Diagnosis-Related Group (DRG) codes are essential for hospital reimbursement and operations but require labor-intensive assignment. Large Language Models (LLMs) struggle with DRG coding due to the out-of-distribution (OOD) nature of the task: pretraining corpora rarely contain private clinical or billing data. We introduce DRG-Sapphire, which uses large-scale reinforcement learning (RL) for automated DRG coding from clinical notes. Built on Qwen2.5-7B and trained with Group Relative Policy Optimization (GRPO) using rule-based rewards, DRG-Sapphire introduces a series of RL enhancements to address domain-specific challenges not seen in previous mathematical tasks. Our model achieves state-of-the-art accuracy on the MIMIC-IV benchmark and generates physician-validated reasoning for DRG assignments, significantly enhancing explainability. Our study further sheds light on broader challenges of applying RL to knowledge-intensive, OOD tasks. We observe that RL performance scales approximately linearly with the logarithm of the number of supervised fine-tuning (SFT) examples, suggesting that RL effectiveness is fundamentally constrained by the domain knowledge encoded in the base model. For OOD tasks like DRG coding, strong RL performance requires sufficient knowledge infusion prior to RL. Consequently, scaling SFT may be more effective and computationally efficient than scaling RL alone for such tasks.

While black-box large language models are widely deployed, they produce generic outputs that overlook individual user preferences. Current personalization methods are fundamentally limited to response-level personalization; they only match final outputs, failing to model the underlying reasoning that connects user behavior to responses. To address this, this work introduces reasoning-level personalization as a new paradigm and proposes RPM, the first systematic framework designed to guide the model's reasoning process using structured rationales constructed from patterns in a user's behavior. RPM constructs a structured model of user behavior-built from response-influential features and statistical factors-to create personalized reasoning paths and retrieve beneficial examples for guiding inference through a feature-based retrieval mechanism. Extensive experiments across four diverse tasks demonstrate that RPM consistently outperforms existing response-level methods while simultaneously enhancing both personalization performance and interpretability, providing a promising direction for black-box LLM personalization.

The emergence of large language models (LLMs) enables the development of intelligent agents capable of engaging in complex and multi-turn dialogues. However, multi-agent collaboration faces critical safety challenges, such as hallucination amplification and error injection and propagation. This paper presents GUARDIAN, a unified method for detecting and mitigating multiple safety concerns in GUARDing Intelligent Agent collaboratioNs. By modeling the multi-agent collaboration process as a discrete-time temporal attributed graph, GUARDIAN explicitly captures the propagation dynamics of hallucinations and errors. The unsupervised encoder-decoder architecture incorporating an incremental training paradigm learns to reconstruct node attributes and graph structures from latent embeddings, enabling the identification of anomalous nodes and edges with unparalleled precision. Moreover, we introduce a graph abstraction mechanism based on the Information Bottleneck Theory, which compresses temporal interaction graphs while preserving essential patterns. Extensive experiments demonstrate GUARDIAN's effectiveness in safeguarding LLM multi-agent collaborations against diverse safety vulnerabilities, achieving state-of-the-art accuracy with efficient resource utilization. The code is available at https://github.com/JialongZhou666/GUARDIAN

Large Language Models (LLMs) exhibit remarkable emergent abilities but remain poorly understood at a mechanistic level. This paper introduces the Multi-Scale Probabilistic Generation Theory (MSPGT), a theoretical framework that models LLMs as Hierarchical Variational Information Bottleneck (H-VIB) systems. MSPGT posits that standard language modeling objectives implicitly optimize multi-scale information compression, leading to the spontaneous formation of three internal processing scales-Global, Intermediate, and Local. We formalize this principle, derive falsifiable predictions about boundary positions and architectural dependencies, and validate them through cross-model experiments combining multi-signal fusion and causal interventions. Results across Llama and Qwen families reveal consistent multi-scale organization but strong architecture-specific variations, partially supporting and refining the theory. MSPGT thus advances interpretability from descriptive observation toward predictive, information-theoretic understanding of how hierarchical structure emerges within large neural language models.

Electroencephalography (EEG) and magnetoencephalography (MEG) measure neural activity non-invasively by capturing electromagnetic fields generated by dendritic currents. Although rooted in the same biophysics, EEG and MEG exhibit distinct signal patterns, further complicated by variations in sensor configurations across modalities and recording devices. Existing approaches typically rely on separate, modality- and dataset-specific models, which limits the performance and cross-domain scalability. This paper proposes BrainOmni, the first brain foundation model that generalises across heterogeneous EEG and MEG recordings. To unify diverse data sources, we introduce BrainTokenizer,the first tokenizer that quantises spatiotemporal brain activity into discrete representations. Central to BrainTokenizer is a novel Sensor Encoder that encodes sensor properties such as spatial layout, orientation, and type, enabling compatibility across devices and modalities. Building upon the discrete representations, BrainOmni learns unified semantic embeddings of brain signals by self-supervised pretraining. To the best of our knowledge, it is the first foundation model to support both EEG and MEG signals, as well as the first to incorporate large-scale MEG pretraining. A total of 1,997 hours of EEG and 656 hours of MEG data are curated and standardised from publicly available sources for pretraining. Experiments show that BrainOmni outperforms both existing foundation models and state-of-the-art task-specific models on a range of downstream tasks. It also demonstrates strong generalisation to unseen EEG and MEG devices. Further analysis reveals that joint EEG-MEG (EMEG) training yields consistent improvements across both modalities. Code and checkpoints are publicly available at https://github.com/OpenTSLab/BrainOmni.

