arXiv subjects

Qian Zhang

Publications and source records attributed to Qian Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2026

Space-division multiplexed quantum key distribution exploiting multi-plane light conversion for few-mode fibers

As quantum key distribution (QKD) progresses from laboratory demonstrations toward practical deployment, quantum communi- cation networks increasingly require higher key rates and the ability to distribute independent secret keys among multiple users and network nodes. In this paper we present a promsing approach with multi-plane light conversion (MPLC) for demultiplexing entangled photons, transmitted through a few-mode fiber (FMF). We experimentally demonstrated a spatially multiplexed BBM92 QKD scheme. The modes are selectively excited through separate single-mode-fibers and subsequently separated by MPLC into distinct output ports. Unlike high-dimensional QKD based on coherent modal superpositions, our approach exploits distinguishable guided modes as parallel channels while preserving the entanglement required for QKD. For the multiplexed links, we obtain quantum bit error rates of $1.9 \pm 0.4\%$ for the channel 1 and $6.8 \pm 0.8\%$ for the channel 2. These results are relevant for scalable quantum-secured networks, space-division-multiplexed QKD systems, multi-user entanglement distribution, and future quantum internet architectures, where parallel quantum channels must be implemented without compromising the quantum correlations required for security.

quant-ph↗

arXiv2026

SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution

Real-world software must continuously evolve to meet ever-changing and open-ended requirements. AI agents, increasingly deployed as long-running systems, are now entrusted to drive this evolution. Yet, existing benchmarks evaluate agents on isolated, one-off coding tasks, neglecting the temporal dependencies and technical debt inherent in real-world software evolution. To bridge this gap, we introduce DeepCommit, an agentic pipeline that reconstructs verifiable Milestone DAGs from noisy commit logs, where milestones are defined as functionally cohesive development goals. These executable sequences enable SWE-Milestone, a benchmark that evaluates agents on streams of milestone-level tasks, requiring them to sustain system integrity and limit error accumulation, dimensions of long-term software evolution largely missing from current benchmarks. Our evaluation of 12 frontier models across 4 agent frameworks reveals a critical vulnerability: overall performance scores drop significantly from >80% on isolated tasks to 38.03% in continuous settings, exposing agents' profound struggle with long-term maintenance and error propagation.

cs.SE↗

arXiv2026

Efficient Group Lasso Regularized Rank Regression with Simulation-Based Tuning

High-dimensional regression often suffers from heavy-tailed noise and outliers, which can severely undermine the reliability of least-squares based methods. To improve robustness, we adopt a non-smooth Wilcoxon score based rank objective and incorporate the group sparsity regularization. By extending the tuning-free property originally developed for the rank Lasso, we introduce a simulation-based tuning rule and further establish a finite-sample error bound for the resulting estimator. To solve the associated optimization problem, we develop a proximal augmented Lagrangian method, for which we provide a novel convergence analysis by proving the metric subregularity of the underlying non-polyhedral KKT mapping, while enabling efficient semismooth Newton updates for the subproblems. Extensive numerical experiments demonstrate the robustness and effectiveness of our proposed estimator against several leading alternatives, and showcase the efficiency and scalability of our algorithm compared to the state-of-the-art baseline in both simulated and real-data settings.

stat.ML↗

arXiv2026

Regression Accumulation in Multi-Turn LLM Programming Conversations

In LLM-assisted software development, coding is often iterative. We study regression accumulation in multi-turn LLM programming conversations, where later code suggestions may break requirements introduced in earlier turns. Reliability therefore depends not only on satisfying the current request, but also on preserving previously satisfied behavior. We construct 542 tasks from HumanEval+ and MBPP+ and extend each task into an 8-turn requirement-evolution chain. We evaluate six LLMs on 26,016 turn instances (542 x 6 x 8). At each turn, we test whether the current code still passes earlier benchmark tests. We also analyze 384 failure cases from the failure population and build a taxonomy of multi-turn regression bugs through independent four-annotator labeling. Our results show that regression accumulation appears across all six models: 40% to 73% of tasks lose previously correct behavior over the full conversation. Final-turn quality is lower than initial-turn quality across models, especially when later turns add input validation or broader input types. Manual analysis shows that Cross-Turn Conflict, where later code conflicts with earlier requirements, is the main failure class. We further find that Verification Gate, which checks new code against prior tests and triggers rollback and retry, is the only strategy that consistently improves all models, raising final-turn quality from 75.8% to 87.9% on DeepSeek-V3 and from 31.6% to 47.3% on Llama-3.1-8B. These findings suggest that strong single-turn performance can overestimate reliability in multi-turn coding conversations. Future evaluation and tool design should test whether later code suggestions preserve earlier requirements and should include Verification Gate mechanisms.

