arXiv subjects

Zihan Fang

Publications and source records attributed to Zihan Fang.

At least 19 recordsLinked to original sources

arXiv2026

GraphAlignCoder: Aligning Program and Proof Graphs for Code Generation

Code large language models (LLMs) can generate syntactically plausible programs that nevertheless violate hidden semantic constraints. Existing execution-feedback training methods identify whether a completed program fails, but provide limited supervision about how a correct solution should be organized. We introduce GraphAlignCoder, a training framework that transfers explicit correctness structure into code generation. GraphAlignCoder constructs an implementation graph that captures control and dependence among program regions. In parallel, a constrained Lean pipeline produces proof traces, from which we extract a formal proof-flow graph. The model first learns executable code together with graph-derived descriptions of why individual program regions are correct, and then consolidates this knowledge into code generation. GraphAlignCoder consistently outperforms the base model, code-only SFT, and CodeRL across all benchmarks. Compared with CodeRL, it increases the solved count from 38 to 50 on LiveCodeBench v6 and from 16 to 23 on BigCodeBench Hard, corresponding to relative gains of 31.6% and 43.8%, while also improving BigCodeBench Full from 359 to 363 tasks. The ablation study further shows that verification-graph injection produces the initial reasoning gain, while verification to code consolidation is essential for robust cross-benchmark transfer.

cs.SE↗

arXiv2026

AgentForge: An Immersive Role-Playing Platform for Learning Agentic Software Engineering

Agentic AI is increasingly used to coordinate planning, implementation, review, and testing in software development, yet it often offers limited transparency into its decisions and interactions. Many such systems also assume that users can effectively guide the AI's decisions and validate its outputs. This assumption poses a particular challenge for novices, who must simultaneously learn how agentic AI works, how to collaborate with it effectively, and how to evaluate its outputs critically. To address this challenge, we present \textit{AgentForge}, an immersive learning system in which novices take on one of four software-engineering roles: Task Planner, Patch Author, Code Reviewer, or Test Runner, within a multi-agent code-repair workflow. In each practice session, the novices perform their chosen role while AI agents perform the remaining three. Through role-based scaffolding and metacognitive support, AgentForge clarifies role-specific responsibilities, makes agent coordination and intermediate artifacts visible, and encourages novices to monitor and evaluate their decisions. In a study with 37 novice developers, participants achieved high task-completion rates with AI-agent support. However, interaction demands differed significantly across practices: the Code Reviewer practice required more interaction turns, reroutes, and completion time ($p_{\mathrm{adj}} = .004$) and was perceived as the most challenging. Participants nevertheless reported significant gains in their understanding of software repair and agent collaboration ($p_{\mathrm{adj}} < .001$). These findings suggest that AgentForge can help novices develop practical software-engineering skills while learning to collaborate with agentic AI more critically and effectively.

cs.SE↗

arXiv2026

SCOPE: Leveraging Subgoal Critiques for Code Generation

Code generation with large language models (LLMs) remains unreliable because generated programs can appear correct while still violating key semantic requirements in the natural language specification. Existing feedback-based methods improve over coder-only generation, but they often rely on unstructured critique or execution signals that do not explicitly identify what the code is semantically missing. We present SCOPE, a prover-initialized subgoal critic for code generation. SCOPE adapts a Lean-oriented prover model to produce three parseable feedback fields for downstream code generation: subgoals, gap analysis, and a robustness checklist. Our approach combines supervised fine-tuning, process-aligned reinforcement learning (RL), and feedback-guided inference, with two complementary rewards during RL: a dense reward for structured critique quality and a sparse reward based on whether the critique improves the coder's execution score. Experiments show that SCOPE improves over the compared feedback baselines. On LiveCodeBench V6, SCOPE achieves 39.4% pass@1, compared with 36.6% for Reflexion and 20.6% for the coder-only baseline. On BigCodeBench (Hard), it reaches 42.6%, surpassing Reflexion at 36.5% and coder-only generation at 34.5%. Further analysis shows that SCOPE's gains are concentrated in tasks with concrete semantic constraints and that its code corrections are more localized than Reflexion's.

