Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training separate preference models for helpfulness and safety, while framing safety as a constraint within a constrained Markov Decision Process (CMDP) framework. This paper identifies a potential issue when using the widely adopted expected safety constraints for LLM safety alignment, termed "safety compensation", where the constraints are satisfied on expectation, but individual prompts may trade off safety, resulting in some responses being overly restrictive while others remain unsafe. To address this issue, we propose Rectified Policy Optimization (RePO), which replaces the expected safety constraint with critical safety constraints imposed on every prompt. At the core of RePO is a policy update mechanism driven by rectified policy gradients, which penalizes the strict safety violation of every prompt, thereby enhancing safety across nearly all prompts. Our experiments demonstrate that RePO outperforms strong baseline methods and significantly enhances LLM safety alignment.

Recent studies empirically reveal that large reasoning models (LRMs) can automatically allocate more reasoning strengths (i.e., the number of reasoning tokens) for harder problems, exhibiting difficulty-awareness for better task performance. While this automatic reasoning strength allocation phenomenon has been widely observed, its underlying mechanism remains largely unexplored. To this end, we provide explanations for this phenomenon from the perspective of model activations. We find evidence that LRMs pre-plan the reasoning strengths in their activations even before generation, with this reasoning strength causally controlled by the magnitude of a pre-allocated directional vector. Specifically, we show that the number of reasoning tokens is predictable solely based on the question activations using linear probes, indicating that LRMs estimate the required reasoning strength in advance.

While substantial advances have been achieved in TTS for languages such as English and Mandarin, Korean remains comparatively underrepresented due to the lack of rigorous preprocessing methods, systematically constructed datasets, a shortage of standardized Korean TTS benchmarks, and explicitly optimized models for Korean. To address these limitations, we propose a Korean-tailored data-refinement and coreset selection pipeline. It refines speech data and performs textual normalization especially for numerals and English terms, followed by a novel coreset selection strategy that leverages Jamo-based linguistic and phonological features unique to Korean. As a result, we release CoreaSpeech, an efficient and robust Korean speech corpus comprising 700 hours across 21,449 speakers. This refined core subset, evenly balanced across utterances ranging from 0 to 30 seconds, is derived from 2,058 hours of widely used Korean datasets. Building on this, we conducted extensive experiments via cross-lingual fine-tuning with our CoreaSpeech dataset. Furthermore, we introduce a new universal Korean TTS benchmark dataset including clean, noisy, and numeric subsets. Additionally, we demonstrate that our Korean-specific text normalization serves as a plug-and-play module, reliably improving performance regardless of the underlying TTS architecture.

Drug recommendation systems aim to identify optimal drug combinations for patient care, balancing therapeutic efficacy and safety. Advances in large-scale longitudinal EHRs have enabled learning-based approaches that leverage patient histories such as diagnoses, procedures, and previously prescribed drugs, to model complex patient-drug relationships. Yet, many existing solutions overlook standard clinical practices that favor certain drugs for specific conditions and fail to fully integrate the influence of molecular substructures on drug efficacy and safety. In response, we propose SubRec, a unified framework that integrates representation learning across both patient and drug spaces. Specifically, SubRec introduces a conditional information bottleneck to extract core drug substructures most relevant to patient conditions, thereby enhancing interpretability and clinical alignment. Meanwhile, an adaptive vector quantization mechanism is designed to generate patient-drug interaction patterns into a condition-aware codebook which reuses clinically meaningful patterns, reduces training overhead, and provides a controllable latent space for recommendation. Crucially, the synergy between condition-specific substructure learning and discrete patient prototypes allows SubRec to make accurate and personalized drug recommendations. Experimental results on the real-world MIMICIII and IV demonstrate our model's advantages. The source code is available at https://DrugRecommendation/.

The task of issue resolving aims to modify a codebase to generate a patch that addresses a given issue. However, most existing benchmarks focus almost exclusively on Python, making them insufficient for evaluating Large Language Models (LLMs) across different programming languages. To bridge this gap, we introduce a multilingual issue-resolving benchmark, called Multi-SWE-bench, covering 8 widely used programming languages: Python, Java, TypeScript, JavaScript, Go, Rust, C, and C++. In particular, this benchmark includes a total of 2,132 highquality instances, carefully curated by 68 expert annotators, ensuring a reliable and accurate evaluation of LLMs on the issue-resolving task. Based on humanannotated results, the issues are further classified into three difficulty levels. We evaluate a series of state-of-the-art models on Multi-SWE-bench, utilizing both procedural and agent-based frameworks for issue resolving. Experimental results based on Multi-SWE-bench reveal three key findings: (1) Limited generalization across languages: While existing LLMs perform well on Python issues, their ability to generalize across other languages remains limited; (2) Performance aligned with human-annotated difficulty: LLM-based agents' performance closely aligns with human-assigned difficulty, with resolved rates notably decreasing as issue complexity rises; and (3) Performance drop on cross-file issues: The performance of current methods significantly deteriorates when handling cross-file issues. These findings highlight the limitations of current LLMs and underscore the need for more robust models capable of handling a broader range of programming languages and complex issue scenarios.

