arXiv subjects

Yiping Zuo

Publications and source records attributed to Yiping Zuo.

12 recordsLinked to original sources

arXiv2026

WirelessOpsAgent: A Benchmark and Agent Design for Action Assurance in Wireless Networks

Large language model (LLM) agents are emerging as planners for autonomous wireless network operations. Yet a task answer that is correct at proposal time can still be unsafe at execution time if supporting telemetry is stale or inconsistent. Existing benchmarks mainly evaluate task solving from fixed observations and leave support checking at execution time untested. We introduce WirelessOptBench, a benchmark for action assurance in wireless operations. It turns wireless tasks into execution state decision episodes with controlled telemetry faults and action constraints. We further develop WirelessOpsAgent, which grounds candidate actions in current evidence and repairs recoverable support failures before execution. Across three backbone evaluations with 600 episodes each, WirelessOpsAgent achieves up to 0.983 Exact Action Accuracy. On Claude Sonnet 4.6, the Unsafe APPLY Rate decreases from 82.2% to 10.3% relative to the safest baseline. We make WirelessOptBench available at https://anonymous.4open.science/r/wirelessopsbench-artifact-D969/.

cs.NI↗

arXiv2026

Prior Directions: Why GUI Grounding Gets Locked in the Past

Vision-language models often use descriptions of earlier visual states to make decisions about the current scene. When the scene changes, stale language can redirect an otherwise correct visual judgment toward an outdated answer. We study this failure as visual lock-in in a controlled grounding setting where only the verbalized prior varies. Across models, stronger lock-in accompanies smaller changes in the model representation before the final answer. This reversal suggests that lock-in depends not on how far this representation moves, but on how that movement is organized. In models that are harder to correct, prior-induced changes concentrate along a compact set of directions that repeatedly appear across examples. We call these recurrent axes the Prior Directions. They recur on held-out examples, while a descriptive four-model comparison associates greater concentration with stronger lock-in. Controlled interventions show that removing the component aligned with the Prior Directions restores visual grounding, whereas removing an equally large orthogonal component has little effect. Prior control thus arises when prior-induced changes form a coherent and reusable pattern in the representation used to produce the answer. This account explains why the same prior remains revisable in one model yet becomes dominant in another.

cs.CV↗

arXiv2026

VITAL-RAG: Invariance Race for Context Allocation in Coding Agents

Coding agents often retrieve code from an entire repository, but only limited evidence can fit into the final model input. Conventional retrieval-augmented generation (RAG) for coding agents treats fragments from the same code object as separate results, so redundant views can occupy multiple context positions and crowd out useful code. Grouping fragments by code object reduces this redundancy, but can discard local information needed for the task. We describe this tension as an invariance race: allocation should stay stable under redundant renderings but change when a fragment adds task-relevant semantics. To address this race, we introduce VITAL-RAG, which organizes evidence by canonical code object, keeps one query-relevant companion only when it adds semantics not already represented, and renders selected evidence under per-object and global token budgets. On RepoBench, VITALRAG improves Recall@4K from 39.59% to 63.67% while reducing evidence tokens by 35.63%. Across three model backends, it matches or outperforms recent baselines on RepoClassBench and achieves the highest raw Pass@1 on RepoExec.

cs.SE↗

arXiv2026

Geometric Risk Control for Vision-Language Model OCR

Vision-language models (VLMs) enable flexible generative optical character recognition (OCR), while their open-ended decoders can expose wrong but fluent text with weak visual support. In audit-sensitive records, such an output can be more costly than abstention. Frozen or externally served VLMs therefore require an external decision layer that can determine whether a transcription has sufficient visual evidence for release. We introduce the Geometric Risk Controller (GRC), a model-agnostic controller that treats controlled geometric transformations as repeatable black-box probes, screens structurally implausible continuations, and releases the unique candidate supported by coherent cross-view evidence. The protocol provides empirical selective exposure control with explicit coverage and query cost under a reproducible fixed decision rule. Experiments across frozen VLMs and standard scene-text benchmarks consistently reduce mean, upper-tail, and catastrophic error among released outputs while retaining high coverage.

