cost, significant latency, and opaque decisions -- limitations that undermine its scalability and reliability.
arXiv:2607. 22649v1 Announce Type: new Abstract: Following complex instructions with multiple explicit constraints remains a fundamental challenge for large language models (LLMs).
arXiv:2607. 22837v1 Announce Type: cross Abstract: Many organizations aim to adapt language models for internal use, both to improve performance on domain-specific tasks and to address privacy concerns around sensitive data.
arXiv:2607. 23565v1 Announce Type: cross Abstract: Safe quadrotor navigation in cluttered and dynamic environments depends not only on instantaneous geometric perception, but more critically on anticipating collision risks induced by relative motion.
arXiv:2607. 23263v1 Announce Type: new Abstract: Deciding whether a trajectory actually fulfills its instruction governs how we measure computer-use agents on long-horizon graphical-user-interface tasks and how we train them with reinforcement learning.
arXiv:2607. 24522v1 Announce Type: new Abstract: While on-policy distillation (OPD) effectively addresses sparse rewards and exposure bias in large language model post-training, its extension to flow models remains underexplored.
arXiv:2607. 23434v1 Announce Type: cross Abstract: Unexpected shocks recur in global operations, requiring decision rules that adapt as market and operating conditions change.
arXiv:2602. 05547v2 Announce Type: replace-cross Abstract: RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks.
arXiv:2509. 06278v4 Announce Type: replace Abstract: Table reasoning requires models to jointly perform comprehensive semantic understanding and precise numerical operations.
arXiv:2607. 22982v1 Announce Type: new Abstract: Natural Policy Gradient (NPG) is a well-established Reinforcement Learning algorithm that underlies widely used methods such as Trust Region Policy Optimization and Proximal Policy Optimization, both of which have demonstrated strong empirical success.
arXiv:2607. 23124v1 Announce Type: new Abstract: Large language model agents have advanced rapidly, yet progress remains fragmented across domains, capabilities, task difficulty, and interaction settings.
arXiv:2607. 24653v1 Announce Type: cross Abstract: We introduce Kimi K3, a 2.
Document-level relation extraction (DocRE) aims to extract relations among multiple entities across extended contexts while maintaining consistency across predicted triples. Although large language models (LLMs) show remarkable reasoning capabilities in information extraction, their predictions are typically generated independently for each candidate triple and may violate fundamental relational constraints such as transitivity, symmetry, and functional uniqueness, leading to contradictory and unreliable outputs.
arXiv:2607. 22012v1 Announce Type: new Abstract: Off-Policy Evaluation and Learning (OPE/L) in contextual bandits is rapidly gaining popularity in real systems because new policies can be evaluated and learned securely using only historical logged data.
arXiv:2607. 21653v1 Announce Type: new Abstract: Agentic reinforcement learning research is constant algorithm modification, new estimators, new pipeline stages, new rollout schemes, and in mainstream frameworks each change threads through layers of trainer, distributed backend, and rollout glue: the cost lands on the researcher at every iteration.
arXiv:2603. 05789v5 Announce Type: replace-cross Abstract: Repeated multi-agent interactions require evaluation metrics that capture not only payoff distributions but also their temporal organization.
arXiv:2607. 21627v1 Announce Type: cross Abstract: End-to-end reinforcement learning can improve the accuracy of compound LLM systems, but it does not constrain how modules divide labor internally.
arXiv:2607. 22465v1 Announce Type: cross Abstract: Routing to select large language models (LLMs) with different cost-quality trade-offs has become a fundamental deployment feature of enterprise AI.