Aligning large language models (LLMs) with human preferences typically demands vast amounts of meticulously curated data, which is both expensive and prone to labeling noise. We propose Stackelberg Game Preference Optimization (SGPO), a robust alignment framework that models alignment as a two-player Stackelberg game between a policy (leader) and a worst-case preference distribution (follower). The proposed SGPO guarantees O(ϵ)-bounded regret within an ϵ-Wasserstein ball, offering formal robustness to (self-)annotation noise. We instantiate SGPO with Stackelberg Self-Annotated Preference Optimization (SSAPO), which uses minimal humanlabeled "seed" preferences and iteratively self-annotates new prompts. In each iteration, SSAPO applies a distributionally robust reweighting of synthetic annotations, ensuring that noisy or biased self-labels do not derail training. Remarkably, using only 2K seed preferences--about 1/30 of standard human labels--SSAPO achieves strong win rates against GPT-4 across multiple benchmarks within three iterations.

In this paper, we introduce BMMR, a large-scale bilingual, multimodal, multidisciplinary reasoning dataset for the community to develop and evaluate large multimodal models (LMMs). BMMR comprises 110k college-level questions spanning 300 UNESCO-defined subjects, spanning diverse formats--multiplechoice, fill-in-the-blank, and open-ended QA--and sourced from both print and digital media such as books, exams, and quizzes. All data are curated and filtered via a human-in-the-loop and scalable framework, and each instance is paired with a high-quality reasoning path. The dataset is organized into two parts: BMMR-Eval that comprises 20,458high-quality instances to comprehensively assess LMMs' knowledge and reasoning across multiple disciplines in both Chinese and English; and BMMR-Train that contains 88,991 instances to support further research and development, extending the current focus on mathematical reasoning to diverse disciplines and domains. In addition, we propose the process-based multi-discipline verifier (i.e., BMMR-Verifier) for accurate and fine-grained evaluation of reasoning paths. Extensive experiments on 24 models reveal that (i) even SOTA models (e.g., o3and Gemini-2.5-Pro)

PCWorld explains how Windows 11 users can leverage AI chatbots like ChatGPT, Claude, or Gemini to analyze their PC's health using MSINFO32 system reports. This method allows comprehensive system analysis without granting AI direct file access, maintaining privacy while getting actionable insights about hardware and software issues.

Arriving six years after Google's last smart speaker, the new HomePod-style device was redesigned to play host to Gemini's chatbot. The last time Google released a smart speaker, the world was in the throes of a pandemic . Yes, it's been six years since the company trotted out a dedicated speaker. However, this newest Google Home Speaker brings a big change with it: The device has been redesigned to showcase the new Gemini assistant instead of the Google Assistant that powered all previous speakers and smart displays. Google announced the speaker last fall alongside new Nest smart home cameras and video doorbells, promising a spring 2026 launch.

Despite the growing integration of retrieval-enabled AI agents into society, their safety and ethical behavior remain inadequately understood. In particular, the growing integration of LLMs and AI agents with external information sources and real-world environments raises critical questions about how they engage with and are influenced by these external data sources and interactive contexts. This study investigates how expanding retrieval access--from no external sources to Wikipedia-based retrieval and open web search--affects model reliability, bias propagation, and harmful content generation. Through extensive benchmarking of censored and uncensored LLMs and AIAgents, our findings reveal a consistent degradation in refusal rates, bias sensitivity, and harmfulness safeguards as models gain broader access to external sources, culminating in a phenomenon we term safety degradation. Notably, retrieval-enabled agents built on aligned LLMs often behave more unsafely than uncensored models without retrieval. This effect persists even under strong retrieval accuracy and prompt-based mitigation, suggesting that the mere presence of retrieved content reshapes model behavior in structurally unsafe ways. These findings underscore the need for robust mitigation strategies to ensure fairness and reliability in retrieval-enabled and increasingly autonomous AI systems. Content Warning: This paper contains examples of harmful language.