Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions

Despite great advances in tool-use capabilities of large language models (LLMs), existing evaluation benchmarks struggle to fully align with real-world scenarios. Such benchmarks mostly rely on simulated idealized user assumptions and lacks experience-oriented evaluation. These limitations fail to account for the ambiguity, uncooperative behaviors, and shifting intentions characteristic of real-world users. To fill this gap, we propose RUT-Bench, a dedicated benchmark designed to assess LLMs under diverse Real-world User Tool calling scenarios. RUT-Bench supports high-fidelity simulations covering both ideal rational patterns and heterogeneous non-ideal behaviors across single-turn and multi-turn dialogues. We conduct comprehensive evaluations on 19 widely adopted open-source and proprietary LLMs using our benchmark. Experimental results reveal that no tested LLMs achieve an overall success rate above 40%, and nearly all of them experience noticeable performance drops when facing more complicated non-ideal user inputs. Our code and data is available at https://github.com/Miaow-Lab/RUT-Bench.

Astra: a generalizable report generation foundation model for 3D computed tomography

CT interpretation requires radiologists to review hundreds of volumetric slices per examination, making reporting time-consuming and highly expertise-dependent. Automated CT report generation offers a promising route to improving clinical efficiency, yet the field still lacks a generalizable CT report generation foundation model that supports multi-region reporting and remains robust across external real-world cohorts. Intrinsic inconsistencies in reporting style and diagnostic terminology across cohorts make naive joint training prone to noisy textual supervision, thereby limiting model generalizability. Here we present Astra, a generalizable CT report generation foundation model trained on 90,678 thoracoabdominal CT-report pairs (CTRgDB) with 353,671 abnormalities spanning eight organ systems. By harmonizing report style and further refining diagnostic consistency via reinforcement learning, Astra achieves style-consistent and diagnostically accurate report generation across diverse anatomical regions and institutions. Evaluating on CTRgDB and six external cohorts, Astra achieves state-of-the-art performance with a 44.1% average improvement in fine-grained diagnostic metrics (P<0.001). In real-world clinical workflows, Astra assistance accelerates chest report drafting by 29.6% and improves abdominal report completeness by 11.3% (P<0.001). Furthermore, Astra also demonstrates broad utility as a foundation for CT AI development, improving downstream diagnostic performance and scaling vision-language pretrain through high-quality report synthesis. Overall, Astra serves as a broadly accessible clinical assistant and a pivotal infrastructure for the next generation of AI-powered healthcare.

GenClaw: Code-Driven Agentic Image Generation

Image generation models have evolved from text-conditioned pixel synthesis toward multimodal agents endowed with visual comprehension and tool invocation capabilities. Yet, existing agents remain at the mercy of underlying black-box image models. Their workflow is trapped in a repetitive cycle of prompt rewriting for generation refinement, leaving them with no mechanism to directly manipulate the canvas. In essence, the potential of LLMs to serve as a genuine "brush" for precise visual construction remains largely untapped. In this paper, we propose GenClaw, a code-driven agentic image generation paradigm that empowers the agent to create like a human artist: first conceptualizing, then sketching, and finally coloring. Specifically, the agent first constructs the conceptual knowledge and context through search and reasoning. It then utilizes code (e.g., SVG, HTML, Three.js) to render executable visual sketches. Finally, it employs an image generation model to supplement textures, materials, and photorealism. In this workflow, code serves as a controllable intermediate canvas bridging linguistic reasoning and pixel synthesis, seamlessly integrating programmatic logic with the visual expressiveness of generative models. By transforming image generation from a black-box paradigm into a staged process akin to authentic human creation, GenClaw offers a step toward for highly controllable and interpretable visual generation systems.

