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.

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.

Generating long, informative, and factual outputs remains a major challenge for Large Language Models (LLMs). Existing benchmarks for long-form generation typically assess real-world queries with hard-to-verify metrics or use synthetic setups that ease evaluation but overlook real-world intricacies. In this paper, we introduce LongWeave, which balance real-world and verifiable assessment with Target-Anchored Evaluation (TAE). TAE constructs tasks by first defining verifiable targets within real-world scenarios, then systematically generating corresponding queries, textual materials, and anchors based on these targets. This ensures that tasks are both realistic and objectively assessable, enabling rigorous assessment of model capabilities in meeting complex real-world constraints. LongWeave supports customizable input/output lengths (up to 64K/8K tokens) across seven distinct tasks. Evaluation on 23 LLMs show that even state-of-the-art models encounter significant challenges in long-form generation as real-world complexity and output length increase. Dataset will be publicly available.

While Large Language Models (LLMs) support long contexts, they struggle with performance degradation within the context window. Current solutions incur prohibitive training costs, leaving statistical behaviors and cost-effective approaches underexplored. From the decoding perspective, we identify the Posterior Salience Attenuation (PSA) phenomenon, where the salience ratio correlates with long-text performance degradation. Notably, despite the attenuation, gold tokens still occupy high-ranking positions in the decoding space. Motivated by it, we propose the training-free Positional Contrastive Decoding (PCD) that contrasts the logits derived from long-aware attention with those from designed local-aware attention, enabling the model to focus on the gains introduced by large-scale short-to-long training. Through the analysis of long-term decay simulation, we demonstrate that PCD effectively alleviates attention score degradation. Experimental results show that PCD achieves state-of-the-art performance on long-context benchmarks.