cs.SE↗

arXiv2026

From Conversation to Contribution: Characterizing Coding Agent in Open-Source Software

AI coding assistants such as GitHub Copilot and Cursor have evolved from code-suggestion tools into conversational collaborators, enabling vibe-coding workflows in which developers guide AI-generated code through natural-language dialogue. Although researchers have increasingly recognized the importance of AI coding agents and begun examining their impact on open-source development, a comprehensive understanding of how developers' chat-based interactions with AI relate to subsequent open-source development and collaboration remains limited. This hinders efforts to effectively design, evaluate, and govern AI-assisted open-source software development. To address this gap, we collected 13,360 AI conversation sessions comprising 79,172 user messages from 1,356 OSS repositories, linked them to repository development histories, and complemented this analysis with a targeted developer survey. We find heavier AI use in smaller, less mature, and less collaborative repositories. After AI adoption, projects tended to show more active contributors and lower contributor concentration (p < .001), although communication remained highly concentrated. Code Writing was the dominant chat purpose, and nearly all AI chat sessions were followed by subsequent commits. We find no broad deterioration in code-quality signals or pull request merging rates. However, developers perceive others' AI-generated code as harder to maintain than their own (p = .029) and view AI as lowering barriers to OSS contribution. While most developers (68%) are willing to share their chat, concerns remain around appearing incompetent, increasing reviewer burden, and exposing ideas to competitors. These findings provide a large-scale empirical characterization of AI-assisted OSS contribution and offer practical insights for designing and governing responsible vibe-coding practices in open-source development.

cs.SE↗

arXiv2026

Conflict-Aware Federated Fine-Tuning of Large Language Models with Mixture-of-Experts

The continuous scaling of large language models (LLMs) incurs prohibitive computational costs, making Mixture-of-Experts (MoE) a scalable alternative for efficient fine-tuning via sparse activation. While federated learning (FL) emerges as the paradigm for privacy-preserving collaborative optimization, integrating MoE into FL under data heterogeneity may trigger conflicting expert optimizations. Client-specific data distributions force same-indexed experts to optimize under inconsistent or even conflicting feature-label correlations. This mismatch induces destructive interference during aggregation, thus destabilizing the optimization trajectory and degrading model performance. To address this issue, we propose FC-MoE, a federated conflict-aware framework for MoE fine-tuning. It employs an importance aware weighting scheme to prioritize reliable local updates and utilizes gradient consensus projection to suppress conflicting updates, ensuring a stable global optimization path. Moreover, a local knowledge retention mechanism further preserves specialized client expertise by re-anchoring domain-specific residuals. Extensive experiments demonstrate that FC-MoE accelerates convergence and enhances both global and local model performance in non-IID federated environments.

cs.LG↗

arXiv2026

Multi-Agent Embodied Autonomous Driving (MAEAD): From V2X Information Exchange to Shared World Models

Autonomous driving is shifting from isolated vehicle intelligence toward multi-agent embodied systems that share perception, infer intent, and coordinate action under uncertainty. This survey examines this transition through the lens of Shared World Models (SWMs): predictive cross-agent representations maintained across vehicles, infrastructure, and other traffic participants. We review approximately 400 publications covering vehicle-to-everything (V2X) communication, collaborative perception, inter-agent cognition, cooperative planning, end-to-end cooperative driving, and simulation and data engines for closed-loop validation. The organizing question is how exchanged observations become aligned state, intent-aware interaction, and coordinated downstream action. Across the surveyed literature, evaluation remains concentrated in simulation, curated benchmarks, and offline protocols. Foundation-model-based coordination also lacks verifiable real-time safety guarantees in open traffic. These gaps motivate key research priorities for multi-agent embodied autonomous driving (MAEAD): verifiable shared-state maintenance, robust intent and plan alignment, and safe coordinated action under communication and computing constraints in real-world deployment. We maintain an open-source project to continuously track the latest developments at https://github.com/dl-m9/Multi-Agent-Embodied-Autonomous-Driving.