Large Reasoning Models (LRMs) leverage transparent reasoning traces, known as Chain-of-Thoughts (CoTs), to break down complex problems into intermediate steps and derive final answers. However, these reasoning traces introduce unique safety challenges: harmful content can be embedded in intermediate steps even when final answers appear benign. Existing moderation tools, designed to handle generated answers, struggle to effectively detect hidden risks within CoTs. To address these challenges, we introduce ReasoningShield, a lightweight yet robust framework for moderating CoTs in LRMs. Our key contributions include: (1) formalizing the task of CoT moderation with a multi-level taxonomy of 10 risk categories across 3 safety levels, (2) creating the first CoT moderation benchmark which contains 9.2K pairs of queries and reasoning traces, including a 7K-sample training set annotated via a human-AI framework and a rigorously curated 2.2K human-annotated test set, and (3) developing a two-stage training strategy that combines stepwise risk analysis and contrastive learning to enhance robustness. Experiments show that ReasoningShield achieves state-of-the-art performance, outperforming task-specific tools like LlamaGuard-4 by 35.6% and general-purpose commercial models like GPT-4o by 15.8% on benchmarks, while also generalizing effectively across diverse reasoning paradigms, tasks, and unseen scenarios. All resources are released at https://github.com/CosmosYi/ReasoningShield.

The rapid spread of multimodal misinformation on social media has raised growing concerns, while research on video misinformation detection remains limited due to the lack of large-scale, diverse datasets. Existing methods often overfit to rigid templates and lack deep reasoning over deceptive content. To address these challenges, we introduce FakeVV, a large-scale benchmark comprising over 100,000 video-text pairs with fine-grained, interpretable annotations. In addition, we further propose Fact-R1, a novel framework that integrates deep reasoning with collaborative rule-based reinforcement learning. Fact-R1 is trained through a three-stage process: (1) misinformation long-Chain-of-Thought (CoT) instruction tuning, (2) preference alignment via Direct Preference Optimization (DPO), and (3) Group Relative Policy Optimization (GRPO) using a novel verifiable reward function. This enables Fact-R1 to exhibit emergent reasoning behaviors comparable to those observed in advanced text-based reinforcement learning systems, but in the more complex multimodal misinformation setting. Our work establishes a new paradigm for misinformation detection, bridging large-scale video understanding, reasoning-guided alignment, and interpretable verification.

Standard imitation learning (IL) methods have achieved considerable success in robotics, yet often rely on the Markov assumption, which falters in long-horizon tasks where history is crucial for resolving perceptual ambiguity. This limitation stems not only from a conceptual gap but also from a fundamental computational barrier: prevailing architectures like Transformers are often constrained by quadratic complexity, rendering the processing of long, high-dimensional observation sequences infeasible. To overcome this dual challenge, we introduce Mamba Temporal Imitation Learning (MTIL). Our approach represents a new paradigm for robotic learning, which we frame as a practical synthesis of World Model and Dynamical System concepts. By leveraging the linear-time recurrent dynamics of State Space Models (SSMs), MTIL learns an implicit, action-oriented world model that efficiently encodes the entire trajectory history into a compressed, evolving state. This allows the policy to be conditioned on a comprehensive temporal context, transcending the confines of Markovian approaches. Through extensive experiments on simulated benchmarks (ACT, Robomimic, LIBERO) and on challenging real-world tasks, MTIL demonstrates superior performance against SOTA methods like ACT and Diffusion Policy, particularly in resolving long-term temporal ambiguities. Our findings not only affirm the necessity of full temporal context but also validate MTIL as a powerful and a computationally feasible approach for learning long-horizon, non-Markovian behaviors from high-dimensional observations.

Natural Gradient Descent (NGD) has emerged as a promising optimization algorithm for training neural network-based solvers for partial differential equations (PDEs), such as Physics-Informed Neural Networks (PINNs). However, its practical use is often limited by the high computational cost of solving linear systems involving the Gramian matrix. While matrix-free NGD methods based on the conjugate gradient (CG) method avoid explicit matrix inversion, the ill-conditioning of the Gramian significantly slows the convergence of CG. In this work, we extend matrix-free NGD to broader classes of problems than previously considered and propose the use of Randomized Nyström preconditioning to accelerate convergence of the inner CG solver. The resulting algorithm demonstrates substantial performance improvements over existing NGD-based methods and other state-of-the-art optimizers on a range of PDE problems discretized using neural networks.

Stochastic games have become a prevalent framework for studying long-term multi-agent interactions, especially in the context of multi-agent reinforcement learning. In this work, we comprehensively investigate the concept of constant-memory strategies in stochastic games. We first establish some results on best responses and Nash equilibria for behavioral constant-memory strategies, followed by a discussion on the computational hardness of best responding to mixed constant-memory strategies. Those theoretic insights are later verified on several sequential decision-making testbeds, including the $\textit{Iterated Prisoner's Dilemma}$, the $\textit{Iterated Traveler's Dilemma}$, and the $\textit{Pursuit}$ domain. This work aims to enhance the understanding of theoretical issues in single-agent planning under multi-agent systems, and uncover the connection between decision models in single-agent and multi-agent contexts. The code is available at $\texttt{https://github.com/Fernadoo/Const-Mem.}$