While bariatric and metabolic surgery (MBS) is considered the gold standard treatment for severe and morbid obesity, its therapeutic efficacy hinges upon active and longitudinal engagement with multidisciplinary providers, including surgeons, dietitians/nutritionists, psychologists, and endocrinologists. This engagement spans the entire patient journey, from preoperative preparation to long-term postoperative management. However, this process is often hindered by numerous healthcare disparities, such as logistical and access barriers, which impair easy patient access to timely, evidence-based, clinician-endorsed information. To address these gaps, we introduce bRAGgen, a novel adaptive retrieval-augmented generation (RAG)-based model that autonomously integrates real-time medical evidence when response confidence dips below dynamic thresholds. This self-updating architecture ensures that responses remain current and accurate, reducing the risk of misinformation. Additionally, we present bRAGq, a curated dataset of 1,302 bariatric surgery--related questions, validated by an expert bariatric surgeon. bRAGq constitutes the first large-scale, domain-specific benchmark for comprehensive MBS care. In a two-phase evaluation, bRAGgen is benchmarked against state-of-the-art models using both large language model (LLM)--based metrics and expert surgeon review. Across all evaluation dimensions, bRAGgen demonstrates substantially superior performance in generating clinically accurate and relevant responses.

LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing defenses focus on known types of attacks, it is more critical to prepare LLMs for unseen attacks that may arise during deployment. To address this, we propose a lifelong safety alignment framework that enables LLMs to continuously adapt to new and evolving jailbreaking strategies. Our framework introduces a competitive setup between two components: a Meta-Attacker, trained to actively discover novel jailbreaking strategies, and a Defender, trained to resist them. To effectively warm up the Meta-Attacker, we first leverage the GPT-4o API to extract key insights from a large collection of jailbreak-related research papers. Through iterative training, the first iteration Meta-Attacker achieves a 73% attack success rate (ASR) on RR and a 57% transfer ASR on LAT using only single-turn attacks. Meanwhile, the Defender progressively improves its robustness and ultimately reduces the Meta-Attacker's success rate to just 7%, enabling safer and more reliable deployment of LLMs in open-ended environments. The code is available at https://github.com/sail-sg/LifelongSafetyAlignment.

Assessing higher-order thinking skills in large language models (LLMs) remains a fundamental challenge, especially in tasks that go beyond surface-level accuracy. In this work, we propose THiNK (Testing Higher-order Notion of Knowledge), a multi-agent, feedback-driven evaluation framework grounded in Bloom's Taxonomy. THiNK frames reasoning assessment as an iterative task of problem generation, critique, and revision, encouraging LLMs to think-aloud through step-by-step reflection and refinement. This enables a systematic evaluation of both lower-order (e.g., remember, understand) and higher-order (e.g., evaluate, create) thinking skills. We apply THiNK to seven state-of-the-art LLMs and perform a detailed cognitive analysis of their outputs. Results reveal that while models reliably perform lower-order categories well, they struggle with applying knowledge in realistic contexts and exhibit limited abstraction. Structured feedback loops significantly improve reasoning performance, particularly in higher-order thinking. Qualitative evaluations further confirm that THiNK-guided outputs better align with domain logic and problem structure. The code of our framework provides a scalable methodology for probing and enhancing LLM reasoning, offering new directions for evaluation grounded in learning science, which is available at our GitHub repository.

