Bo Zheng

Peng Chen, Pi Bu, Yingyao Wang et al.

Recent advances in Vision-Language-Action models (VLAs) have expanded the capabilities of embodied intelligence. However, significant challenges remain in real-time decision-making in complex 3D environments, which demand second-level responses, high-resolution perception, and tactical reasoning under dynamic conditions. To advance the field, we introduce CombatVLA, an efficient VLA model optimized for combat tasks in 3D action role-playing games(ARPGs). Specifically, our CombatVLA is a 3B model trained on video-action pairs collected by an action tracker, where the data is formatted as action-of-thought (AoT) sequences. Thereafter, CombatVLA seamlessly integrates into an action execution framework, allowing efficient inference through our truncated AoT strategy. Experimental results demonstrate that CombatVLA not only outperforms all existing models on the combat understanding benchmark but also achieves a 50-fold acceleration in game combat. Moreover, it has a higher task success rate than human players. We will open-source all resources, including the action tracker, dataset, benchmark, model weights, training code, and the implementation of the framework at https://combatvla.github.io/.

Jiashun Liu, Johan Obando-Ceron, Han Lu et al.

Most recent RL for LLMs (RL4LLM) methods avoid explicit critics, replacing them with average advantage baselines. This shift is largely pragmatic: conventional value functions are computationally expensive to train at LLM scale and often fail under sparse rewards and long reasoning horizons. We revisit this bottleneck from an architectural perspective and introduce Asymmetric Proximal Policy Optimization (AsyPPO), a simple and scalable framework that restores the critics role while remaining efficient in large-model settings. AsyPPO employs a set of lightweight mini-critics, each trained on disjoint prompt shards. This design encourages diversity while preserving calibration, reducing value-estimation bias. Beyond robust estimation, AsyPPO leverages inter-critic uncertainty to refine the policy update: (i) masking advantages in states where critics agree and gradients add little learning signal, and (ii) filtering high-divergence states from entropy regularization, suppressing spurious exploration. After training on open-source data with only 5,000 samples, AsyPPO consistently improves learning stability and performance across multiple benchmarks over strong baselines, such as GRPO, achieving performance gains of more than six percent on Qwen3-4b-Base and about three percent on Qwen3-8b-Base and Qwen3-14b-Base over classic PPO, without additional tricks. These results highlight the importance of architectural innovations for scalable, efficient algorithms.

Jingyu Liu, Jingquan Peng, xiaopeng Wu et al.

Despite the widespread application of Large Language Models (LLMs) across various domains, they frequently exhibit overconfidence when encountering uncertain scenarios, yet existing solutions primarily rely on evasive responses (e.g., "I don't know") overlooks the opportunity of identifying and addressing the uncertainty to generate more satisfactory responses. To systematically investigate and improve LLMs' ability of recognizing and addressing the source of uncertainty, we introduce \textbf{ConfuseBench}, a benchmark mainly focus on three types of uncertainty: document scarcity, limited capability, and query ambiguity. Experiments with ConfuseBench reveal that current LLMs struggle to accurately identify the root cause of uncertainty and solve it. They prefer to attribute uncertainty to query ambiguity while overlooking capability limitations, especially for those weaker models. To tackle this challenge, we first generate context-aware inquiries that highlight the confusing aspect of the original query. Then we judge the source of uncertainty based on the uniqueness of the inquiry's answer. Further we use an on-policy training method, InteractDPO to generate better inquiries. Experimental results demonstrate the efficacy of our approach.

Chao Yi, Dian Chen, Gaoyang Guo et al.

Recommender systems are among the most impactful applications of artificial intelligence, serving as critical infrastructure connecting users, merchants, and platforms. However, most current industrial systems remain heavily reliant on historical co-occurrence patterns and log-fitting objectives, i.e., optimizing for past user interactions without explicitly modeling user intent. This log-fitting approach often leads to overfitting to narrow historical preferences, failing to capture users' evolving and latent interests. As a result, it reinforces filter bubbles and long-tail phenomena, ultimately harming user experience and threatening the sustainability of the whole recommendation ecosystem. To address these challenges, we rethink the overall design paradigm of recommender systems and propose RecGPT, a next-generation framework that places user intent at the center of the recommendation pipeline. By integrating large language models (LLMs) into key stages of user interest mining, item retrieval, and explanation generation, RecGPT transforms log-fitting recommendation into an intent-centric process. To effectively align general-purpose LLMs to the above domain-specific recommendation tasks at scale, RecGPT incorporates a multi-stage training paradigm, which integrates reasoning-enhanced pre-alignment and self-training evolution, guided by a Human-LLM cooperative judge system. Currently, RecGPT has been fully deployed on the Taobao App. Online experiments demonstrate that RecGPT achieves consistent performance gains across stakeholders: users benefit from increased content diversity and satisfaction, merchants and the platform gain greater exposure and conversions. These comprehensive improvement results across all stakeholders validates that LLM-driven, intent-centric design can foster a more sustainable and mutually beneficial recommendation ecosystem.

Qianqian Zhang, Xinru Liao, Quan Liu et al.

Advertisers play an essential role in many e-commerce platforms like Taobao and Amazon. Fulfilling their marketing needs and supporting their business growth is critical to the long-term prosperity of platform economies. However, compared with extensive studies on user modeling such as click-through rate predictions, much less attention has been drawn to advertisers, especially in terms of understanding their diverse demands and performance. Different from user modeling, advertiser modeling generally involves many kinds of tasks (e.g. predictions of advertisers' expenditure, active-rate, or total impressions of promoted products). In addition, major e-commerce platforms often provide multiple marketing scenarios (e.g. Sponsored Search, Display Ads, Live Streaming Ads) while advertisers' behavior tend to be dispersed among many of them. This raises the necessity of multi-task and multi-scenario consideration in comprehensive advertiser modeling, which faces the following challenges: First, one model per scenario or per task simply doesn't scale; Second, it is particularly hard to model new or minor scenarios with limited data samples; Third, inter-scenario correlations are complicated, and may vary given different tasks. To tackle these challenges, we propose a multi-scenario multi-task meta learning approach (M2M) which simultaneously predicts multiple tasks in multiple advertising scenarios.

Guannan Geng, Qingyang Xiao, Shigan Liu et al.

Air pollution has altered the Earth radiation balance, disturbed the ecosystem and increased human morbidity and mortality. Accordingly, a full-coverage high-resolution air pollutant dataset with timely updates and historical long-term records is essential to support both research and environmental management. Here, for the first time, we develop a near real-time air pollutant database known as Tracking Air Pollution in China (TAP, tapdata.org) that combines information from multiple data sources, including ground measurements, satellite retrievals, dynamically updated emission inventories, operational chemical transport model simulations and other ancillary data. Daily full-coverage PM2.5 data at a spatial resolution of 10 km is our first near real-time product. The TAP PM2.5 is estimated based on a two-stage machine learning model coupled with the synthetic minority oversampling technique and a tree-based gap-filling method. Our model has an averaged out-of-bag cross-validation R2 of 0.83 for different years, which is comparable to those of other studies, but improves its performance at high pollution levels and fills the gaps in missing AOD on daily scale. The full coverage and near real-time updates of the daily PM2.5 data allow us to track the day-to-day variations in PM2.5 concentrations over China in a timely manner. The long-term records of PM2.5 data since 2000 will also support policy assessments and health impact studies. The TAP PM2.5 data are publicly available through our website for sharing with the research and policy communities.