Embodied Science: Closing the Discovery Loop with Agentic Embodied AI

Artificial intelligence has demonstrated remarkable capability in predicting scientific properties, yet scientific discovery remains an inherently physical, long-horizon pursuit governed by experimental cycles. Most current computational approaches are misaligned with this reality, framing discovery as isolated, task-specific predictions rather than continuous interaction with the physical world. Here, we argue for embodied science, a paradigm that reframes scientific discovery as a closed loop tightly coupling agentic reasoning with physical execution. We propose a unified Perception-Language-Action-Discovery (PLAD) framework, wherein embodied agents perceive experimental environments, reason over scientific knowledge, execute physical interventions, and internalize outcomes to drive subsequent exploration. By grounding computational reasoning in robust physical feedback, this approach bridges the gap between digital prediction and empirical validation, offering a roadmap for autonomous discovery systems in the life and chemical sciences.

Developing Foundation Models for Universal Segmentation from 3D Whole-Body Positron Emission Tomography

Positron emission tomography (PET) is a key nuclear medicine imaging modality that visualizes radiotracer distributions to quantify in vivo physiological and metabolic processes, playing an irreplaceable role in disease management. Despite its clinical importance, the development of deep learning models for quantitative PET image analysis remains severely limited, driven by both the inherent segmentation challenge from PET's paucity of anatomical contrast and the high costs of data acquisition and annotation. To bridge this gap, we develop generalist foundational models for universal segmentation from 3D whole-body PET imaging. We first build the largest and most comprehensive PET dataset to date, comprising 11041 3D whole-body PET scans with 59831 segmentation masks for model development. Based on this dataset, we present SegAnyPET, an innovative foundational model with general-purpose applicability to diverse segmentation tasks. Built on a 3D architecture with a prompt engineering strategy for mask generation, SegAnyPET enables universal and scalable organ and lesion segmentation, supports efficient human correction with minimal effort, and enables a clinical human-in-the-loop workflow. Extensive evaluations on multi-center, multi-tracer, multi-disease datasets demonstrate that SegAnyPET achieves strong zero-shot performance across a wide range of segmentation tasks, highlighting its potential to advance the clinical applications of molecular imaging.

PET-F2I: A Comprehensive Benchmark and Parameter-Efficient Fine-Tuning of LLMs for PET/CT Report Impression Generation

PET/CT imaging is pivotal in oncology and nuclear medicine, yet summarizing complex findings into precise diagnostic impressions is labor-intensive. While LLMs have shown promise in medical text generation, their capability in the highly specialized domain of PET/CT remains underexplored. We introduce PET-F2I-41K (PET Findings-to-Impression Benchmark), a large-scale benchmark for PET/CT impression generation using LLMs, constructed from over 41k real-world reports. Using PET-F2I-41K, we conduct a comprehensive evaluation of 27 models across proprietary frontier LLMs, open-source generalist models, and medical-domain LLMs, and we develop a domain-adapted 7B model (PET-F2I-7B) fine-tuned from Qwen2.5-7B-Instruct via LoRA. Beyond standard NLG metrics (e.g., BLEU-4, ROUGE-L, BERTScore), we propose three clinically grounded metrics - Entity Coverage Rate (ECR), Uncovered Entity Rate (UER), and Factual Consistency Rate (FCR) - to assess diagnostic completeness and factual reliability. Experiments reveal that neither frontier nor medical-domain LLMs perform adequately in zero-shot settings. In contrast, PET-F2I-7B achieves substantial gains (e.g., 0.708 BLEU-4) and a 3.0x improvement in entity coverage over the strongest baseline, while offering advantages in cost, latency, and privacy. Beyond this modeling contribution, PET-F2I-41K establishes a standardized evaluation framework to accelerate the development of reliable and clinically deployable reporting systems for PET/CT.

Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification

As LLM-powered agents have been used for high-stakes decision-making, such as clinical diagnosis, it becomes critical to develop reliable verification of their decisions to facilitate trustworthy deployment. Yet, existing verifiers usually underperform owing to a lack of domain knowledge and limited calibration. To address this, we establish GLEAN, an agent verification framework with Guideline-grounded Evidence Accumulation that compiles expert-curated protocols into trajectory-informed, well-calibrated correctness signals. GLEAN evaluates the step-wise alignment with domain guidelines and aggregates multi-guideline ratings into surrogate features, which are accumulated along the trajectory and calibrated into correctness probabilities using Bayesian logistic regression. Moreover, the estimated uncertainty triggers active verification, which selectively collects additional evidence for uncertain cases via expanding guideline coverage and performing differential checks. We empirically validate GLEAN with agentic clinical diagnosis across three diseases from the MIMIC-IV dataset, surpassing the best baseline by 12% in AUROC and 50% in Brier score reduction, which confirms the effectiveness in both discrimination and calibration. In addition, the expert study with clinicians recognizes GLEAN's utility in practice.

Hyperparameter Transfer Laws for Non-Recurrent Multi-Path Neural Networks

Deeper modern architectures are costly to train, making hyperparameter transfer preferable to expensive repeated tuning. Maximal Update Parametrization ($μ$P) helps explain why many hyperparameters transfer across width. Yet depth scaling is less understood for modern architectures, whose computation graphs contain multiple parallel paths and residual aggregation. To unify various non-recurrent multi-path neural networks such as CNNs, ResNets, and Transformers, we introduce a graph-based notion of effective depth. Under stabilizing initializations and a maximal-update criterion, we show that the optimal learning rate decays with effective depth following a universal -3/2 power law. Here, the maximal-update criterion maximizes the typical one-step representation change at initialization without causing instability, and effective depth is the minimal path length from input to output, counting layers and residual additions. Experiments across diverse architectures confirm the predicted slope and enable reliable zero-shot transfer of learning rates across depths and widths, turning depth scaling into a predictable hyperparameter-transfer problem.

