Recent advances in Medical Large Language Models have shown strong performance in medical question answering and clinical knowledge understanding, yet real-world clinical practice requires long-horizon, dynamic treatment decision-making rather than static prediction. Existing medical agent environments are mostly turn-based, assuming patient states change after actions while overlooking natural disease progression and delayed treatment effects. We propose MedACE, a time-aware asynchronous clinical world model, where patient evolution is formulated as an elapsed-time-conditioned process driven by historical observations, treatment actions, clinical context, and disease-level knowledge. Built from timestamped MIMIC-IV trajectories, our JEPA-style simulator, MedWorld-JEPA, learns future patient state representations in latent space rather than directly generating noisy clinical observations. Based on this simulator, we construct an asynchronous treatment environment with global time advancement, closed-loop patient simulation, multi-step physician-agent interaction, and outcome-grounded rewards. Experiments on Hospital and ICU scenarios demonstrate competitive physiological forecasting, strong clinical consistency, and the importance of jointly modeling time, disease progression, and treatment effects. Agent evaluations further show that current LLM-based physicians struggle with long-horizon treatment decisions, highlighting our environment as a challenging foundation for future medical treatment agents.

High-quality, diverse data are vital for large language models (LLMs) but remain scarce and costly. Data synthesis is a viable alternative and succeeds on closed tasks, yet the humanities and social sciences (HSS) are overlooked, and their open-ended nature makes synthesis challenging.Moving beyond prior capability-centric, fragmented attempts, we adopt a subject-centric paradigm, define the first HSS domain system covering 14 mainstream fields, and introduce HSS-Synth—the first data synthesis pipeline for HSS.HSS-Synth comprises: (1) constructing seed document from web corpora via multi-step filtering and text refinement evaluated by a judge; (2) specifying “requirements + persona” to backtranslate seed document into diverse yet faithful instructions with strict Q&A alignment check; and (3) breaking LLM response limits via teacher-forced Answering that fed seed documents during response to anchor semantics, reduce hallucinations, and preserve tone and integrity.HSS-Synth yields 237k high-quality, diverse instruction-tuning samples that outperform 14 leading baselines on 16 benchmarks. The fine-tuned Qwen3-8B-Base set new SOTA and approached official Qwen3-8B, improving both human preference and knowledge capability without performance seesaws. Extensive experiments demonstrate the HSS-Synth’s robustness and transferability.Our code is publicly available at https://github.com/pengr/HSS-Synth.

Vision–language models (VLMs) have demonstrated impressive capabilities in general medical visual question answering, yet it remains unclear whether their predictions reflect evidence-grounded clinical reasoning or reliance on spurious priors. We introduce Med-R2 Bench, a hierarchical benchmark aligned with the clinical workflow to evaluate adversarial robustness with visual grounding. We design stepwise QA tasks to assess whether reasoning chains are strictly grounded in visual evidence across the four clinical stages, and employ adversarial perturbations to test robustness against misleading cues. Med-R2 comprises 42,432 images, 31 task categories, and 110,406 QA pairs. Evaluation across 14 VLMs reveals a sequential performance degradation along the four-stage clinical workflow. Adversarial experiments show that models rely heavily on correct prompts to guess answers. Even when provided with explicit visual cues, the models struggle to accurately align textual descriptions. Finally, we demonstrate that stepwise fine-tuning using our hierarchical data significantly improves reasoning robustness, highlighting its potential to drive future improvements in evidence-based medical AI.

Large language models (LLMs) are prone to capturing biases from training corpus, leading to potential negative social impacts. Existing prompt-based debiasing methods exhibit instability due to their sensitivity to prompt changes, while fine-tuning-based techniques incur substantial computational overhead and catastrophic forgetting. In this paper, we propose FairSteer, a novel inference-time debiasing framework without requiring customized prompt design or model retraining. Motivated by the linear representation hypothesis, our preliminary investigation demonstrates that fairness-related features can be encoded into separable directions in the hidden activation space. FairSteer operates in three steps: biased activation detection, debiasing steering vector (DSV) computation, and dynamic activation steering. Specifically, it first trains a lightweight linear classifier to detect bias signatures in activations, and then computes DSVs as intervention directions derived from small contrastive prompt pairs. Subsequently, it performs debiasing by adjusting activations with DSVs in the inference stage. Comprehensive evaluation with six LLMs demonstrates the superiority of FairSteer across question-answering, counterfactual input evaluation and open-ended text generation tasks. Code will be released.

Identifying bias in LLM-generated content is a crucial prerequisite for ensuring fairness in LLMs. Existing methods, such as fairness classifiers and LLM-based judges, face limitations related to difficulties in understanding underlying intentions and the lack of criteria for fairness judgment. In this paper, we introduce BiasGuard, a novel bias detection tool that explicitly analyzes inputs and reasons through fairness specifications to provide accurate judgments. BiasGuard is implemented through a two-stage approach: the first stage initializes the model to explicitly reason based on fairness specifications, while the second stage leverages reinforcement learning to enhance its reasoning and judgment capabilities. Our experiments, conducted across five datasets, demonstrate that BiasGuard outperforms existing tools, improving accuracy and reducing over-fairness misjudgments. We also highlight the importance of reasoning-enhanced decision-making and provide evidence for the effectiveness of our two-stage optimization pipeline.

Video Temporal Grounding (VTG) aims to localize relevant temporal segments in videos given natural language queries. Despite recent progress with large vision-language models (LVLMs) and instruction-tuning, existing approaches often suffer from limited temporal awareness and poor generalization. In this work, we introduce a two-stage training framework that integrates supervised fine-tuning with reinforcement learning (RL) to improve both the accuracy and robustness of VTG models. Our approach first leverages high-quality curated cold-start data for SFT initialization, followed by difficulty-controlled RL to further enhance temporal localization and reasoning abilities. Comprehensive experiments on multiple VTG benchmarks demonstrate that our method consistently outperforms existing models, particularly in challenging and open-domain scenarios. We conduct an in-depth analysis of training strategies and dataset curation, highlighting the importance of both high-quality cold-start data and difficulty-controlled RL. To facilitate further research and industrial adoption, we release all intermediate datasets, models, and code to the community.

Evaluating the bias of LLMs becomes more crucial with their rapid development. However, existing evaluation approaches rely on fixed-form outputs and cannot adapt to the flexible open-text generation scenarios of LLMs (e.g., sentence completion and question answering). To address this, we introduce BiasAlert, a plug-and-play tool designed to detect social bias in open-text generations of LLMs. BiasAlert integrates external human knowledge with its inherent reasoning capabilities to detect bias reliably. Extensive experiments demonstrate that BiasAlert significantly outperforms existing state-of-the-art methods like GPT-4-as-Judge in detecting bias. Furthermore, through application studies, we showcase the utility of BiasAlert in reliable LLM fairness evaluation and bias mitigation across various scenarios. Model and code will be publicly released.