探索全球前沿学术脉络

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

arXiv:2602.12670v4 Announce Type: replace Abstract: Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired with curated Skills and deterministic verifiers. Our latest aggregate evaluation runs the 87-task benchmark under matched no-Skills and curated-Skills conditions for 18 model-harness configurations. Curated Skills raise the average pass rate from 33.9% to 50.5% (+16.6 percentage points; 25.5% normalized gain), with configuration-level gains ranging from +4.1 to +25.7 pp. Focused Skills with at most three modules outperform larger or exhaustive bundles, and smaller models with Skills can match larger models without them. SkillsBench establishes paired evaluation as the foundation for rigorous measurement of Skill efficacy on agentic, expertise-heavy work.

TS-Memory: Plug-and-Play Memory for Time Series Foundation Models

arXiv:2602.11550v2 Announce Type: replace-cross Abstract: Time Series Foundation Models (TSFMs) achieve strong zero-shot forecasting through large-scale pre-training, but adapting them to downstream domains under distribution shift remains challenging. Existing solutions face a trade-off: Parametric Adaptation can cause catastrophic forgetting and requires costly multi-domain maintenance, while Non-Parametric Retrieval improves forecasts but incurs high inference latency due to datastore search. We propose Parametric Memory Distillation and implement it as TS-Memory, a lightweight memory adapter that augments frozen TSFMs. TS-Memory is trained in two stages. First, we construct an offline, retrieval-leakage-safe kNN teacher that synthesizes confidence-aware quantile targets from retrieved futures. Second, we distill this retrieval-induced distributional correction into a lightweight memory adapter via confidence-gated supervision. During inference, TS-Memory fuses memory and backbone predictions with constant-time overhead, enabling retrieval-free deployment. Experiments across diverse TSFMs and benchmarks demonstrate consistent improvements in both point and probabilistic forecasting over representative adaptation methods, with efficiency comparable to the frozen backbone. Code: https://github.com/sisuolv/TS-Memory.

MCR-VQGAN: A Scalable and Cost-Effective Tau PET Synthesis Approach for Alzheimer's Disease Imaging

Tau positron emission tomography (PET) is a critical diagnostic modality for Alzheimer's disease (AD), but its widespread clinical adoption is hindered by radiation exposure, limited availability, high clinical workload, and substantial financial costs. To address these limitations, we propose the Multi-scale CBAM Residual Vector Quantized Generative Adversarial Network (MCR-VQGAN) to synthesize high-fidelity tau PET images from structural T1-weighted MRI. MCR-VQGAN advances the standard VQGAN architecture through three enhancements: multi-scale convolutions, ResNet blocks, and Convolutional Block Attention Modules (CBAM), which collectively improve the capture of local and global features. Using 222 paired T1-weighted MRI and tau PET scans from the ADNI database, we trained and compared MCR-VQGAN against cGAN, WGAN-GP, CycleGAN, and baseline VQGAN. MCR-VQGAN achieved superior image synthesis performance across all metrics (MSE = 0.0056 +/- 0.0061, PSNR = 30.65 +/- 4.47 dB, SSIM = 0.9263 +/- 0.0469). A CNN-based AD classifier trained on real tau PET achieved comparable accuracy on real (63.64%) and synthetic (65.91%) images, indicating that diagnostically relevant features are preserved. Regional SUVR-equivalent analysis across Braak-defined ROIs further indicated strong agreement between real and synthetic tau PET (Pearson r = 0.78-0.88; ICC = 0.71-0.84), with the strongest agreement in Braak V/VI (ICC = 0.838). Together, these results suggest that MCR-VQGAN offers a promising and scalable surrogate for conventional tau PET imaging, potentially improving the accessibility of tau biomarkers for AD research and clinical workflows.

Cosmos 3: Omnimodal World Models for Physical AI

We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. By supporting highly flexible input-output configurations, Cosmos 3 seamlessly unifies critical modalities for Physical AI – effectively subsuming vision-language models, video generators, world simulators, and world-action models into a single framework. Our evaluation demonstrates that Cosmos 3 establishes a new state-of-the-art across a diverse suite of understanding and generation tasks, demonstrating omnimodal world models as scalable, general-purpose backbones for embodied agents. Our post-trained Cosmos 3 models were ranked as the best open-source Text-to-Image and Image-to-Video models by Artificial Analysis, and the best policy model by RoboArena at the time the technical report was written. To accelerate open research and deployment in Physical AI, we make our code, model checkpoints, curated synthetic datasets, and evaluation benchmark available under the Linux Foundation's OpenMDW-1.1 License at https://github.com/nvidia/cosmos and https://huggingface.co/collections/nvidia/cosmos3. The project website is available at https://research.nvidia.com/labs/cosmos-lab/cosmos3.

Agents' Last Exam

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long horizon, economically valuable, real world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 sub fields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is below 1%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP relevant impact.