Uncovering Modality Discrepancy and Generalization Illusion for General-Purpose 3D Medical Segmentation

While emerging 3D medical foundation models are envisioned as versatile tools with offer general-purpose capabilities, their validation remains largely confined to regional and structural imaging, leaving a significant modality discrepancy unexplored. To provide a rigorous and objective assessment, we curate the UMD dataset comprising 490 whole-body PET/CT and 464 whole-body PET/MRI scans ($\sim$675k 2D images, $\sim$12k 3D organ annotations) and conduct a thorough and comprehensive evaluation of representative 3D segmentation foundation models. Through intra-subject controlled comparisons of paired scans, we isolate imaging modality as the primary independent variable to evaluate model robustness in real-world applications. Our evaluation reveals a stark discrepancy between literature-reported benchmarks and real-world efficacy, particularly when transitioning from structural to functional domains. Such systemic failures underscore that current 3D foundation models are far from achieving truly general-purpose status, necessitating a paradigm shift toward multi-modal training and evaluation to bridge the gap between idealized benchmarking and comprehensive clinical utility. This dataset and analysis establish a foundational cornerstone for future research to develop truly modality-agnostic medical foundation models.

Kimi K2.5: Visual Agentic Intelligence

We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that two modalities enhance each other. This includes a series of techniques such as joint text-vision pre-training, zero-vision SFT, and joint text-vision reinforcement learning. Building on this multimodal foundation, K2.5 introduces Agent Swarm, a self-directed parallel agent orchestration framework that dynamically decomposes complex tasks into heterogeneous sub-problems and executes them concurrently. Extensive evaluations show that Kimi K2.5 achieves state-of-the-art results across various domains including coding, vision, reasoning, and agentic tasks. Agent Swarm also reduces latency by up to $4.5\times$ over single-agent baselines. We release the post-trained Kimi K2.5 model checkpoint to facilitate future research and real-world applications of agentic intelligence.

Small-Margin Preferences Still Matter-If You Train Them Right

Preference optimization methods such as DPO align large language models (LLMs) using paired comparisons, but their effectiveness can be highly sensitive to the quality and difficulty of preference pairs. A common heuristic treats small-margin (ambiguous) pairs as noisy and filters them out. In this paper, we revisit this assumption and show that pair difficulty interacts strongly with the optimization objective: when trained with preference-based losses, difficult pairs can destabilize training and harm alignment, yet these same pairs still contain useful supervision signals when optimized with supervised fine-tuning (SFT). Motivated by this observation, we propose MixDPO, a simple yet effective difficulty-aware training strategy that (i) orders preference data from easy to hard (a curriculum over margin-defined difficulty), and (ii) routes difficult pairs to an SFT objective while applying a preference loss to easy pairs. This hybrid design provides a practical mechanism to leverage ambiguous pairs without incurring the optimization failures often associated with preference losses on low-margin data. Across three LLM-judge benchmarks, MixDPO consistently improves alignment over DPO and a range of widely-used variants, with particularly strong gains on AlpacaEval~2 length-controlled (LC) win rate.

Reasoning as State Transition: A Representational Analysis of Reasoning Evolution in Large Language Models

Large Language Models have achieved remarkable performance on reasoning tasks, motivating research into how this ability evolves during training. Prior work has primarily analyzed this evolution via explicit generation outcomes, treating the reasoning process as a black box and obscuring internal changes. To address this opacity, we introduce a representational perspective to investigate the dynamics of the model's internal states. Through comprehensive experiments across models at various training stages, we discover that post-training yields only limited improvement in static initial representation quality. Furthermore, we reveal that, distinct from non-reasoning tasks, reasoning involves a significant continuous distributional shift in representations during generation. Comparative analysis indicates that post-training empowers models to drive this transition toward a better distribution for task solving. To clarify the relationship between internal states and external outputs, statistical analysis confirms a high correlation between generation correctness and the final representations; while counterfactual experiments identify the semantics of the generated tokens, rather than additional computation during inference or intrinsic parameter differences, as the dominant driver of the transition. Collectively, we offer a novel understanding of the reasoning process and the effect of training on reasoning enhancement, providing valuable insights for future model analysis and optimization.

Leveraging Second-Order Curvature for Efficient Learned Image Compression: Theory and Empirical Evidence

Training learned image compression (LIC) models entails navigating a challenging optimization landscape defined by the fundamental trade-off between rate and distortion. Standard first-order optimizers, such as SGD and Adam, struggle with \emph{gradient conflicts} arising from competing objectives, leading to slow convergence and suboptimal rate-distortion performance. In this work, we demonstrate that a simple utilization of a second-order quasi-Newton optimizer, \textbf{SOAP}, dramatically improves both training efficiency and final performance across diverse LICs. Our theoretical and empirical analyses reveal that Newton preconditioning inherently resolves the intra-step and inter-step update conflicts intrinsic to the R-D objective, facilitating faster, more stable convergence. Beyond acceleration, we uncover a critical deployability benefit: second-order trained models exhibit significantly fewer activation and latent outliers. This substantially enhances robustness to post-training quantization. Together, these results establish second-order optimization, achievable as a seamless drop-in replacement of the imported optimizer, as a powerful, practical tool for advancing the efficiency and real-world readiness of LICs.