Effective generalization in language models depends critically on the diversity of their training data. Yet existing diversity metrics often fall short of this goal, relying on surface-level heuristics that are decoupled from model behavior. This motivates us to ask: What kind of diversity in training data actually drives generalization in language models -- and how can we measure and amplify it? Through large-scale empirical analyses spanning over 300 training runs, carefully controlled for data scale and quality, we show that data diversity can be a strong predictor of generalization in LLM reasoning -- as measured by average model performance on unseen out-of-distribution benchmarks. We introduce G-Vendi, a metric that quantifies diversity via the entropy of model-induced gradients. Despite using a small off-the-shelf proxy model for gradients, G-Vendi consistently outperforms alternative measures, achieving strong correlation (Spearman's $ρ\approx 0.9$) with out-of-distribution (OOD) performance on both natural language inference (NLI) and math reasoning tasks. Building on this insight, we present Prismatic Synthesis, a framework for generating diverse synthetic data by targeting underrepresented regions in gradient space. Experimental results show that Prismatic Synthesis consistently improves model performance as we scale synthetic data -- not just on in-distribution test but across unseen, out-of-distribution benchmarks -- significantly outperforming state-of-the-art models that rely on 20 times larger data generator than ours. For example, PrismMath-7B, our model distilled from a 32B LLM, outperforms R1-Distill-Qwen-7B -- the same base model trained on proprietary data generated by 671B R1 -- on 6 out of 7 challenging benchmarks.

Shared understanding plays a key role in the effective communication in and performance of human-human interactions. With the increasingly common integration of AI into human contexts, the future of personal and workplace interactions will see a greater prevalence of human-AI interaction (HAII) in which the perception of shared understanding (PSU) will be important. Existing literature has addressed the processes and effects of PSU in human-human interactions, but the construal remains underexplored in HAII. To better understand PSU in that context, we conducted an online survey to collect user reflections on interactions with a large-language model when its understanding of a situation was thought to be similar or different from the participant's. Through inductive thematic analysis, we identified eight dimensions comprising PSU in human-AI interactions. The descriptive framework we derive supports an operational characterization of PSU and serves as a springboard for future work into the phenomenon.

Autonomous agents, which perceive environments and take actions to achieve goals, have become increasingly feasible with the advancements in large language models (LLMs). However, current powerful agents often depend on sophisticated prompt engineering combined with closed-source LLMs like GPT-4. Although training open-source LLMs using expert trajectories from teacher models has yielded some improvements in agent capabilities, this approach still faces limitations such as performance plateauing and error propagation. To mitigate these challenges, we propose STeP, a novel method for improving LLM-based agent training. We synthesize self-reflected trajectories that include reflections and corrections of error steps, which enhance the effectiveness of LLM agents in learning from teacher models, enabling them to become agents capable of self-reflecting and correcting. We also introduce partial masking strategy that prevents the LLM from internalizing incorrect or suboptimal steps. Experiments demonstrate that our method improves agent performance across three representative tasks: ALFWorld, WebShop, and SciWorld. For the open-source model LLaMA2-7B-Chat, when trained using self-reflected trajectories constructed with Qwen1.5-110B-Chat as the teacher model, it achieves comprehensive improvements with less training data compared to agents trained exclusively on expert trajectories.

Recent advances in Large Reasoning Models (LRMs) have significantly improved long-chain reasoning capabilities over Large Language Models (LLMs). However, LRMs often produce unnecessarily lengthy outputs even for simple queries, leading to inefficiencies or even accuracy degradation compared to LLMs. To overcome this, we propose CP-Router, a training-free and model-agnostic routing framework that dynamically selects between an LLM and an LRM, demonstrated with multiple-choice question answering (MCQA) prompts. The routing decision is guided by the prediction uncertainty estimates derived via Conformal Prediction (CP), which provides rigorous coverage guarantees. To further refine the uncertainty differentiation across inputs, we introduce Full and Binary Entropy (FBE), a novel entropy-based criterion that adaptively selects the appropriate CP threshold. Experiments across diverse MCQA benchmarks, including mathematics, logical reasoning, and Chinese chemistry, demonstrate that CP-Router efficiently reduces token usage while maintaining or even improving accuracy compared to using LRM alone. We also extend CP-Router to diverse model pairings and open-ended QA, where it continues to demonstrate strong performance, validating its generality and robustness.