Echo4DIR: 4D Implicit Heart Reconstruction from 2D Echocardiography Videos

Reconstructing 4D (3D+t) cardiac geometry from sparse 2D echocardiography is highly desirable yet fundamentally challenged by geometric ambiguity and temporal discontinuity. To tackle these issues, we propose Echo4DIR, a novel test-time 4D implicit reconstruction framework. Specifically, we learn robust 3D shape priors from statistical shape models (SSMs) via a cardiac conditional SDF, constructing an Epipolar Mask Encoder module with epipolar cross attention to effectively fuse multi-view features. To bridge the synthetic-to-real domain gap, we introduce a self-supervised SDF-tailored differentiable rendering strategy for patient-specific 3D shape adaptation using uncalibrated clinical masks without requiring 3D ground truth. Crucially, the inherent continuity of implicit representation overcomes sparse observations, enabling anatomically reliable geometry at arbitrary resolutions. Furthermore, to empower our framework with physically continuous 4D extension, we introduce a Radial SDF Alignment strategy that strictly locks shape evolution to the predicted velocity field, fundamentally eliminating mesh drift. Extensive experiments on synthetic benchmarks and real clinical datasets demonstrate that Echo4DIR achieves state-of-the-art 4D cardiac mesh reconstruction, notably yielding an impressive clinical overlap of up to 98.35% Dice and 96.75% IoU.

Dynamic Shapley Computation

Shapley-based data valuation provides a principled way to quantify the contribution of training data, but its high computational cost makes it impractical in dynamic settings where tasks and training players evolve. Existing methods treat Shapley computation as a one-shot process and collapse contributions into aggregated scores, preventing reuse and requiring recomputation under any change. We introduce a new perspective that represents Shapley values as a player-by-task matrix and formulates dynamic valuation as a structured matrix maintenance problem. We exploit the fact that each task depends on a small subset of training players and that similar tasks yield similar valuations, leading to utility locality and coalition locality. Based on these insights, we propose D-Shap, a dynamic valuation framework that enables efficient updates by modifying only a small portion of the matrix: new task valuations are inferred via structure-aware interpolation, while updates induced by new players are confined to affected local matrix blocks. To eliminate the need for pre-specified evaluation tasks, we introduce self-valuation, which constructs the initial matrix directly from training data, supported by scalable subset reuse and coverage-aware anchor selection. Experiments across diverse models show that D-Shap performs task updates in milliseconds and reduces the cost of player updates by up to three orders of magnitude, while achieving valuation quality competitive with full recomputation.

RePCM: Region-Specific and Phenotype-Adaptive Bi-Ventricular Cardiac Motion Synthesis

Cardiac motion over a cardiac cycle is crucial for quantifying regional function and is strongly affected by cardiovascular diseases. Since temporally dense mesh sequences are difficult to obtain in practice, we focus on leveraging the more accessible end-diastolic frame to infer a full-cycle sequence. Due to strong regional and disease-specific differences, traditional methods often oversmooth the data by relying on generative models that are optimized for global patterns. To address this problem, we propose Region-Aware and Phenotype-Adaptive Bi-Ventricular Cardiac Motion Synthesis (RePCM) for single frame Bi-ventricular mesh motion completion. In Stage I, a reconstruction network learns vertex wise motion descriptors and clustering yields a data driven functional partition, providing an explicit motion derived region structure. In Stage II, a Region-Specific Injection Module enforces masked, synchronized region exchange within a conditional VAE, preserving localized specific dynamics and restricting cross-region mixing. A Phenotype-Adaptive Mixture-of-Experts prior conditioned on ED shape uses anatomy-guided cues to model latent motion trends and capture inter-disease variability. Experiments on three datasets covering different cardiovascular diseases show consistent gains in geometric and functional metrics and improved preservation of region specific dynamics.

NodeSynth: Socially Aligned Synthetic Data for AI Evaluation

Recent advancements in generative AI facilitate large-scale synthetic data generation for model evaluation. However, without targeted approaches, these datasets often lack the sociotechnical nuance required for sensitive domains. We introduce NodeSynth, an evidence-grounded methodology that generates socially relevant synthetic queries by leveraging a fine-tuned taxonomy generator (TaG) anchored in real-world evidence. Evaluated against four mainstream LLMs (e.g., Claude 4.5 Haiku), NodeSynth elicited failure rates up to five times higher than human-authored benchmarks. Ablation studies confirm that our granular taxonomic expansion significantly drives these failure rates, while independent validation reveals critical deficiencies in prominent guard models (e.g., Llama-Guard-3). We open-source our end-to-end research prototype and datasets to enable scalable, high-stakes model evaluation and targeted safety interventions (https://github.com/google-research/nodesynth).

