arXiv subjects

Weihao Zhang

Publications and source records attributed to Weihao Zhang.

11 recordsLinked to original sources

arXiv2026

Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verification

Knowledge Graphs (KGs) serve as a critical foundation for AI systems, yet their automated construction inevitably introduces noise, compromising data trustworthiness. Existing triple verification methods, based on graph embeddings or language models, often suffer from single-source bias by relying on either internal structural constraints or external semantic evidence, and usually follow a static inference paradigm. As a result, they struggle with complex or long-tail facts and provide limited interpretability. To address these limitations, we propose SHARP (Schema-Hybrid Agent for Reliable Prediction), a training-free autonomous agent that reformulates triple verification as a dynamic process of strategic planning, active investigation, and evidential reasoning. Specifically, SHARP combines a Memory-Augmented Mechanism with Schema-Aware Strategic Planning to improve reasoning stability, and employs an enhanced ReAct loop with a Hybrid Knowledge Toolset to dynamically integrate internal KG structure and external textual evidence for cross-verification. Experiments on FB15K-237 and Wikidata5M-Ind show that SHARP significantly outperforms existing state-of-the-art baselines, achieving accuracy gains of 4.2% and 12.9%, respectively. Moreover, SHARP provides transparent, fact-based evidence chains for each judgment, demonstrating strong interpretability and robustness for complex verification tasks.

cs.AI↗

arXiv2026

Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling

Mixture-of-Experts is a promising approach for edge AI with low-batch inference. Yet, on-device deployments often face limited on-chip memory and severe workload imbalance; the prevalent use of offloading further incurs off-chip memory access bottlenecks. Moreover, MoE sparsity and dynamic gating shift distributed strategies toward much finer granularity and introduce runtime scheduling considerations. Recently, high die-to-die bandwidth chiplet interconnects have created new opportunities for multi-chiplet systems to address workload imbalance and offloading bottlenecks with fine-grained scheduling. In this paper, we propose Fully Sharded Expert Data Parallelism, a parallelization paradigm specifically architected for low-batch MoE inference on multi-chiplet accelerators. FSE-DP attains adaptive computation-communication overlap and balanced load by orchestrating fine-grained, complementary expert streams along dynamic trajectories across high-bandwidth D2D links. The attendant dataflow complexity is tamed by a minimal, hardware-amenable set of virtualization rules and a lightweight scheduling algorithm. Our approach achieves 1.22 to 2.00 times speedup over state-of-the-art baselines and saves up to 78.8 percent on-chip memory.

cs.AR↗

arXiv2026

Loosely-Structured Software: Engineering Context, Structure, and Evolution Entropy in Runtime-Rewired Multi-Agent Systems

As LLM-based multi-agent systems (MAS) become more autonomous, their free-form interactions increasingly dominate system behavior. However, scaling the number of agents often amplifies context pressure, coordination errors, and system drift. It is well known that building robust MAS requires more than prompt tuning or increased model intelligence. It necessitates engineering discipline focused on architecture to manage complexity under uncertainty. We characterize agentic software by a core property: \emph{runtime generation and evolution under uncertainty}. Drawing upon and extending software engineering experience, especially object-oriented programming, this paper introduces \emph{Loosely-Structured Software (LSS)}, a new class of software systems that shifts the engineering focus from constructing deterministic logic to managing the runtime entropy generated by View-constructed programming, semantic-driven self-organization, and endogenous evolution. To make this entropy governable, we introduce design principles under a three-layer engineering framework: \emph{View/Context Engineering} to manage the execution environment and maintain task-relevant Views, \emph{Structure Engineering} to organize dynamic binding over artifacts and agents, and \emph{Evolution Engineering} to govern the lifecycle of self-rewriting artifacts. Building on this framework, we develop LSS design patterns as semantic control blocks that stabilize fluid, inference-mediated interactions while preserving agent adaptability. Together, these abstractions improve the \emph{designability}, \emph{scalability}, and \emph{evolvability} of agentic infrastructure. We provide basic experimental validation of key mechanisms, demonstrating the effectiveness of LSS.

cs.SE↗

arXiv2025

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression

Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead. We introduce a unified framework based on dynamic expert clustering and structured compression to address these issues cohesively. Our method employs an online clustering procedure that periodically regroups experts using a fused metric of parameter and activation similarity, which stabilizes expert utilization. To our knowledge, this is one of the first frameworks to leverage the semantic embedding capability of the router to dynamically reconfigure the model's architecture during training for substantial efficiency gains. Within each cluster, we decompose expert weights into a shared base matrix and extremely low-rank residual adapters, achieving up to fivefold parameter reduction per group while preserving specialization. This structure enables a two-stage hierarchical routing strategy: tokens are first assigned to a cluster, then to specific experts within it, drastically reducing the routing search space and the volume of all-to-all communication. Furthermore, a heterogeneous precision scheme, which stores shared bases in FP16 and residual factors in INT4, coupled with dynamic offloading of inactive clusters, reduces peak memory consumption to levels comparable to dense models. Evaluated on GLUE and WikiText-103, our framework matches the quality of standard MoE models while reducing total parameters by approximately 80%, improving throughput by 10% to 20%, and lowering expert load variance by a factor of over three. Our work demonstrates that structural reorganization is a principled path toward scalable, efficient, and memory-effective MoE LLMs. Code is available at https://github.com/szdtzpj/Breaking_the_moe_trilemma

cs.CL↗

arXiv2025

CompAir: Synergizing Complementary PIMs and In-Transit NoC Computation for Efficient LLM Acceleration