cs.SE↗

arXiv2026

DRL-Based Joint Beamforming and Surface Shape Optimization for Flexible Intelligent Metasurface-Aided ISAC Systems

Integrated sensing and communication (ISAC) unifies high-precision sensing and wireless data transmission. In this paper, we investigate the design of ISAC systems enabled by flexible intelligent metasurface (FIM) and aim to minimize the Cramér-Rao bound (CRB) with quality of service (QoS) constraints using deep reinforcement learning (DRL). Specifically, we formulate the joint design of beamforming matrix and FIMs surface shape to reduce the CRB subject to transmit power, QoS and the FIMs surface shape constraints. However, the non-convex formulation makes optimization problem difficult to solve. To tackle this issue, we develop a deep deterministic policy gradient (DDPG) actor critic DRL scheme for the joint design, guided by a constraint aware reward to progressively improve sensing performance. Numerical results demonstrate that jointly optimizing the beamforming matrix and the FIMs surface shape substantially decreases CRB while ensuring communication quality compared with existing rigid arrays.

cs.IT↗

arXiv2026

Revealing Safety-Critical Scenarios for UTM via Transformer

Unmanned Traffic Management (UTM) systems are cloud-based platforms designed to manage and coordinate multiple aerial vehicles remotely. UTM systems are safety-critical which cannot tolerate failures like crash or collision. To reveal latent vulnerabilities, there are neither optimal failure-exposing demonstrations nor clear reward signals. Additionally, UTM's self-healing capability introduces the ``long-tail effect'' of critical failures. We propose framing UTM vulnerability discovery as a sequence modeling problem amenable to transformer-based RL architectures. Our approach leverages attention mechanisms to directly model the relationship among system states, and predict optimal actions. Our framework introduces a Policy Model that generates targeted test scenarios and an Action Sampler that enforces domain constraints. We use a risk-based reward function to guide exploration. Through extensive evaluation on a 700-hour simulation study, we demonstrate an 8$\times$ improvement in vulnerability discovery efficiency compared to expert-guided testing. It also discovers critical edge cases that traditional methods have missed.

cs.AI↗

arXiv2026

The Forgetting-Retention Dilemma: Certified Unlearning Theory in Continual Learning

Machine unlearning aims to eliminate the influence of specific data from trained models to safeguard privacy. However, this presents a significant challenge in the context of continual learning (CL), where models update sequentially on dynamic datasets. A major limitation is that current certified unlearning algorithms fail to account for the complex, cumulative model evolution inherent to CL framework. In this work, we establish the first theoretical foundation bridging CL and machine unlearning. We formulate the CL's unlearning objective as the minimization of post-unlearning excess risk, which decomposes into CL excess risk and unlearning loss, characterizing the fundamental trade-off between preserving historical knowledge and targeted forgetting. Under mild assumptions, we first establish an upper bound for the CL excess risk in non-convex models. We then adapt two certified unlearning approaches, gradient-based and Hessian-based, to the CL framework. Our analysis reveals that while the gradient-based approach is less effective than the Hessian-based method in minimizing unlearning loss, it offers the distinct advantage of nearly zero storage overhead for enabling unlearning. This insight motivates a hybrid strategy that reduces storage costs while maintaining post-unlearning performance. Experimental results further validate our theoretical findings.

cs.LG↗

arXiv2026

Convergence analysis of the Riemannian proximal gradient method with inexact oracle