cs.RO↗

arXiv2026

V2VCrafter: Consistent Street-View Image Generation Across Vehicles

Connected and autonomous driving (CAD) systems leverage vehicle-to-vehicle (V2V) communication for multi-agent collaborative perception, yet remain constrained by scarce annotated real-world V2V datasets and limited generalization across diverse driving conditions. While image generation offers a feasible solution for data augmentation, existing single-vehicle multi-view generation frameworks face two key challenges in multi-agent settings: (1) the expanded learning objective degrades generation quality, and (2) dynamic inter-agent variation hinders consistency modeling for physical attributes (e.g., color, category) of jointly observed objects. To bridge this gap, we propose V2VCrafter, the first framework for generating controllable and realistic multi-view driving images across vehicles. For effective learning, we develop a progressive multi-agent diffusion model based on a single-agent backbone, using neighboring agents' latent states to progressively guide single-to-multi-agent generation. To address cross-vehicle inconsistency, we further propose a cross-agent attention module that leverages a collaboration view graph and learnable jointly observed object representations to model dynamic cross-vehicle camera view relationships. Experiments on real-world V2X-Real dataset show that V2VCrafter generates high-fidelity, controllable, and consistent street views across vehicles, thereby effectively enhancing downstream collaborative 3D object detection tasks.

cs.CV↗

arXiv2026

Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents

Large language model (LLM) agents excel at solving complex long-horizon tasks through autonomous interaction with environments. However, their real-world deployment faces a fundamental device--cloud dilemma: on-device models are efficient but often brittle, while cloud models are stronger but costly in computation. State-of-the-art LLM device--cloud routers usually make coarse task-level decisions, which cannot adapt to the changing difficulty of multi-step agent interactions. To address this issue, we present Hera, a step-level device--cloud LLM agent coordinator for long-horizon tasks achieving a strong performance--cost Pareto frontier. Hera adopts a novel two-stage training paradigm: (1) imitation learning for cold-start, followed by (2) reinforcement learning that jointly optimizes task success and cloud usage efficiency. The first stage casts step-level routing as a supervised classification problem: the device agent is replayed on cloud trajectories, with each state labeled by the agreement between device and cloud actions. In the second stage, we perform cost-aware reinforcement learning by grouping identical states across trajectories and updating Hera with labels favoring higher expected return and fewer future cloud calls. We evaluate Hera on ALFWorld, WebShop, and AppWorld, where it consistently outperforms prior methods, achieving 92.5% of the cloud-only success rate with cloud use in only 46.3% of steps.

cs.AI↗

arXiv2026

CA3D: Computing Accessibility-Aware Cooperative 3D Deployment of Multiple UAVs

This letter investigates computing-accessibility-aware cooperative 3D deployment of multiple UAVs for task completion enhancement, termed CA3D. We first provide a theoretical analysis showing that computing accessibility is the key mechanism linking UAV deployment to delay-constrained task completion, and that UAV inter-spacing creates a fundamental tradeoff between computing-resource accessibility and task completion. We then develop a cooperative 3D deployment design that jointly balances accessible computing capacity, task completion probability, and redundant UAV overlap. Simulation results under heterogeneous computing node capacities show that CA3D consistently outperforms Random, Fixed, and Greedy deployment baselines under both hotspot and random ground user (GU) distributions. Under the hotspot GU distribution, CA3D achieves nearly full task completion, improving the task completion probability by about 3.3x over Random deployment when the number of UAVs is 8. Under a more challenging random GU distribution, CA3D still achieves about 35% higher task completion probability than the best baseline when the number of UAVs is 12. These results demonstrate that computing-accessibility-aware cooperative 3D deployment improves not only task completion but also robustness to GU distribution changes.

