Mingzhe Xing

Mingzhe Xing, Rongkai Zhang, Hui Xue et al.

Large language models (LLMs) have empowered intelligent agents to execute intricate tasks within domain-specific software such as browsers and games. However, when applied to general-purpose software systems like operating systems, LLM agents face three primary challenges. Firstly, the action space is vast and dynamic, posing difficulties for LLM agents to maintain an up-to-date understanding and deliver accurate responses. Secondly, real-world tasks often require inter-application cooperation}, demanding farsighted planning from LLM agents. Thirdly, agents need to identify optimal solutions aligning with user constraints, such as security concerns and preferences. These challenges motivate AndroidArena, an environment and benchmark designed to evaluate LLM agents on a modern operating system. To address high-cost of manpower, we design a scalable and semi-automated method to construct the benchmark. In the task evaluation, AndroidArena incorporates accurate and adaptive metrics to address the issue of non-unique solutions. Our findings reveal that even state-of-the-art LLM agents struggle in cross-APP scenarios and adhering to specific constraints. Additionally, we identify a lack of four key capabilities, i.e., understanding, reasoning, exploration, and reflection, as primary reasons for the failure of LLM agents. Furthermore, we provide empirical analysis on the failure of reflection, and improve the success rate by 27% with our proposed exploration strategy. This work is the first to present valuable insights in understanding fine-grained weakness of LLM agents, and offers a path forward for future research in this area. Environment, benchmark, and evaluation code for AndroidArena are released at https://github.com/AndroidArenaAgent/AndroidArena.

Jie Ma, Ningyu He, Jinwen Xi et al.

As Ethereum continues to thrive, the Ethereum Virtual Machine (EVM) has become the cornerstone powering tens of millions of active smart contracts. Intuitively, security issues in EVMs could lead to inconsistent behaviors among smart contracts or even denial-of-service of the entire blockchain network. However, to the best of our knowledge, only a limited number of studies focus on the security of EVMs. Moreover, they suffer from 1) insufficient test input diversity and invalid semantics; and 2) the inability to automatically identify bugs and locate root causes. To bridge this gap, we propose OpDiffer, a differential testing framework for EVM, which takes advantage of LLMs and static analysis methods to address the above two limitations. We conducted the largest-scale evaluation, covering nine EVMs and uncovering 26 previously unknown bugs, 22 of which have been confirmed by developers and three have been assigned CNVD IDs. Compared to state-of-the-art baselines, OpDiffer can improve code coverage by at most 71.06%, 148.40% and 655.56%, respectively. Through an analysis of real-world deployed Ethereum contracts, we estimate that 7.21% of the contracts could trigger our identified EVM bugs under certain environmental settings, potentially resulting in severe negative impact on the Ethereum ecosystem.

Jie Ma, Ningyu He, Jinwen Xi et al.

The Ethereum ecosystem, which secures over $381 billion in assets, fundamentally relies on client APIs as the sole interface between users and the blockchain. However, these critical APIs suffer from widespread implementation inconsistencies, which can lead to financial discrepancies, degraded user experiences, and threats to network reliability. Despite this criticality, existing testing approaches remain manual and incomplete: they require extensive domain expertise, struggle to keep pace with Ethereum's rapid evolution, and fail to distinguish genuine bugs from acceptable implementation variations. We present APIDiffer, the first specification-guided differential testing framework designed to automatically detect API inconsistencies across Ethereum's diverse client ecosystem. APIDiffer transforms API specifications into comprehensive test suites through two key innovations: (1) specification-guided test input generation that creates both syntactically valid and invalid requests enriched with real-time blockchain data, and (2) specification-aware false positive filtering that leverages large language models to distinguish genuine bugs from acceptable variations. Our evaluation across all 11 major Ethereum clients reveals the pervasiveness of API bugs in production systems. APIDiffer uncovered 72 bugs, with 90.28% already confirmed or fixed by developers. Beyond these raw numbers, APIDiffer achieves up to 89.67% higher code coverage than existing tools and reduces false positive rates by 37.38%. The Ethereum community's response validates our impact: developers have integrated our test cases, expressed interest in adopting our methodology, and escalated one bug to the official Ethereum Project Management meeting.

Chang Tian, Matthew B. Blaschko, Wenpeng Yin et al.

