Training-free KV cache compression is essential for deploying vision-language GUI agents under memory and latency constraints, yet existing methods are designed for generic language workloads and ignore the distinctive structure of GUI interaction traces. We characterize three GUI-specific workload properties — high inter-frame visual redundancy, extremely small UI-element spatial footprints, and near-uniform cross-layer attention sparsity — that cause existing schemes to retain as few as 39% of oracle-important KV pairs at the standard 20% budget. To address this, we propose **ST-Lite**, a training-free compression scheme whose three components each target one property: Trajectory-aware Semantic Gating (TSG) filters redundant historical frames, Component-centric Spatial Saliency (CSS) preserves fine-grained element boundaries, and a flat per-layer budget avoids hierarchical misallocation. Across seven GUI benchmarks and two backbones in the deployment-relevant β ∈ [10%, 40%] window, **ST-Lite** consistently outperforms all existing compression baselines — matching or exceeding Full Cache task accuracy on the primary backbone at the 20% budget — while delivering up to 2.35× decoding speedup at fivefold compression. Code: https://github.com/94wen94/ST-Lite

Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and external tools. Existing benchmarks, however, often evaluate these interfaces as separable capabilities, leaving long-horizon cross-interface orchestration under-tested. Thus, we introduce **WeaveBench**, a long-horizon hybrid-interface benchmark with 114 tasks across 8 real-world work domains, grounded in real user requests and publicly verifiable artifacts. Each task requires agents to combine GUI observations/actions with CLI/code operations within a single trajectory. We evaluate these tasks on a real Ubuntu desktop inside deployed CLI-agent runtimes, augmented with a minimal desktop-control plugin. We also propose a companion trajectory-aware judge that inspects deliverables, files, screenshots, logs, and action traces, while detecting shortcut behaviors such as fabricated visual evidence or hard-coded metrics. Across frontier model-runtime pairings, the best PassRate reaches only 41.2%, showing the benchmark remains far from saturated. The trajectory-aware judge further reveals that outcome-only grading substantially overestimates agent performance. Overall, **WeaveBench** exposes a critical gap in CUA evaluation and provides an effective testbed to measure whether agents can orchestrate GUI, CLI, and code operations across long-horizon real-world tasks.

Supervised fine-tuning (SFT) is widely adopted for tailoring large language models (LLMs) to specific downstream tasks. However, the substantial computational demands of LLMs hinder iterative exploration of fine-tuning datasets and accurate evaluation of individual sample importance. To address this challenge, we introduce Meta-LoRA, a memory-efficient method for automatic sample reweighting. Meta-LoRA learns to reweight fine-tuning samples by minimizing the loss on a small, high-quality validation set through an end-to-end bi-level optimization framework based on meta-learning. To reduce memory usage associated with computing second derivatives, we approximate the bi-level optimization using gradient similarity between training and validation datasets, replacing bi-dimensional gradient similarity with the product of one-dimensional activation states and their corresponding gradients. Further memory optimization is achieved by refining gradient computations, selectively applying them to the low-rank layers of LoRA, which results in as little as 4% additional memory usage. Comprehensive evaluations across benchmark datasets in mathematics, coding, and medical domains demonstrate Meta-LoRA’s superior efficacy and efficiency. The source code is available at https://github.com/liweicheng-ai/meta-lora.

Few-shot relation extraction (FSRE) has been a challenging problem since it only has a handful of training instances. Existing models follow a ‘one-for-all’ scheme where one general large model performs all individual N-way-K-shot tasks in FSRE, which prevents the model from achieving the optimal point on each task. In view of this, we propose a model generation framework that consists of one general model for all tasks and many tiny task-specific models for each individual task. The general model generates and passes the universal knowledge to the tiny models which will be further fine-tuned when performing specific tasks. In this way, we decouple the complexity of the entire task space from that of all individual tasks while absorbing the universal knowledge.Extensive experimental results on two public datasets demonstrate that our framework reaches a new state-of-the-art performance for FRSE tasks. Our code is available at: https://github.com/NLPWM-WHU/GM_GEN.