cs.NI↗

arXiv2026

Collaborative Air-Ground Sensing, Communication, Computing, Storage, and Intelligence for Low-Altitude Economy

Low-altitude economy (LAE) is transforming low-altitude airspace into a new cyber-physical infrastructure. Although air-ground communications have been widely studied, LAE is fundamentally different in the sense that it is mission-centric with diverse requirements, such as stringent safety and compliance constraints not be effectively addressed with a communication-centric design alone, which makes air-ground collaboration indispensable: Only through effectively coordinating air-ground infrastructure and resources can LAE missions be fulfilled. Consequently, LAE calls for task-driven, closed-loop, multi-resource orchestration of Sensing, Communication, Computing, Storage, and Intelligence (SCCSI), where key decisions must be co-designed under mobility and uncertainty. In this paper, we first present a novel framework that connects (i) LAE scenarios and a requirement--resource coupling matrix, (ii) an air--ground collaborative architecture, and (iii) methodological toolboxes for SCCSI co-optimization and online decision-making. We then systematically review enabling technologies for collaborative SCCSI resources and capabilities, emphasizing their coupling and end-to-end tradeoffs. Finally, we summarize testbeds, datasets, and evaluation metrics, and provide representative use cases to illustrate how the proposed framework translates application requirements into practical task-driven optimization designs, together with open challenges and a roadmap toward scalable and trustworthy LAE deployment.

cs.NI↗

arXiv2026

FluxShard: Motion-Aware Feature Cache Reuse for Collaborative Video Analytics in Mobile Edge Computing

Caching and reusing intermediate features across consecutive frames is a common technique to reduce redundant computation and transmission for edge-cloud video analytics in mobile edge computation. Existing methods manage the cache in a fixed or globally shifted coordinate system, treating it as an indivisible whole. Under the non-uniform motion patterns of mobile scenes, this whole-scene granularity invalidates large portions of the cache even when most content has merely shifted spatially, wasting computation and bandwidth. The root cause is a granularity mismatch: the cache is managed per scene, yet motion varies per region. In this paper, we present FluxShard, a motion-aware edge-cloud video analytics system that uses codec-level block motion vectors (MVs) to manage feature cache reuse and recomputation at the granularity of individual motion regions. By re-indexing cached features along per-block MVs, FluxShard separates spatial displacement from content changes, recovering reusable content that whole-scene methods would otherwise discard. To ensure correct reuse under heterogeneous motion, the Receptive Field Alignment Principle (RFAP) identifies, from the input-level MV field alone, the positions that must be recomputed due to inconsistent spatial composition within receptive fields. To maintain cache coherence across frames, MV-guided cache remapping warps the entire feature cache to the current coordinate system each frame, sustaining a high reuse ratio over time. A profiling-driven dispatcher routes the remaining sparse workload between edge and cloud for lower latency. Evaluation across multiple vision tasks, dynamic video benchmarks, and network conditions shows that FluxShard reduces latency by 32.6-83.8% and energy by 14.9-64.0% over all baselines under the prescribed accuracy budget.

cs.NI↗

arXiv2026

Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classification

Adversarial attacks pose a severe threat to the reliability of deep learning models in remote sensing (RS) image classification. Most existing methods rely on direct pixel-wise perturbations, failing to exploit the inherent atmospheric characteristics of RS imagery or survive real-world image degradations. In this paper, we propose FogFool, a physically plausible adversarial framework that generates fog-based perturbations by iteratively optimizing atmospheric patterns based on Perlin noise. By modeling fog formations with natural, irregular structures, FogFool generates adversarial examples that are not only visually consistent with authentic RS scenes but also deceptive. By leveraging the spatial coherence and mid-to-low-frequency nature of atmospheric phenomena, FogFool embeds adversarial information into structural features shared across diverse architectures. Extensive experiments on two benchmark RS datasets demonstrate that FogFool achieves superior performance: not only does it exceed in white-box settings, but also exhibits exceptional black-box transferability (reaching 83.74% TASR) and robustness against common preprocessing-based defenses such as JPEG compression and filtering. Detailed analyses, including confusion matrices and Class Activation Map (CAM) visualizations, reveal that our atmospheric-driven perturbations induce a universal shift in model attention. These results indicate that FogFool represents a practical, stealthy, and highly persistent threat to RS classification systems, providing a robust benchmark for evaluating model reliability in complex environments.

