Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2509. 05208v2 Announce Type: replace-cross Abstract: Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise visual content remains underexplored.
arXiv:2602. 02276v2 Announce Type: replace-cross Abstract: We introduce Kimi K2.
arXiv:2602. 20710v2 Announce Type: replace Abstract: Inspecting Chain-of-Thought reasoning is among the most common means of understanding why an LLM produced its output.
arXiv:2608. 06756v1 Announce Type: new Abstract: Vision-language models are increasingly serving as the reasoning core of embodied agents.
arXiv:2608. 06381v1 Announce Type: cross Abstract: Explainable AI (XAI) has shown promise for human-agent collaboration, yet results rely on hand-crafted policies in custom environments, limiting generalizability to state-of-the-art teaming research.
arXiv:2608. 07068v1 Announce Type: new Abstract: Long-horizon agents accumulate growing contexts during interaction, impairing performance and stability.
arXiv:2608. 06792v1 Announce Type: cross Abstract: Foundation model(FM) for recommendation has shown strong ability to model long-horizon sequential user behavior.
arXiv:2604. 00310v2 Announce Type: replace-cross Abstract: Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions.
arXiv:2605. 31044v2 Announce Type: replace Abstract: Reinforcement learning has shown promising results for optimizing the control of industrial energy systems, yet most existing studies remain limited to the application in simulation environments.
arXiv:2608. 07371v1 Announce Type: new Abstract: Recent agentic reinforcement learning methods use hindsight to complement sparse outcome rewards.
arXiv:2506. 06793v2 Announce Type: replace-cross Abstract: Reward assignment from scarce demonstrations is a key challenge in both offline and online imitation learning.
Reinforcement Learning with Verifiable Rewards (RLVR) makes Multimodal Large Language Models more accurate, but the gains are brittle: simply paraphrasing a question or changing the prompt template can degrade them, which challenges reliable deployment in high-stakes scenarios like medical VQA. We trace this to two issues of the standard RL objective.
We consider the problem of sampling compositional and discrete objects from a given unnormalized posterior distribution. Notably, recent studies have shown that this problem can be efficiently solved by learning a deterministic Markov Decision Process (MDP) that progressively builds each object in proportion to the posterior.
Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective approach for improving multimodal reasoning. However, most existing methods evaluate an entire response using a binary reward based only on final-answer correctness, thereby discarding the supervision available in intermediate reasoning steps.
arXiv:2608. 05255v1 Announce Type: cross Abstract: Retail investors lack access to the kind of personalized, tax-aware portfolio management that institutional clients take for granted -- existing robo-advisors use static, rule-based allocation, and institutional-grade systems require account minimums and technology stacks unavailable to individual investors.
arXiv:2608. 05346v1 Announce Type: cross Abstract: Time-sensitive networking (TSN) is increasingly integrated into mobile edge computing (MEC) to support applications with stringent latency requirements, such as extended reality (XR).
arXiv:2608. 05891v1 Announce Type: new Abstract: Mobile GUI agents can operate apps through pixel perception and touch actions, making them a promising interface for collecting and improving long-horizon mobile interaction policies.
arXiv:2608. 05340v1 Announce Type: cross Abstract: Time-Sensitive Networking (TSN) and Mobile Edge Computing (MEC) hold strong potential for enabling ultra-reliable low-latency communication for time-sensitive applications, such as eXtended Reality (XR).
arXiv:2608. 06128v1 Announce Type: new Abstract: Search agents extend large language models beyond static parametric memory by enabling them to acquire and use ex ternal evidence during multi-step reasoning.
arXiv:2605. 16411v2 Announce Type: replace-cross Abstract: Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet physically inconsistent or visually ungrounded responses due to likelihood maximization under joint probabilistic modeling.