Mingming Zhao

GLM-5 Team, Aohan Zeng, Xin Lv et al. · tsinghua

We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context fidelity. To advance model alignment and autonomy, we implement a new asynchronous reinforcement learning infrastructure that drastically improves post-training efficiency by decoupling generation from training. Furthermore, we propose novel asynchronous agent RL algorithms that further improve RL quality, enabling the model to learn from complex, long-horizon interactions more effectively. Through these innovations, GLM-5 achieves state-of-the-art performance on major open benchmarks. Most critically, GLM-5 demonstrates unprecedented capability in real-world coding tasks, surpassing previous baselines in handling end-to-end software engineering challenges. Code, models, and more information are available at https://github.com/zai-org/GLM-5.

Lin Liu, Mingming Zhao, Shanxin Yuan et al.

Image compression aims to reduce the information redundancy in images. Most existing neural image compression methods rely on side information from hyperprior or context models to eliminate spatial redundancy, but rarely address the channel redundancy. Inspired by the mask sampling modeling in recent self-supervised learning methods for natural language processing and high-level vision, we propose a novel pretraining strategy for neural image compression. Specifically, Cube Mask Sampling Module (CMSM) is proposed to apply both spatial and channel mask sampling modeling to image compression in the pre-training stage. Moreover, to further reduce channel redundancy, we propose the Learnable Channel Mask Module (LCMM) and the Learnable Channel Completion Module (LCCM). Our plug-and-play CMSM, LCMM, LCCM modules can apply to both CNN-based and Transformer-based architectures, significantly reduce the computational cost, and improve the quality of images. Experiments on the public Kodak and Tecnick datasets demonstrate that our method achieves competitive performance with lower computational complexity compared to state-of-the-art image compression methods.

GLM-4. 5 Team, Aohan Zeng, Xin Lv et al.

We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that supports both thinking and direct response modes. Through multi-stage training on 23T tokens and comprehensive post-training with expert model iteration and reinforcement learning, GLM-4.5 achieves strong performance across agentic, reasoning, and coding (ARC) tasks, scoring 70.1% on TAU-Bench, 91.0% on AIME 24, and 64.2% on SWE-bench Verified. With much fewer parameters than several competitors, GLM-4.5 ranks 3rd overall among all evaluated models and 2nd on agentic benchmarks. We release both GLM-4.5 (355B parameters) and a compact version, GLM-4.5-Air (106B parameters), to advance research in reasoning and agentic AI systems. Code, models, and more information are available at https://github.com/zai-org/GLM-4.5.

Mingming Zhao, Lin Liu, Lifu Liu et al.

The downlink channel state information (CSI) estimation and low overhead acquisition are the major challenges for massive MIMO systems in frequency division duplex to enable high MIMO gain. Recently, numerous studies have been conducted to harness the power of deep neural networks for better channel estimation and feedback. However, existing methods have yet to fully exploit the intrinsic correlation features present in CSI. As a consequence, distinct network structures are utilized for handling these two tasks separately. To achieve joint channel estimation and feedback, this paper proposes an encoder-decoder based network that unveils the intrinsic frequency-domain correlation within the CSI matrix. The entire encoder-decoder network is utilized for channel compression. To effectively capture and restructure correlation features, a self-mask-attention coding is proposed, complemented by an active masking strategy designed to improve efficiency. The channel estimation is achieved through the decoder part, wherein a lightweight multilayer perceptron denoising module is utilized for further accurate estimation. Extensive experiments demonstrate that our method not only outperforms state-of-the-art channel estimation and feedback techniques in joint tasks but also achieves beneficial performance in individual tasks.

Yiming Pan, Chengwei Hu, Xuancheng Huang et al.

Large language models (LLMs) have demonstrated strong potential in agentic tasks, particularly in slide generation. However, slide generation poses a fundamental challenge: the generation process is text-centric, whereas its quality is governed by visual aesthetics. This modality gap leads current models to frequently produce slides with aesthetically suboptimal layouts. Existing solutions typically rely either on heavy visual reflection, which incurs high inference cost yet yields limited gains; or on fine-tuning with large-scale datasets, which still provides weak and indirect aesthetic supervision. In contrast, the explicit use of aesthetic principles as supervision remains unexplored. In this work, we present AeSlides, a reinforcement learning framework with verifiable rewards for Aesthetic layout supervision in Slide generation. We introduce a suite of meticulously designed verifiable metrics to quantify slide layout quality, capturing key layout issues in an accurate, efficient, and low-cost manner. Leveraging these verifiable metrics, we develop a GRPO-based reinforcement learning method that directly optimizes slide generation models for aesthetically coherent layouts. With only 5K training prompts on GLM-4.7-Flash, AeSlides improves aspect ratio compliance from 36% to 85%, while reducing whitespace by 44%, element collisions by 43%, and visual imbalance by 28%. Human evaluation further shows a substantial improvement in overall quality, increasing scores from 3.31 to 3.56 (+7.6%), outperforming both model-based reward optimization and reflection-based agentic approaches, and even edging out Claude-Sonnet-4.5. These results demonstrate that such a verifiable aesthetic paradigm provides an efficient and scalable approach to aligning slide generation with human aesthetic preferences. Our repository is available at https://github.com/ympan0508/aeslides.