cs.CV↗

arXiv2026

SL-FAC: A Communication-Efficient Split Learning Framework with Frequency-Aware Compression

The growing complexity of neural networks hinders the deployment of distributed machine learning on resource-constrained devices. Split learning (SL) offers a promising solution by partitioning the large model and offloading the primary training workload from edge devices to an edge server. However, the increasing number of participating devices and model complexity leads to significant communication overhead from the transmission of smashed data (e.g., activations and gradients), which constitutes a critical bottleneck for SL. To tackle this challenge, we propose SL-FAC, a communication-efficient SL framework comprising two key components: adaptive frequency decomposition (AFD) and frequency-based quantization compression (FQC). AFD first transforms the smashed data into the frequency domain and decomposes it into spectral components with distinct information. FQC then applies customized quantization bit widths to each component based on its spectral energy distribution. This collaborative approach enables SL-FAC to achieve significant communication reduction while strategically preserving the information most crucial for model convergence. Extensive experiments confirm the superior performance of SL-FAC for improving the training efficiency.

cs.LG↗

arXiv2026

Programming by Chat: A Large-Scale Behavioral Analysis of 11,579 Real-World AI-Assisted IDE Sessions

IDE-integrated AI coding assistants, which operate conversationally within developers' working codebases with access to project context and multi-file editing, are rapidly reshaping software development. However, empirical investigation of this shift remains limited: existing studies largely rely on small-scale, controlled settings or analyze general-purpose chatbots rather than codebase-aware IDE workflows. We present, to the best of our knowledge, the first large-scale study of real-world conversational programming in IDE-native settings, analyzing 74,998 developer messages from 11,579 chat sessions across 1,300 repositories and 899 developers using Cursor and GitHub Copilot. These chats were committed to public repositories as part of routine development, capturing in-the-wild behavior. Our findings reveal three shifts in how programming work is organized: conversational programming operates as progressive specification, with developers iteratively refining outputs rather than specifying complete tasks upfront; developers redistribute cognitive work to AI, delegating diagnosis, comprehension, and validation rather than engaging with code and outputs directly; and developers actively manage the collaboration, externalizing plans into persistent artifacts, and negotiating AI autonomy through context injection and behavioral constraints. These results provide foundational empirical insights into AI-assisted development and offer implications for the design of future programming environments.

cs.SE↗

arXiv2026

Aggregation Alignment for Federated Learning with Mixture-of-Experts under Data Heterogeneity

Large language models (LLMs) increasingly adopt Mixture-of-Experts (MoE) architectures to scale model capacity while reducing computation. Fine-tuning these MoE-based LLMs often requires access to distributed and privacy-sensitive data, making centralized fine-tuning impractical. Federated learning (FL) therefore provides a paradigm to collaboratively fine-tune MoE-based LLMs, enabling each client to integrate diverse knowledge without compromising data privacy. However, the integration of MoE-based LLM fine-tuning into FL encounters two critical aggregation challenges due to inherent data heterogeneity across clients: (i) divergent local data distributions drive clients to develop distinct gating preference for localized expert selection, causing direct parameter aggregation to produce a ``one-size-fits-none'' global gating network, and (ii) same-indexed experts develop disparate semantic roles across clients, leading to expert semantic blurring and the degradation of expert specialization. To address these challenges, we propose FedAlign-MoE, a federated aggregation alignment framework that jointly enforces routing consistency and expert semantic alignment. Specifically, FedAlign-MoE aggregates gating behaviors by aligning routing distributions through consistency weighting and optimizes local gating networks through distribution regularization, maintaining cross-client stability without overriding discriminative local preferences. Meanwhile, FedAlign-MoE explicitly quantifies semantic consistency among same-indexed experts across clients and selectively aggregates updates from semantically aligned clients, ensuring stable and specialized functional roles for global experts. Extensive experiments demonstrate that FedAlign-MoE outperforms state-of-the-art benchmarks, achieving faster convergence and superior accuracy in non-IID federated environments.