MPCEval: A Benchmark for Multi-Party Conversation Generation

Multi-party conversation generation, such as smart reply and collaborative assistants, is an increasingly important capability of generative AI, yet its evaluation remains a critical bottleneck. Compared to two-party dialogue, multi-party settings introduce distinct challenges, including complex turn-taking, role-dependent speaker behavior, long-range conversational structure, and multiple equally valid continuations. Accordingly, we introduce MPCEval, a task-aware evaluation and benchmarking suite for multi-party conversation generation. MPCEval decomposes generation quality into speaker modeling, content quality, and speaker--content consistency, and explicitly distinguishes local next-turn prediction from global full-conversation generation. It provides novel, quantitative, reference-free, and reproducible metrics that scale across datasets and models. We apply MPCEval to diverse public and real-world datasets and evaluate modern generation methods alongside human-authored conversations. The results reveal systematic, dimension-specific model characteristics in participation balance, content progression and novelty, and speaker--content consistency, demonstrating that evaluation objectives critically shape model assessment and that single-score evaluation obscures fundamental differences in multi-party conversational behavior. The implementation of MPCEval and the associated evaluation code are publicly available at https://github.com/Owen-Yang-18/MPCEval.

Local Shapley: Model-Induced Locality and Optimal Reuse in Data Valuation

The Shapley value provides a principled foundation for data valuation, but exact computation is #P-hard due to the exponential coalition space. Existing accelerations remain global and ignore a structural property of modern predictors: for a given test instance, only a small subset of training points influences the prediction. We formalize this model-induced locality through support sets defined by the model's computational pathway (e.g., neighbors in KNN, leaves in trees, receptive fields in GNNs), showing that Shapley computation can be projected onto these supports without loss when locality is exact. This reframes Shapley evaluation as a structured data processing problem over overlapping support-induced subset families rather than exhaustive coalition enumeration. We prove that the intrinsic complexity of Local Shapley is governed by the number of distinct influential subsets, establishing an information-theoretic lower bound on retraining operations. Guided by this result, we propose LSMR (Local Shapley via Model Reuse), an optimal subset-centric algorithm that trains each influential subset exactly once via support mapping and pivot scheduling. For larger supports, we develop LSMR-A, a reuse-aware Monte Carlo estimator that remains unbiased with exponential concentration, with runtime determined by the number of distinct sampled subsets rather than total draws. Experiments across multiple model families demonstrate substantial retraining reductions and speedups while preserving high valuation fidelity.

Step-Level Sparse Autoencoder for Reasoning Process Interpretation

Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated to analyze. While Sparse Autoencoders (SAEs) have emerged as a powerful tool for interpretability, existing approaches predominantly operate at the token level, creating a granularity mismatch when capturing more critical step-level information, such as reasoning direction and semantic transitions. In this work, we propose step-level sparse autoencoder (SSAE), which serves as an analytical tool to disentangle different aspects of LLMs' reasoning steps into sparse features. Specifically, by precisely controlling the sparsity of a step feature conditioned on its context, we form an information bottleneck in step reconstruction, which splits incremental information from background information and disentangles it into several sparsely activated dimensions. Experiments on multiple base models and reasoning tasks show the effectiveness of the extracted features. By linear probing, we can easily predict surface-level information, such as generation length and first token distribution, as well as more complicated properties, such as the correctness and logicality of the step. These observations indicate that LLMs should already at least partly know about these properties during generation, which provides the foundation for the self-verification ability of LLMs. The code is available at https://github.com/Miaow-Lab/SSAE