Fine-grained category discovery using only coarse-grained supervision is a cost-effective yet challenging task. Previous training methods focus on aligning query samples with positive samples and distancing them from negatives. They often neglect intra-category and inter-category semantic similarities of fine-grained categories when navigating sample distributions in the embedding space. Furthermore, some evaluation techniques that rely on pre-collected test samples are inadequate for real-time applications. To address these shortcomings, we introduce a method that successfully detects fine-grained clusters of semantically similar texts guided by a novel objective function. The method uses semantic similarities in a logarithmic space to guide sample distributions in the Euclidean space and to form distinct clusters that represent fine-grained categories. We also propose a centroid inference mechanism to support real-time applications. The efficacy of the method is both theoretically justified and empirically confirmed on three benchmark tasks. The proposed objective function is integrated in multiple contrastive learning based neural models. Its results surpass existing state-of-the-art approaches in terms of Accuracy, Adjusted Rand Index and Normalized Mutual Information of the detected fine-grained categories. Code and data will be available at Code and data are publicly available at https://github.com/changtianluckyforever/F-grained-STAR.

Tiehan Cui, Peipei Liu, Yanxu Mao et al.

While Large Language Models (LLMs) have catalyzed progress in embodied intelligence, a fundamental gap between their inherent probabilistic uncertainty and the strict determinism and verifiable safety required in the physical world. To mitigate this gap, this paper introduces NEXUS, a modular framework designed for continual learning in embodied agents. Different from prior works that treat symbolic artifacts merely as static interfaces, NEXUS leverages them for symbolic grounding and knowledge evolution. The framework explicitly decouples physical feasibility from safety specifications: capability of agents is improved through closed-loop execution feedback, while probabilistic risk assessments are grounded into deterministic hard constraints to establish a rigorous pre-action defense. Experiments on SafeAgentBench demonstrate that NEXUS achieves superior task success rates while effectively refusing unsafe instructions, exhibiting robust defense against adversarial attacks, and progressively improving planning efficiency through knowledge accumulation.

Yanxu Mao, Peipei Liu, Tiehan Cui et al.

With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team methods mostly rely on modifying user prompts, which lack adaptability to new data and may impact the agent's performance. To address the challenge, this paper proposes the JailAgent framework, which completely avoids modifying the user prompt. Specifically, it implicitly manipulates the agent's reasoning trajectory and memory retrieval with three key stages: Trigger Extraction, Reasoning Hijacking, and Constraint Tightening. Through precise trigger identification, real-time adaptive mechanisms, and an optimized objective function, JailAgent demonstrates outstanding performance in cross-model and cross-scenario environments.

Zhifei Yang, Keyang Lu, Chao Zhang et al. · pku

Controllable 3D scene generation has extensive applications in virtual reality and interior design, where the generated scenes should exhibit high levels of realism and controllability in terms of geometry. Scene graphs provide a suitable data representation that facilitates these applications. However, current graph-based methods for scene generation are constrained to text-based inputs and exhibit insufficient adaptability to flexible user inputs, hindering the ability to precisely control object geometry. To address this issue, we propose MMGDreamer, a dual-branch diffusion model for scene generation that incorporates a novel Mixed-Modality Graph, visual enhancement module, and relation predictor. The mixed-modality graph allows object nodes to integrate textual and visual modalities, with optional relationships between nodes. It enhances adaptability to flexible user inputs and enables meticulous control over the geometry of objects in the generated scenes. The visual enhancement module enriches the visual fidelity of text-only nodes by constructing visual representations using text embeddings. Furthermore, our relation predictor leverages node representations to infer absent relationships between nodes, resulting in more coherent scene layouts. Extensive experimental results demonstrate that MMGDreamer exhibits superior control of object geometry, achieving state-of-the-art scene generation performance. Project page: https://yangzhifeio.github.io/project/MMGDreamer.

Chang Tian, Matthew B. Blaschko, Mingzhe Xing et al.