cs.CV↗

arXiv2026

ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents

Self-generated skills for web agents are often unstable and can even hurt performance relative to direct acting. We argue that the key bottleneck is not only skill generation quality, but the fact that web skills remain implicit and therefore cannot be checked or locally repaired. To address this, we present ContractSkill, a framework that converts a draft skill into an executable artifact with explicit procedural structure, enabling deterministic verifica tion, fault localization, and minimal local repair. This turns skill refinement from full rewriting into localized editing of a single skill artifact. Experiments on VisualWebArena show that Contract Skill is effective in realistic web environments, while MiniWoB provides a controlled test of the mechanism behind the gain. Under matched transfer layers, repaired artifacts also remain reusable after removing the source model from the loop, providing evi dence of portability within the same benchmark family rather than full-benchmark generalization. These results suggest that the central challenge is not merely generating skills, but mak ing them explicit, executable, and repairable. Code is available at https://github.com/underfitting-lu/contractskill.git.

cs.SE↗

arXiv2025

Cylindrical RIS-Assisted Low-Complexity Transmission with Differentiated Visible Regions Exploiting Statistical CSI

Reconfigurable intelligent surfaces (RIS), recognized as a critical enabler for 6G networks, exhibit unprecedented capabilities in electromagnetic wave manipulation and wireless channel reconfiguration. By leveraging existing network infrastructure, RIS can cost-effectively create signal hotspots in low-altitude environments, ensuring robust connectivity to support the sustainable development of the low-altitude economy. However, achieving optimal phase shift design in multi-user scenarios faces two major challenges: the high-dimensional optimization introduced by massive RIS elements, and the persistent coupling of multi-user signals caused by shared RIS reflections. This paper utilize the visible region of an RIS arranged as the uniform cylindrical array (UCA) to reduce the complexity of phase shift design. Under the UCA architecture, RIS elements are categorized into two types: user-specific units and multi-user shared units. We then determine the optimal phase shifts by iteratively optimizing the phase shifts of multi-user shared units while directly configuring those of user-specific units based on a derived closed-form solution. The proposed approach significantly reduces optimization complexity, which is further corroborated by numerical simulation results demonstrating its substantial impact on both system performance and computational efficiency compared to the conventional RIS with uniform planar array.

cs.IT↗

arXiv2025

A Fluid Antenna Enabled Physical Layer Key Generation for Next-G Wireless Networks

As a promising physical layer security technique, physical layer key generation (PLKG) enables legitimate users to obtain secret keys from wireless channel without security infrastructures. However, in harsh propagation environments, the channel characteristic becomes unsatisfactory, the key generation rate (KGR) is significantly deteriorated. In this paper, we propose a novel fluid antenna (FA) enabled PLKG system to address this challenge. Specifically, we first derive the closed-form expression of the KGR for FA array, and then jointly optimize the precoding matrix and the antenna positions via a particle swarm optimization (PSO) algorithm. Next, to further reduce the computational complexity of the optimization procedure, we develop an alternating optimization (AO) algorithm, which combines the projected gradient descent (PGD) and the PSO. Simulation results demonstrate that by exploiting the additional spatial degree of freedom (DoF), our FA enabled PLKG system is superior to the benchmarks, such as the conventional fixed-position antenna (FPA) array and the reconfigurable intelligent surface (RIS). It is worth highlighting that compared to the conventional uniform planar antenna (UPA), the FA enabled PLKG achieves a 35.42\% KGR performance improvement under PSO algorithm and a 67.73\% KGR performance improvement under AO algorithm, respectively.

eess.SP↗

arXiv2024

Fluid Antenna-enabled Integrated Sensing, Communication, and Computing Systems

The current integrated sensing, communication, and computing (ISCC) systems face significant challenges in both efficiency and resource utilization. To tackle these issues, we propose a novel fluid antenna (FA)-enabled ISCC system, specifically designed for vehicular networks. We develop detailed models for the communication and sensing processes to support this architecture. An integrated latency optimization problem is formulated to jointly optimize computing resources, receive combining matrices, and antenna positions. To tackle this complex problem, we decompose it into three sub-problems and analyze each separately. A mixed optimization algorithm is then designed to address the overall problem comprehensively. Numerical results demonstrate the rapid convergence of the proposed algorithm. Compared with baseline schemes, the FA-enabled vehicle ISCC system significantly improves resource utilization and reduces latency for communication, sensing, and computation.