Mingming Zhao, Xiaokang Wei, Yuanqi Shao et al.

Large language models (LLMs) have shown strong potential in automating the design of agentic workflows. However, existing methods still rely heavily on manually predefined operators, limiting generalization and scalability. To address this issue, we propose $A^2Flow$, a fully automated framework for agentic workflow generation based on self-adaptive abstraction operators. $A^2Flow$ employs a three-stage operator extraction process: 1) Case-based Initial Operator Generation: leveraging expert demonstrations and LLM reasoning to generate case-specific operators; 2) Operator Clustering and Preliminary Abstraction: grouping similar operators across tasks to form preliminary abstractions; and 3) Deep Extraction for Abstract Execution Operators: applying long chain-of-thought prompting and multi-path reasoning to derive compact and generalizable execution operators. These operators serve as reusable building blocks for workflow construction without manual predefinition. Furthermore, we enhance node-level workflow search with an operator memory mechanism, which retains historical outputs to enrich context and improve decision-making. Experiments on general and embodied benchmarks show that $A^2Flow$ achieves a 2.4\% and 19.3\% average performance improvement and reduces resource usage by 37\% over state-of-the-art baselines. Homepage:https://github.com/pandawei-ele/A2FLOW

Yihong Tang, Kehai Chen, Liang Yue et al.

With the rise of large language models (LLMs), LLM agents capable of autonomous reasoning, planning, and executing complex tasks have become a frontier in artificial intelligence. However, how to translate the research on general agents into productivity that drives industry transformations remains a significant challenge. To address this, this paper systematically reviews the technologies, applications, and evaluation methods of industry agents based on LLMs. Using an industry agent capability maturity framework, it outlines the evolution of agents in industry applications, from "process execution systems" to "adaptive social systems." First, we examine the three key technological pillars that support the advancement of agent capabilities: Memory, Planning, and Tool Use. We discuss how these technologies evolve from supporting simple tasks in their early forms to enabling complex autonomous systems and collective intelligence in more advanced forms. Then, we provide an overview of the application of industry agents in real-world domains such as digital engineering, scientific discovery, embodied intelligence, collaborative business execution, and complex system simulation. Additionally, this paper reviews the evaluation benchmarks and methods for both fundamental and specialized capabilities, identifying the challenges existing evaluation systems face regarding authenticity, safety, and industry specificity. Finally, we focus on the practical challenges faced by industry agents, exploring their capability boundaries, developmental potential, and governance issues in various scenarios, while providing insights into future directions. By combining technological evolution with industry practices, this review aims to clarify the current state and offer a clear roadmap and theoretical foundation for understanding and building the next generation of industry agents.

Yongfeng Li, Mingming Zhao, Weijie Chen et al.

In this paper, we consider the linear programming (LP) formulation for deep reinforcement learning. The number of the constraints depends on the size of state and action spaces, which makes the problem intractable in large or continuous environments. The general augmented Lagrangian method suffers the double-sampling obstacle in solving the LP. Namely, the conditional expectations originated from the constraint functions and the quadratic penalties in the augmented Lagrangian function impose difficulties in sampling and evaluation. Motivated from the updates of the multipliers, we overcome the obstacles in minimizing the augmented Lagrangian function by replacing the intractable conditional expectations with the multipliers. Therefore, a deep parameterized augment Lagrangian method is proposed. Furthermore, the replacement provides a promising breakthrough to integrate the two steps in the augmented Lagrangian method into a single constrained problem. A general theoretical analysis shows that the solutions generated from a sequence of the constrained optimizations converge to the optimal solution of the LP if the error is controlled properly. A theoretical analysis on the quadratic penalty algorithm under neural tangent kernel setting shows the residual can be arbitrarily small if the parameter in network and optimization algorithm is chosen suitably. Preliminary experiments illustrate that our method is competitive to other state-of-the-art algorithms.