cs.LG↗

arXiv2026

GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems

The increasing complexity of neural networks poses significant challenges for democratizing federated learning (FL) on resource-constrained edge devices. Parallel split learning (PSL) has emerged as a promising solution by offloading substantial computing workload to a server via model partitioning, shrinking client-side computing load, and eliminating the client-side model aggregation for reduced communication and deployment costs. However, the highly heterogeneous nature of client data in edge computing systems causes aggregation-free PSL to suffer from severe training divergence, stemming from gradient directional inconsistency across clients. To address this challenge, we propose GAPSL, a gradient-aligned PSL framework tailored for data-heterogeneous edge systems, which comprises two key components: leader gradient identification (LGI) and gradient direction alignment (GDA). LGI dynamically selects a set of directionally consistent device gradients to construct a leader gradient as a robust proxy for the global convergence trend. GDA employs a direction-aware regularization to align each client's gradient with the leader gradient, thereby mitigating inter-device gradient directional inconsistency and enhancing model convergence. We evaluate GAPSL on a prototype computing testbed. Extensive experiments demonstrate that GAPSL consistently outperforms state-of-the-art benchmarks in training accuracy, convergence latency, and system robustness under severe data heterogeneity.

cs.LG↗

arXiv2026

Exploiting Adaptive Channel Pruning for Communication-Efficient Split Learning

Split learning (SL) transfers most of the training workload to the server, which alleviates computational burden on client devices. However, the transmission of intermediate feature representations, referred to as smashed data, incurs significant communication overhead, particularly when a large number of client devices are involved. To address this challenge, we propose an adaptive channel pruning-aided SL (ACP-SL) scheme. In ACP-SL, a label-aware channel importance scoring (LCIS) module is designed to generate channel importance scores, distinguishing important channels from less important ones. Based on these scores, an adaptive channel pruning (ACP) module is developed to prune less important channels, thereby compressing the corresponding smashed data and reducing the communication overhead. Experimental results show that ACP-SL consistently outperforms benchmark schemes in test accuracy. Furthermore, it reaches a target test accuracy in fewer training rounds, thereby reducing communication overhead.

cs.LG↗

arXiv2026

Transformer-Based Multipath Congestion Control: A Decoupled Approach for Wireless Uplinks

The proliferation of artificial intelligence applications on edge devices necessitates efficient transport protocols that leverage multi-homed connectivity across heterogeneous networks. While Multipath TCP enables bandwidth aggregation, its in-kernel congestion control mechanisms lack the programmability and flexibility needed for achieving efficient transmission. Additionally, inherent measurement noise renders network state partially observable, challenging data-driven approaches like deep reinforcement learning (DRL). To address these challenges, we propose a Transformer-based Congestion Control Optimization (TCCO) framework for multipath transport. TCCO employs a decoupled architecture that offloads control decisions to an external decision engine via a lightweight in-kernel client and user-space proxy, enabling edge devices to leverage external computational resources while maintaining TCP/IP compatibility. The Transformer-based DRL agent in the external decision engine uses self-attention to capture temporal dependencies, filter noise, and coordinate control across subflows through a unified policy. Extensive evaluation on both simulated and real dual-band Wi-Fi testbeds demonstrates that TCCO achieves superior adaptability and performance than state-of-the-art baselines, validating the feasibility and effectiveness of TCCO for wireless networks.

cs.NI↗