Zirui Zhuang

In the era of large language models, Text-to-SQL, as a natural language interface for databases, is playing an increasingly important role. State-of-the-art Text-to-SQL models have achieved impressive accuracy, but their performance critically relies on expert-written evidence. This evidence typically clarifies schema and value linking that existing models struggle to identify. Such limitations stem from the ambiguity of user queries and, more importantly, the complexity of comprehending large-scale and dynamic database values. Consequently, in real-world scenarios where expert assistance is unavailable, existing methods suffer a severe performance collapse, with execution accuracy dropping by over 10%. This underscores their lack of robustness due to the reliance on expert assistance. To address this, we propose DIVER, a robust system that automates evidence reasoning with dynamic interactive value linking. It leverages a compatible toolbox containing diverse tools to probe the database. Then, restricted by a structured workspace (CoTF, Chain of Thoughts and Facts) , it reflects based on probe results and selects a new tool for next round of probing. Through this automatically iterative process, DIVER identifies schema and value linking missed by existing methods. Based on these accurate linkings, DIVER is able to infer correct usage of SQL functions and formulas and generate high-quality evidence, achieving robust Text-to-SQL without expert assistance. Extensive experiments demonstrate that: 1) The DIVER system significantly enhances the robustness of various Text-to-SQL models, improving performance by up to 10.82% in Execution Accuracy (EX) and 16.09% in Valid Efficiency Score (VES). 2) Our dynamic interactive value linking significantly improves the robustness of existing systems and the accuracy of schema and value linking, especially when confronted with challenges posed by large-scale, dynamic database values.

Network configuration management has become increasingly complex, inefficient, and prone to errors due to frequent updates in command structures and the prevalence of multi-vendor network infrastructures. To tackle these challenges, this paper introduces a novel cognitive communication approach, formulating a new task called intent-driven multi-vendor network configuration generation. Within the broader intent-based networking lifecycle, this task specifically targets the realization and command generation stage—translating natural language operational intents into accurate and syntactically valid network commands compatible with multiple vendors, rather than addressing high-level intent interpretation or decomposition. Three primary challenges are addressed: syntactical command validity, vendor-specific syntax diversity, and outdated or inconsistent network knowledge. We propose ConfGen, a cognitive and intent-driven multi-vendor configuration generation framework that consists of two phases: vendor-agnostic syntax retrieval and syntax-constrained command generation. In the first phase, a cognitive retrieval mechanism and reranking strategy identify the most relevant syntax structures based on user intents, while vendor-specific syntax components are effectively generalized. The second phase employs a Large Language Model (LLM) guided by retrieved syntax constraints and user intents to generate precise and valid network commands. To ensure syntactical correctness and vendor compatibility, syntax-constrained decoding strategies are integrated into the LLM generation process. Extensive experimental evaluations conducted on a novel dataset containing network commands from Huawei, Cisco, Nokia, and Juniper demonstrate the superiority of ConfGen. Results confirm significant performance improvements over state-of-the-art solutions in generating accurate, multi-vendor-compatible network configurations driven by user intent.

Edge slicing is envisioned to support connected autonomous vehicle (CAV) applications with diverse key performance indicator (KPI) requirements by splitting the shared physical infrastructure into several virtual networks. Unfortunately, existing provisioning approaches struggle to accommodate the spatiotemporal dynamics of CAV traffic, leading to significant violated KPIs or soared resource usage. In this paper, we introduce the transient sharing mechanism among edge slices to obtain reused gains without generating harmful performance interference, in which a slice is allowed to access to the under-utilized reserved resources of other slices but may experience interruptions at any time. Considering the heterogeneity and uncertainty of transient resources, we further develop a two-timescale provisioning scheme. Specifically, slices proactively make reservation decisions based on multi-armed bandit architectures at the beginning of large timescales, while hinging on cost-incentive auction mechanisms selectively preempt transient resources in terms of real-time application demands at each small timescale. With extensive experiments based on real traffic traces, we demonstrate that the proposed scheme can improve 10.43% resource utilization and make slices reduce 42.92% cost than state-of-the-art works, which verifies its high assurance and adaptability.

Multi-agent cooperation is an open challenge in intelligent transportation systems (ITS). Traditional rule-based algorithms struggle to adapt to dynamic and uncertain environments, while learning-based algorithms are hindered by the scarcity and cost of labeled data. Reinforcement Learning (RL) offers a promising solution within ITS, as it allows for data acquisition through environmental interaction. However, our investigation has identified two primary issues when deploying RL-based algorithms: (1) The design of the reward function should strike a balance between the cooperative and competitive attributes of the system. Purely cooperative reward designs are challenging to learn due to delayed and sparse feedback, while individualized competitive reward designs may promote selfish behavior and rely heavily on expert knowledge. (2) Learning RL from scratch is also problematic due to the reliance of data generation on policy exploration. Pre-training can provide an initial model to circumvent learning difficulties, but its performance is constrained by the traditional algorithm that supplies the data, necessitating novel solutions to further improve model performance. In this paper, we introduce Hammurabi, a framework designed to enhance cooperation and improve the pre-training model within ITS. Hammurabi employs a social dilemma tool to assess the cooperative properties of the pre-trained policy and incorporates them into specific game models. Based on specific game models, we can leverage existing mature conclusions from game theory to assist in the design of reinforcement learning, thereby enhancing agent cooperation. Theoretical analysis shows that by adopting a multi-agent reinforcement learning scheme with policy shared parameters, Hammurabi can converge multi-agent policies to Nash equilibrium. We illustrate the application of Hammurabi in addressing practical issues within a multi-objective optimization multi-UAV system, demonstrating performance improvements across various optimization objectives compared to baseline algorithms.

Data plane verification (DPV) is critical in ensuring correct network operation, but practical deployment demands solutions that simultaneously achieve real-time responsiveness and massive scalability. Conventional centralized DPV approaches fundamentally struggle with these requirements due to inherent architectural constraints: the single verification server becomes both a computational bottleneck during rapid verification cycles and a collection bottleneck when gathering real-time data plane updates across large-scale networks. As network scale increases, these limitations manifest as either unacceptable verification latency or incomplete data plane visibility—precisely when robust DPV is essential for preventing packet loss and security violations. This paper introduces Atlas*, a novel distributed data plane verification (DPV) system designed to address fundamental scalability and real-time performance challenges in network verification. Atlas* achieves this through a hierarchical architecture that strategically distributes verification tasks across specialized components, combined with innovative parallel processing techniques to maximize computational efficiency. Simultaneously, Atlas* optimizes communication latency between distributed components through a region partitioning algorithm. Extensive evaluations in simulated environments and production deployments demonstrate Atlas*’s capability to perform fast, scalable verification while maintaining lightweight resource allocation. Empirical results show Atlas* achieves 2-7x speedup compared to existing state-of-the-art solutions, with performance advantages progressively increasing as network scale expands.