The deployment of agent systems in an enterprise environment is often hindered by several challenges: common models lack domain-specific process knowledge, leading to disorganized plans, missing key tools, and poor execution stability. To address this, this paper introduces Routine, a multi-step agent planning framework designed with a clear structure, explicit instructions, and seamless parameter passing to guide the agent's execution module in performing multi-step tool-calling tasks with high stability. In evaluations conducted within a real-world enterprise scenario, Routine significantly increases the execution accuracy in model tool calls, increasing the performance of GPT-4o from 41.1% to 96.3%, and Qwen3-14B from 32.6% to 83.3%. We further constructed a Routine-following training dataset and fine-tuned Qwen3-14B, resulting in an accuracy increase to 88.2% on scenario-specific evaluations, indicating improved adherence to execution plans. In addition, we employed Routine-based distillation to create a scenario-specific, multi-step tool-calling dataset. Fine-tuning on this distilled dataset raised the model's accuracy to 95.5%, approaching GPT-4o's performance. These results highlight Routine's effectiveness in distilling domain-specific tool-usage patterns and enhancing model adaptability to new scenarios. Our experimental results demonstrate that Routine provides a practical and accessible approach to building stable agent workflows, accelerating the deployment and adoption of agent systems in enterprise environments, and advancing the technical vision of AI for Process.

Artificial Intelligence (AI) is accelerating the transformation of scientific research paradigms, not only enhancing research efficiency but also driving innovation. We introduce InternAgent, a unified closed-loop multi-agent framework to conduct Autonomous Scientific Research (ASR) across various scientific research fields, enabling researchers to tackle complicated problems in these fields with unprecedented speed and precision. InternAgent highlights three key advantages: 1) Scalability: InternAgent has demonstrated its versatility across 12 scientific research tasks, capable of generating innovative ideas to enhance the performance of baseline code. 2) Interactivity: InternAgent provides an interface for human expert feedback and multi-agent interaction in automated end-to-end processes, allowing for the seamless integration of domain expert knowledge. 3) Efficiency: InternAgent has achieved promising performance gains in several scientific fields with significantly less time cost compared to human efforts. For instance, in reaction yield prediction, it increased from 27.6% to 35.4% in just 12 hours; in enhancer activity prediction, accuracy rose from 0.65 to 0.79 with only 4 hours of processing; and in 2D semantic segmentation, precision advanced from 78.8% to 81.0% in a mere 30 hours.

We have developed Aitomia - a platform powered by AI to assist in performing AI-driven atomistic and quantum chemical (QC) simulations. This evolving intelligent assistant platform is equipped with chatbots and AI agents to help experts and guide non-experts in setting up and running atomistic simulations, monitoring their computational status, analyzing simulation results, and summarizing them for the user in both textual and graphical forms. We achieve these goals by exploiting large language models that leverage the versatility of our MLatom ecosystem, supporting AI-enhanced computational chemistry tasks ranging from ground-state to excited-state calculations, including geometry optimizations, thermochemistry, and spectral calculations. The multi-agent implementation enables autonomous executions of the complex computational workflows, such as the computation of the reaction enthalpies. Aitomia is the first intelligent assistant publicly accessible online on a cloud computing platform for atomistic simulations of broad scope (Aitomistic Hub at https://aitomistic.xyz). It may also be deployed locally as described at http://mlatom.com/aitomia. Aitomia is expected to lower the barrier to performing atomistic simulations, thereby democratizing simulations and accelerating research and development in relevant fields.

Performance is achieved by modeling natural language as reasoning trees measured by both length and depth instead of linear sequences. The reasoning trees consist of tasks with thoughts, recursive sub-tasks, and conclusions based on the concept we proposed in (Schroeder et al., 2025). During generation, we maintain a working memory that retains only the key/value states of the most relevant context tokens, selected by a rule-based subtask-pruning mechanism, enabling reuse of positional embeddings and GPU memory pages throughout reasoning. Experimental results show that our system sustains high inference throughput, even when manipulating up to 90% of the KV cache in GPU memory. It also delivers accurate reasoning on mathematical tasks and handles information retrieval challenges that require long-horizon reasoning and multi-hop tool use. Large language models (LLMs) have emerged as versatile foundations for a wide range of AI applications, especially agents which handle complicated tasks including multi-hop reasoning and tool use. Their ability to generalize across various tasks with minimal fine-tuning has driven rapid innovation and broad adoption (Brown et al., 2020). However, the fundamental objective of language modeling, to generate unstructured token sequences (Bengio et al., 2003), imposes strict context window limits and makes fine-grained control over internal state difficult. As a result, these inherent constraints pose significant challenges for all state-of-the-art LLMs, notably their inability to maintain long-horizon reasoning trajectories and coordinate complex workflows, which hinders the development of robust, memory-intensive applications. Neural networks generate natural language as a linear sequence. Recurrent neural networks (RNNs) (Mikolov et al., 2010; Luong et al., 2015; Gu & Dao, 2023) and Transformers (V aswani et al., 2017; Y ang et al., 2023) are constrained by token limits, hidden state sizes, and GPU-memory capacities.

The objective of this work is to establish an upper bound for the almost sure convergence rate for a class of push-sum algorithms. The current work extends the methods and results of the authors on a similar low-complexity bound on push-sum algorithms with some particular synchronous message passing schemes and complements the general approach of Gerencsér and Gerencsér from 2022 providing an exact, but often less accessible description. Furthermore, a parametric analysis is presented on the ``weight'' of the messages, which is found to be convex with an explicit expression for the gradient. This allows the fine-tuning of the algorithm used for improved efficiency. Numerical results confirm the speedup in evaluating the computable bounds without deteriorating their performance, for a graph on 120 vertices the runtime drops by more than 4 orders of magnitude.