The rapid advancement of Large Language Models (LLMs) has revolutionized various aspects of human life, yet their immense computational and energy demands pose significant challenges for efficient inference. The memory wall, the growing processor-memory speed disparity, remains a critical bottleneck for LLM. Process-In-Memory (PIM) architectures overcome limitations by co-locating compute units with memory, leveraging 5-20$\times$ higher internal bandwidth and enabling greater energy efficiency than GPUs. However, existing PIMs struggle to balance flexibility, performance, and cost-efficiency for LLMs' dynamic memory-compute patterns and operator diversity. DRAM-PIM suffers from inter-bank communication overhead despite its vector parallelism. SRAM-PIM offers sub-10ns latency for matrix operation but is constrained by limited capacity. This work introduces CompAir, a novel PIM architecture that integrates DRAM-PIM and SRAM-PIM with hybrid bonding, enabling efficient linear computations while unlocking multi-granularity data pathways. We further develop CompAir-NoC, an advanced network-on-chip with an embedded arithmetic logic unit that performs non-linear operations during data movement, simultaneously reducing communication overhead and area cost. Finally, we develop a hierarchical Instruction Set Architecture that ensures both flexibility and programmability of the hybrid PIM. Experimental results demonstrate that CompAir achieves 1.83-7.98$\times$ prefill and 1.95-6.28$\times$ decode improvement over the current state-of-the-art fully PIM architecture. Compared to the hybrid A100 and HBM-PIM system, CompAir achieves 3.52$\times$ energy consumption reduction with comparable throughput. This work represents the first systematic exploration of hybrid DRAM-PIM and SRAM-PIM architectures with in-network computation capabilities, offering a high-efficiency solution for LLM.

cs.AR↗

arXiv2025

Vanishing Angular Viscosity Limit For Micropolar Fluid Model In $\mathbb{R}_+^2$: Boundary Layer And Optimal Convergence Rate

We consider the initial-boundary value problem for the incompressible two-dimensional micropolar fluid model with angular viscosity in the upper half-plane. This model describes the motion of viscous fluids with microstructure. The global well-posedness of strong solutions for this problem with positive angular viscosity can be established via the standard energy method, as presented in the classical monograph [Łkaszewicz, {\it Micropolar fluids: Theory and applications.} Birkhäuser, 1999]. Corresponding results for the zero angular viscosity case were established recently in [Liu, Wang, {\it Commun. Math. Sci.} 16 (2018), no. 8, 2147-2165]. However, the link between the positive angular viscosity model (the full diffusive system) and the zero angular viscosity model (the partially diffusive system) via the vanishing diffusion limit remains unknown. In this work, we first construct Prandtl-type boundary layer profiles. We then provide a rigorous justification for the vanishing angular viscosity limit of global strong solutions, without imposing smallness assumptions on the initial data. Our analysis reveals the emergence of a strong boundary layer in the angular velocity field (micro-rotation velocity of the fluid particles) during this vanishing viscosity process. Moreover, we also obtain the optimal $L^\infty$ convergence rate as the angular viscosity tends to zero. Our approach combines anisotropic Sobolev spaces with careful energy estimates to address the nonlinear interaction between the velocity and angular velocity fields.

math.AP↗

arXiv2025

MLDSE: Scaling Design Space Exploration Infrastructure for Multi-Level Hardware

To efficiently support large-scale NNs, multi-level hardware, leveraging advanced integration and interconnection technologies, has emerged as a promising solution to counter the slowdown of Moore's law. However, the vast design space of such hardware, coupled with the complexity of their spatial hierarchies and organizations, introduces significant challenges for design space exploration (DSE). Existing DSE tools, which rely on predefined hardware templates to explore parameters for specific architectures, fall short in exploring diverse organizations, spatial hierarchies, and architectural polymorphisms inherent in multi-level hardware. To address these limitations, we present Multi-Level Design Space Exploror (MLDSE), a novel infrastructure for domain-specific DSE of multi-level hardware. MLDSE introduces three key innovations from three basic perspectives of DSE: 1) Modeling: MLDSE introduces a hardware intermediate representation (IR) that can recursively model diverse multi-level hardware with composable elements at various granularities. 2) Mapping: MLDSE provides a comprehensive spatiotemporal mapping IR and mapping primitives, facilitating the mapping strategy exploration on multi-level hardware, especially synchronization and cross-level communication; 3) Simulation: MLDSE supports universal simulator generation based on task-level event-driven simulation mechanism. It features a hardware-consistent scheduling algorithm that can handle general task-level resource contention. Through experiments on LLM workloads, we demonstrate MLDSE's unique capability to perform three-tier DSE spanning architecture, hardware parameter, and mapping.