Task-oriented semantic communication enhances transmission efficiency by conveying semantic information rather than exact messages. Deep learning (DL)-based semantic communication can effectively cultivate the essential semantic knowledge for semantic extraction, transmission, and interpretation by leveraging massive labeled samples for downstream task training. In this paper, we propose a self-supervised learning-based semantic communication framework (SLSCom) to enhance task inference performance, particularly in scenarios with limited access to labeled samples. Specifically, we develop a task-relevant semantic encoder using unlabeled samples, which can be collected by devices in real-world edge networks. To facilitate task-relevant semantic extraction, we introduce self-supervision for learning contrastive features and formulate the information bottleneck (IB) problem to balance the tradeoff between the informativeness of the extracted features and task inference performance. Given the computational challenges of the IB problem, we devise a practical and effective solution by employing self-supervised classification and reconstruction pretext tasks. We further propose efficient joint training methods to enhance end-to-end inference accuracy over wireless channels, even with few labeled samples. We evaluate the proposed framework on image classification tasks over multipath wireless channels. Part of this work was presented in WOCC 2024 [1]. Run Gu and Wei Xu are with National Mobile Communications Research Laboratory, Southeast University, Nanjing 210096, China, and also with Purple Mountain Laboratories, Nanjing 211111, China (e-mail: {rung, wxu }@seu.edu.cn). Zhaohui Y ang is with the Zhejiang Lab, Hangzhou 311121, China, and also with the College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, Zhejiang 310027, China (yang zhaohui@zju.edu.cn). Dusit Niyato is with the School of Computer Science and Engineering, Nanyang Technological University, Singapore 308232 (dniyato@ntu.edu.sg). A ylin Y ener is with the Department of Electrical and Computer Engineering, The Ohio State University, OH 43210, USA (yener@ece.osu.edu). 2 With the widespread deployment of edge devices and the rapid development of artificial intelligence (AI), an impressive landscape of connected intelligence is emerging [2]-[5].

Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency. We introduce Efficient Selective Language Modeling (ESLM), a risk-aware algorithm that improves training efficiency and distributional robustness by performing online token-level batch selection. ESLM leverages per-token statistics (e.g., entropy or loss) and applies value-at-risk thresholding to retain only the most informative tokens per batch. This data-centric mechanism reshapes the training loss, prioritizing high-risk tokens and eliminating redundant gradient computation. We frame ESLM as a bilevel game: the model competes with a masking adversary that selects worst-case token subsets under a constrained thresholding rule. In the loss-based setting, ESLM recovers conditional value-at-risk loss minimization, providing a principled connection to distributionally robust optimization. We extend our approach to Ada-ESLM, which adaptively tunes the selection confidence during training. Experiments on GPT-2 pretraining show that ESLM significantly reduces training FLOPs while maintaining or improving both perplexity and downstream performance compared to baselines. Our approach also scales across model sizes, pretraining corpora, and integrates naturally with knowledge distillation.

Large Reasoning Models (LRMs) demonstrate strong performance in complex tasks but often face the challenge of overthinking, leading to substantially high inference costs. Existing approaches synthesize shorter reasoning responses for LRMs to learn, but are inefficient for online usage due to the time-consuming data generation and filtering processes. Meanwhile, online reinforcement learning mainly adopts a length reward to encourage short reasoning responses, but tends to lose the reflection ability and harm the performance. To address these issues, we propose REA-RL, which introduces a small reflection model for efficient scaling in online training, offering both parallel sampling and sequential revision. Besides, a reflection reward is designed to further prevent LRMs from favoring short yet non-reflective responses. Experiments show that both methods maintain or enhance performance while significantly improving inference efficiency. Their combination achieves a good balance between performance and efficiency, reducing inference costs by 35% without compromising performance. Further analysis demonstrates that our methods are effective by maintaining reflection frequency for hard problems while appropriately reducing it for simpler ones without losing reflection ability. Codes are available at https://github.com/hexuandeng/REA-RL.