Reinforcement learning (RL) has become a key technique for enhancing the reasoning abilities of large language models (LLMs), with policy-gradient algorithms dominating the post-training stage because of their efficiency and effectiveness. However, most existing benchmarks evaluate large-language-model reasoning under idealized settings, overlooking performance in realistic, non-ideal scenarios. We identify three representative non-ideal scenarios with practical relevance: summary inference, fine-grained noise suppression, and contextual filtering. We introduce a new research direction guided by brain-science findings that human reasoning remains reliable under imperfect inputs. We formally define and evaluate these challenging scenarios. We fine-tune three LLMs and a state-of-the-art large vision-language model (LVLM) using RL with a representative policy-gradient algorithm and then test their performance on eight public datasets. Our results reveal that while RL fine-tuning improves baseline reasoning under idealized settings, performance declines significantly across all three non-ideal scenarios, exposing critical limitations in advanced reasoning capabilities. Although we propose a scenario-specific remediation method, our results suggest current methods leave these reasoning deficits largely unresolved. This work highlights that the reasoning abilities of large models are often overstated and underscores the importance of evaluating models under non-ideal scenarios. The code and data will be released at XXXX.

Chang Tian, Mingzhe Xing, Zenglin Shi et al.

Predicting web service traffic has significant social value, as it can be applied to various practical scenarios, including but not limited to dynamic resource scaling, load balancing, system anomaly detection, service-level agreement compliance, and fraud detection. Web service traffic is characterized by frequent and drastic fluctuations over time and are influenced by heterogeneous web user behaviors, making accurate prediction a challenging task. Previous research has extensively explored statistical approaches, and neural networks to mine features from preceding service traffic time series for prediction. However, these methods have largely overlooked the causal relationships between services. Drawing inspiration from causality in ecological systems, we empirically recognize the causal relationships between web services. To leverage these relationships for improved web service traffic prediction, we propose an effective neural network module, CCMPlus, designed to extract causal relationship features across services. This module can be seamlessly integrated with existing time series models to consistently enhance the performance of web service traffic predictions. We theoretically justify that the causal correlation matrix generated by the CCMPlus module captures causal relationships among services. Empirical results on real-world datasets from Microsoft Azure, Alibaba Group, and Ant Group confirm that our method surpasses state-of-the-art approaches in Mean Squared Error (MSE) and Mean Absolute Error (MAE) for predicting service traffic time series. These findings highlight the efficacy of leveraging causal relationships for improved predictions.

Zhicong Li, Hangyu Mao, Jiangjin Yin et al.

This paper argues that the next generation of AI agent (NGENT) should integrate across-domain abilities to advance toward Artificial General Intelligence (AGI). Although current AI agents are effective in specialized tasks such as robotics, role-playing, and tool-using, they remain confined to narrow domains. We propose that future AI agents should synthesize the strengths of these specialized systems into a unified framework capable of operating across text, vision, robotics, reinforcement learning, emotional intelligence, and beyond. This integration is not only feasible but also essential for achieving the versatility and adaptability that characterize human intelligence. The convergence of technologies across AI domains, coupled with increasing user demand for cross-domain capabilities, suggests that such integration is within reach. Ultimately, the development of these versatile agents is a critical step toward realizing AGI. This paper explores the rationale for this shift, potential pathways for achieving it.

Mingzhe Xing, Chang Tian, Jianan Zhang et al.

Modern large-scale networks introduce significant complexity in understanding network behaviors, increasing the risk of misconfiguration. Prior work proposed to understand network behaviors by mining network configurations, typically relying on domain-specific languages interfaced with formal models. While effective, they suffer from a steep learning curve and limited flexibility. In contrast, natural language (NL) offers a more accessible and interpretable interface, motivating recent research on NL-guided network behavior understanding. Recent advances in large language models (LLMs) further enhance this direction, leveraging their extensive prior knowledge of network concepts and strong reasoning capabilities. However, three key challenges remain: 1) numerous router devices with lengthy configuration files challenge LLM's long-context understanding ability; 2) heterogeneity across devices and protocols impedes scalability; and 3) complex network topologies and protocols demand advanced reasoning abilities beyond the current capabilities of LLMs. To tackle the above challenges, we propose NetMind, a novel framework for querying networks using NL. Our approach introduces a tree-based configuration chunking strategy to preserve semantic coherence while enabling efficient partitioning. We then construct a unified fact graph as an intermediate representation to normalize vendor-specific configurations. Finally, we design a hybrid imperative-declarative language to reduce the reasoning burden on LLMs and enhance precision. We contribute a benchmark consisting of NL question-answer pairs paired with network configurations. Experiments demonstrate that NetMind achieves accurate and scalable network behavior understanding, outperforming existing baselines.