cs.AR↗

arXiv2024

General-purpose Dataflow Model with Neuromorphic Primitives

Neuromorphic computing exhibits great potential to provide high-performance benefits in various applications beyond neural networks. However, a general-purpose program execution model that aligns with the features of neuromorphic computing is required to bridge the gap between program versatility and neuromorphic hardware efficiency. The dataflow model offers a potential solution, but it faces high graph complexity and incompatibility with neuromorphic hardware when dealing with control flow programs, which decreases the programmability and performance. Here, we present a dataflow model tailored for neuromorphic hardware, called neuromorphic dataflow, which provides a compact, concise, and neuromorphic-compatible program representation for control logic. The neuromorphic dataflow introduces "when" and "where" primitives, which restructure the view of control. The neuromorphic dataflow embeds these primitives in the dataflow schema with the plasticity inherited from the spiking algorithms. Our method enables the deployment of general-purpose programs on neuromorphic hardware with both programmability and plasticity, while fully utilizing the hardware's potential.

cs.CL↗

arXiv2024

Solution-oriented Agent-based Models Generation with Verifier-assisted Iterative In-context Learning

Agent-based models (ABMs) stand as an essential paradigm for proposing and validating hypothetical solutions or policies aimed at addressing challenges posed by complex systems and achieving various objectives. This process demands labor-intensive endeavors and multidisciplinary expertise. Large language models (LLMs) encapsulating cross-domain knowledge and programming proficiency could potentially alleviate the difficulty of this process. However, LLMs excel in handling sequential information, making it challenging for analyzing the intricate interactions and nonlinear dynamics inherent in ABMs. Additionally, due to the lack of self-evaluation capability of LLMs, relying solely on LLMs is insufficient to effectively accomplish this process. In this paper, we present SAGE, a general solution-oriented ABM generation framework designed for automatic modeling and generating solutions for targeted problems. Unlike approaches reliant on expert handcrafting or resource-intensive neural network training, SAGE establishes a verifier-assisted iterative in-context learning process employing large language models (LLMs) to leverages their inherent cross-domain knowledge for tackling intricate demands from diverse domain scenarios. In SAGE, we introduce an semi-structured conceptual representation expliciting the intricate structures of ABMs and an objective representation to guide LLMs in modeling scenarios and proposing hypothetical solutions through in-context learning. To ensure the model executability and solution feasibility, SAGE devises a two-level verifier with chain-of-thought prompting tailored to the complex interactions and non-linear dynamics of ABMs, driving the iterative generation optimization. Moreover, we construct an evaluation dataset of solution-oriented ABMs from open sources.It contains practical models across various domains.

cs.CL↗

arXiv2024

General Automatic Solution Generation of Social Problems

Given the escalating intricacy and multifaceted nature of contemporary social systems, manually generating solutions to address pertinent social issues has become a formidable task. In response to this challenge, the rapid development of artificial intelligence has spurred the exploration of computational methodologies aimed at automatically generating solutions. However, current methods for auto-generation of solutions mainly concentrate on local social regulations that pertain to specific scenarios. Here, we report an automatic social operating system (ASOS) designed for general social solution generation, which is built upon agent-based models, enabling both global and local analyses and regulations of social problems across spatial and temporal dimensions. ASOS adopts a hypergraph with extensible social semantics for a comprehensive and structured representation of social dynamics. It also incorporates a generalized protocol for standardized hypergraph operations and a symbolic hybrid framework that delivers interpretable solutions, yielding a balance between regulatory efficacy and function viability. To demonstrate the effectiveness of ASOS, we apply it to the domain of averting extreme events within international oil futures markets. By generating a new trading role supplemented by new mechanisms, ASOS can adeptly discern precarious market conditions and make front-running interventions for non-profit purposes. This study demonstrates that ASOS provides an efficient and systematic approach for generating solutions for enhancing our society.

cs.CY↗

arXiv2021

A Lightweight Approach of Human-Like Playtesting

A playtest is the process in which human testers are recruited to play video games and to reveal software bugs. Manual testing is expensive and time-consuming, especially when there are many mobile games to test and every software version requires for extensive testing before being released. Existing testing frameworks (e.g., Android Monkey) are limited because they adopt no domain knowledge to play games. Learning-based tools (e.g., Wuji) involve a huge amount of training data and computation before testing any game. This paper presents LIT -- our lightweight approach to generalize playtesting tactics from manual testing, and to adopt the generalized tactics to automate game testing. LIT consists of two phases. In Phase I, while a human plays an Android game app G for a short period of time (e.g., eight minutes), \tool records the user's actions (e.g., swipe) and the scene before each action. Based on the collected data, LIT generalizes a set of \emph{context-aware, abstract playtesting tactics} which describe under what circumstances, what actions can be taken to play the game. In Phase II, LIT tests G based on the generalized tactics. Namely, given a randomly generated game scene, LIT searches match for the abstract context of any inferred tactic; if there is a match, LIT customizes the tactic and generates a feasible event to play the game. Our evaluation with nine games shows LIT to outperform two state-of-the-art tools. This implies that by automating playtest, LIT will significantly reduce manual testing and boost the quality of game apps.

cs.SE↗