cs.IT↗

arXiv2024

Fluid Antenna for Mobile Edge Computing

In the evolving environment of mobile edge computing (MEC), optimizing system performance to meet the growing demand for low-latency computing services is a top priority. Integrating fluidic antenna (FA) technology into MEC networks provides a new approach to address this challenge. This letter proposes an FA-enabled MEC scheme that aims to minimize the total system delay by leveraging the mobility of FA to enhance channel conditions and improve computational offloading efficiency. By establishing an optimization problem focusing on the joint optimization of computation offloading and antenna positioning, we introduce an alternating iterative algorithm based on the interior point method and particle swarm optimization (IPPSO). Numerical results demonstrate the advantages of our proposed scheme compared to traditional fixed antenna positions, showing significant improvements in transmission rates and reductions in delays. The proposed IPPSO algorithm exhibits robust convergence properties, further validating the effectiveness of our method.

cs.IT↗

arXiv2023

A Survey of Blockchain and Artificial Intelligence for 6G Wireless Communications

The research on the sixth-generation (6G) wireless communications for the development of future mobile communication networks has been officially launched around the world. 6G networks face multifarious challenges, such as resource-constrained mobile devices, difficult wireless resource management, high complexity of heterogeneous network architectures, explosive computing and storage requirements, privacy and security threats. To address these challenges, deploying blockchain and artificial intelligence (AI) in 6G networks may realize new breakthroughs in advancing network performances in terms of security, privacy, efficiency, cost, and more. In this paper, we provide a detailed survey of existing works on the application of blockchain and AI to 6G wireless communications. More specifically, we start with a brief overview of blockchain and AI. Then, we mainly review the recent advances in the fusion of blockchain and AI, and highlight the inevitable trend of deploying both blockchain and AI in wireless communications. Furthermore, we extensively explore integrating blockchain and AI for wireless communication systems, involving secure services and Internet of Things (IoT) smart applications. Particularly, some of the most talked-about key services based on blockchain and AI are introduced, such as spectrum management, computation allocation, content caching, and security and privacy. Moreover, we also focus on some important IoT smart applications supported by blockchain and AI, covering smart healthcare, smart transportation, smart grid, and unmanned aerial vehicles (UAVs). We also analyze the open issues and research challenges for the joint deployment of blockchain and AI in 6G wireless communications. Lastly, based on lots of existing meaningful works, this paper aims to provide a comprehensive survey of blockchain and AI in 6G networks.

cs.IT↗

arXiv2019

Computation Offloading in the Untrusted MEC-aided Mobile Blockchain IoT System

Deploying mobile edge computing (MEC) server in the mobile blockchain-enabled Internet of things (IoT) system is a promising approach to improve the system performance, however, it imposes a significant challenge on the trust of MEC server. To address this problem, we first propose an untrusted MEC proof of work scheme in mobile blockchain network where plenty of nonce hash computing demands can be offloaded to MEC server. Then, we design a nonce ordering algorithm for this scheme to provide fairer computing resource allocation for all mobile IoT devices/users. Specifically, we formulate the user's nonce selection strategy as a non-cooperative game, where the utilities of individual user are maximized in the untrusted MEC-aided mobile blockchain network. We also prove the existence of Nash equilibrium and analyze that the cooperation behavior is unsuitable for the blockchain-enabled IoT devices by using the repeated game. Finally, we design the blockchain's difficulty adjustment mechanism to ensure stable block times during a long period of time.

cs.IT↗

arXiv2017

Outage Performance for Cooperative NOMA Transmission with an AF Relay

This letter studies the outage performance of cooperative non-orthogonal multiple access (NOMA) network with the help of an amplify-and-forward relay. An accurate closed-form approximation for the exact outage probability is derived. Based on this, the asymptotic outage probability is investigated, which shows that cooperative NOMA achieves the same diversity order and the superior coding gain compared to cooperative orthogonal multiple access. It is also revealed that when the transmit power of relay is smaller than that of the base station, the outage performance improves as the distance between the relay and indirect link user decreases.

cs.IT↗