Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overcome this, we introduce MemDreamer to decouple perception and reasoning, shifting long-video understanding into an agentic exploration process. As a plug-and-play framework, it incrementally streams videos to construct a Hierarchical Graph Memory, a top-down three-tier architecture for semantic abstraction, anchored by a foundational graph capturing spatiotemporal and causal relations. During inference, the reasoning model employs agentic tool-augmented retrieval, navigating hierarchies, searching nodes, and traversing logical edges via an Observation-Reason-Action loop. Experiments show MemDreamer achieves SOTA results across four mainstream benchmarks, substantially narrowing the gap with human experts. It greatly reduces the reasoning context relative to full-context ingestion while delivering a substantial absolute accuracy gain. Furthermore, statistical analysis uncovers a strong positive linear correlation between an VLM’s performance on logic reasoning and long-video understanding benchmarks, establishing agentic capability scaling as a new paradigm for multimodal comprehension.

GUI agents often encounter dynamic anomalies when deployed on Android devices, from unexpected pop-ups to action misuse, yet existing benchmarks lack systematic evaluation of agent robustness against runtime anomalies. We introduce AnTrap, a comprehensive benchmark that injects dynamic perturbations into agent execution trajectories. We propose a taxonomy organizing real-world anomalies into four layers (State, Thinking, Action and Round) with ten fine-grained subcategories, and develop a construction pipeline that preserves task solvability while introducing realistic adversarial conditions. Evaluating 16 leading GUI models, we reveal universal vulnerability to dynamic anomalies, with even the strongest models suffering significant performance degradation. Furthermore, we conduct GRPO training in both original and adversarial environments to validate our benchmark, separating environment-learnable anomalies from reasoning-bottlenecked ones. Our findings show that while single-step traps at state and action layers are largely addressable through adversarial reinforcement learning, deep contextual traps, like state deadlock, expose intrinsic limitations that cannot be resolved by training in environments with traps alone.

Multi-agent reasoning systems adopt a generate-then-transfer paradigm that forces end-to-end latency to scale linearly with pipeline depth. We introduce StreamMA, a multi-agent reasoning system that streams each reasoning step to downstream agents as soon as it is generated, pipelining adjacent agents and thus reducing latency. Surprisingly, this pipelining also improves effectiveness: because multi-step reasoning quality is non-uniform and early steps are more reliable than later ones, working with these reliable early steps instead of the full chain prevents error-prone late steps from misleading downstream agents. We formalize both advantages with the first closed-form joint analysis of stream, serial, and single protocols, deriving the effectiveness ordering, speedup upper bound, and cost ratio. Across eight reasoning benchmarks spanning mathematics, science, and code, three frontier LLMs (Claude Opus 4.6, GPT-5.4, and GLM-5.2), and three topologies (Chain, Tree, Graph), StreamMA outperforms both baselines (avg.+7.3pp, max +22.4pp on HMMT2026; Claude Opus 4.6-High). Beyond these contributions, we discover a step-level scaling law: increasing per-agent steps consistently improves both effectiveness and efficiency, a new scaling dimension orthogonal to and composable with agent-count scaling.

Online reinforcement learning (RL) serves as an effective method for enhancing the capabilities of Android agents. However, guiding agents to learn through online interaction is prohibitively expensive due to the high latency of emulators and the sample inefficiency of existing RL algorithms. We identify a fundamental limitation in current approaches: the Single State Single Action paradigm, which updates the policy with one-to-one state-action pairs from online one-way rollouts without fully exploring each costly emulator state. In this paper, we propose Android Coach, a novel framework that shifts the training paradigm to Single State Multiple Actions, allowing the agent to sample and utilize multiple actions for a single online state. We enable this without additional emulator overhead by learning a critic that estimates action values. To ensure the critic serves as a reliable coach, we integrate a process reward model and introduce a group-wise advantage estimator based on the averaged critic outputs. Extensive experiments demonstrate the effectiveness and efficiency of Android Coach: it achieves 7.5% and 8.3% success rate improvements on AndroidLab and AndroidWorld over UI-TARS-1.5-7B, and attains 1.4x higher training efficiency than Single State Single Action methods PPO and GRPO at matched success rates.

Benchmark plays a pivotal role in assessing the advancements of large language models (LLMs). While numerous benchmarks have been proposed to evaluate LLMs’ capabilities, there is a notable absence of a dedicated benchmark for assessing their musical abilities. To address this gap, we present ZIQI-Eval, a comprehensive and large-scale music benchmark specifically designed to evaluate the music-related capabilities of LLMs.ZIQI-Eval encompasses a wide range of questions, covering 10 major categories and 56 subcategories, resulting in over 14,000 meticulously curated data entries. By leveraging ZIQI-Eval, we conduct a comprehensive evaluation over 16 LLMs to evaluate and analyze LLMs’ performance in the domain of music.Results indicate that all LLMs perform poorly on the ZIQI-Eval benchmark, suggesting significant room for improvement in their musical capabilities.With ZIQI-Eval, we aim to provide a standardized and robust evaluation framework that facilitates a comprehensive assessment of LLMs’ music-related abilities. The dataset is available at GitHub and HuggingFace.

Sentiment analysis is a fundamental task, and structure sentiment analysis (SSA) is an important component of sentiment analysis. However, traditional SSA is suffering from some important issues: (1) lack of interactive knowledge of different languages; (2) small amount of annotation data or even no annotation data. To address the above problems, we incorporate data augment and auxiliary tasks within a cross-lingual pretrained language model into SSA. Specifically, we employ XLM-Roberta to enhance mutually interactive information when parallel data is available in the pretraining stage. Furthermore, we leverage two data augment strategies and auxiliary tasks to improve the performance on few-label data and zero-shot cross-lingual settings. Experiments demonstrate the effectiveness of our models. Our models rank first on the cross-lingual sub-task and rank second on the monolingual sub-task of SemEval-2022 task 10.

机器翻译错误分析旨在找出机器译文中存在的错误,包括错误类型、错误分布等,它在机器翻译研究和应用中起着重要作用。该文将人工译后编辑与错误分析结合起来,对译后编辑操作进行错误标注,采用自动标注和人工标注相结合的方法,构建了一个细粒度英汉机器翻译错误分析语料库,其中每一个标注样本包括源语言句子、机器译文、人工参考译文、译后编辑译文、词错误率和错误类型标注;标注的错误类型包括增词、漏词、错词、词序错误、未译和命名实体翻译错误等。标注的一致性检验表明了标注的有效性;对标注语料的统计分析结果能有效地指导机器翻译系统的开发和人工译员的后编辑。