Computer-Aided Engineering (CAE) enables simulation experts to optimize complex models, but faces challenges in user experience (UX) that limit efficiency and accessibility. While artificial intelligence (AI) has demonstrated potential to enhance CAE processes, research integrating these fields with a focus on UX remains fragmented. This paper presents a multivocal literature review (MLR) examining how AI enhances UX in CAE software across both academic research and industry implementations. Our analysis reveals significant gaps between academic explorations and industry applications, with companies actively implementing LLMs, adaptive UIs, and recommender systems while academic research focuses primarily on technical capabilities without UX validation. Key findings demonstrate opportunities in AI-powered guidance, adaptive interfaces, and workflow automation that remain underexplored in current research. By mapping the intersection of these domains, this study provides a foundation for future work to address the identified research gaps and advance the integration of AI to improve CAE user experience.

Verification using SystemVerilog assertions (SVA) is one of the most popular methods for detecting circuit design vulnerabilities. However, with the globalization of integrated circuit design and the continuous upgrading of security requirements, the SVA development model has exposed major limitations. It is not only inefficient in development, but also unable to effectively deal with the increasing number of security vulnerabilities in modern complex integrated circuits. In response to these challenges, this paper proposes an innovative SVA automatic generation framework SVAgent. SVAgent introduces a requirement decomposition mechanism to transform the original complex requirements into a structured, gradually solvable fine-grained problem-solving chain. Experiments have shown that SVAgent can effectively suppress the influence of hallucinations and random answers, and the key evaluation indicators such as the accuracy and consistency of the SVA are significantly better than existing frameworks. More importantly, we successfully integrated SVAgent into the most mainstream integrated circuit vulnerability assessment framework and verified its practicality and reliability in a real engineering design environment.

Large language models have paved the way to powerful and flexible AI agents, assisting humans by increasingly integrating into their daily life. This flexibility, potential, and growing adoption demands a holistic and cross-disciplinary approach to developing, monitoring and discussing the capabilities required for agent-driven user experiences. However, current guidance on human-centered AI agent development is scattered: UX heuristics focus on interface behaviors, engineering taxonomies describe internal pipelines, and ethics checklists address high-level governance. There is no concise, user-facing vocabulary that tells teams what an agent should fundamentally be able to do. We introduce ADEPTS, a capability framework defining a set of core user-facing capabilities to provide unified guidance around the development of AI agents. ADEPTS is based on six principles for human-centered agent design, that express the minimal, user-facing capabilities an AI agent should demonstrate to be understandable, controllable and trustworthy in everyday use. ADEPTS complements existing frameworks and taxonomies; differently from them, it sits at the interface between technical and experience development. By presenting ADEPTS, we aim to condense complex AI-UX requirements into a compact framework that is actionable guidance for AI researchers, designers, engineers, and policy reviewers alike. We believe ADEPTS has the potential of accelerating the improvement of user-relevant agent capabilities, of easing the design of experiences that take advantage of those capabilities, and of providing a shared language to track and discuss progress around the development of AI agents.

While embodied AI is commonly understood as general-purpose intelligence that empowers various forms of robotics,9 we believe that its scope extends significantly beyond robotic platforms alone. Embodied AI, as we define it, refers to intelligent systems capable of learning from and actively interacting with their environments, continuously adapting based on real-time sensor feedback and context-driven decision-making. Specifically, we define Environmental Embodied AI as an intelligent virtual agent capable of real-time perception, learning, and interaction with its surrounding environment through sensor inputs, enabling it to actuate environmental elements, e.g. Distinct from traditional embodied AI systems primarily associated with robotic platforms, Environmental Embodied AI specifically emphasizes non-robotic applications, employing virtual agents to directly influence physical or operational states within environments. These intelligent systems autonomously analyze environmental data, dynamically adapting behaviors to optimize outcomes and significantly reduce ecological footprints, inherently supporting environmentally sustainable practices.

--Intelligent fault diagnosis (IFD) plays a crucial role in ensuring the safe operation of industrial machinery and improving production efficiency. However, traditional supervised deep learning methods require a large amount of training data and labels, which are often located in different clients. Additionally, the cost of data labeling is high, making labels difficult to acquire. Meanwhile, differences in data distribution among clients may also hinder the model's performance. T o tackle these challenges, this paper proposes a semi-supervised federated learning framework, SSFL-DCSL, which integrates dual contrastive loss and soft labeling to address data and label scarcity for distributed clients with few labeled samples while safeguarding user privacy. It enables representation learning using unlabeled data on the client side and facilitates joint learning among clients through prototypes, thereby achieving mutual knowledge sharing and preventing local model divergence. Specifically, first, a sample weighting function based on the Laplace distribution is designed to alleviate bias caused by low confidence in pseudo labels during the semi-supervised training process. Second, a dual contrastive loss is introduced to mitigate model divergence caused by different data distributions, comprising local contrastive loss and global contrastive loss. Third, local prototypes are aggregated on the server with weighted averaging and updated with momentum to share knowledge among clients. T o evaluate the proposed SSFL-DCSL framework, experiments are conducted on two publicly available datasets and a dataset collected on motors from the factory. In the most challenging task, where only 10% of the data are labeled, the proposed SSFL-DCSL can improve accuracy by 1.15% to 7.85% over state-of-the-art methods. Dai and Z. Mei are with the School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China (e-mail: { yajiao.dai, J. Li and S. Jin are with the School of Information Science and Engineering, Southeast University, Nanjing, 210096, China (e-mail: jun.li, jinshi@seu.edu.cn).