We extend the notion of an inexact first-order oracle from the Euclidean setting to Riemannian optimization, and conduct a convergence analysis for the Riemannian proximal gradient method equipped with this oracle, which we refer to as RPG-IO. Under mild conditions on the oracle errors, we establish the global convergence of RPG-IO. Specifically, we prove that (i) the norm of the search direction converges to zero; (ii) the sequence of function values converges to the function value at any accumulation point of the iterates; and (iii) every accumulation point of the iterates is a stationary point. Under the additional assumption of the Riemannian Kurdyka--Łojasiewicz (KL) property, we prove that the full sequence of iterates generated by RPG-IO converges to a single stationary point. Moreover, we derive explicit convergence rates when the KL exponent is specified. Finally, when a strong inexact oracle is employed, we establish the convergence rate of the sequence of function values to the optimal value.

math.OC↗

arXiv2026

SenseExpo: Spatial Exploration and Navigation via Scene Estimation from Expeditious Predictive Operators

We present \textbf{SenseExpo}, a lightweight single-robot exploration framework that integrates a compact map prediction network into a frontier-based strategy. SenseExpo addresses two long-standing challenges in classical methods -- high computational overhead and poor environmental generalization. Our prediction network combines Generative Adversarial Networks (GANs), Transformers, and Fast Fourier Convolution (FFC) to achieve a remarkably small footprint of only 709K parameters. Despite its compactness, SenseExpo outperforms U-Net (24.5M) and LaMa (51M) on the KTH dataset, achieving PSNR 9.026 and SSIM 0.718, representing a 38.7\% PSNR gain over LaMa. Cross-domain evaluation further verifies strong generalization with an FID of 161.55 on HouseExpo. In exploration experiments, SenseExpo reaches target coverage 67.9\% faster on KTH and 77.1\% faster on MRPB~1.0 than a MapEx-style global obstacle-prediction baseline under the same simulator; because the methods predict different map semantics, this comparison evaluates planning utility rather than a direct predictor ranking. Implemented as a plug-and-play ROS (Robot Operating System) node, our framework integrates with existing navigation stacks, providing an efficient solution for resource-constrained robotic systems.

cs.CV↗

arXiv2026

ACEsplat: Accelerated 3D Gaussian Scene Regression via RGB and Poses Only

Per-scene 3D Gaussian Splatting (3DGS) enables high-fidelity rendering, but practical robotic and AR scene capture pipelines often depend on external geometric initialization (e.g., SfM point clouds or depth estimates), which can be slow and brittle in on-site deployment. We present ACEsplat, a fast per-scene optimization framework that reconstructs 3D Gaussian representations from RGB images and camera poses only, without requiring external 3D priors (e.g., precomputed SfM models or supervised depth maps). ACEsplat uses a two-stage pipeline: (1) a self-supervised scene coordinate regression (SCR) module builds an internal geometry prior within 4--5 minutes; (2) SCR features and coordinate priors are fused by a lightweight Gaussian initialization head, followed by per-scene 3DGS optimization. On static-view rendering, ACEsplat achieves 29.11 dB PSNR on Wayspots with real-time SLAM poses and 33.20 dB on Cambridge Landmarks with SfM-refined poses. On RealEstate10K sparse-view novel view synthesis, it achieves competitive image fidelity under a challenging 2-view setting. ACEsplat completes scene-specific SCR mapping and 3DGS reconstruction within 15--25 minutes on a single GPU, making it a practical RGB+pose-only solution for rapid scene setup in robotics and mixed-reality applications.

cs.RO↗

arXiv2026

Tensor Algebraic Property Skeletons: Amplifying Property-Based Testing for AI Compilers

Deep learning (DL) compilers such as TVM and ONNX-MLIR lower tensor computation graphs into optimized executables for target backends. Testing these compilers has made substantial progress in generating well-formed inputs in the context of fuzzing. However, such generation alone does not catch semantic drifts from algebraic invariants that graph transformations and optimizations are expected to preserve. While tensor algebra has been studied for decades, it has not been transformed into executable property-based tests (PBTs) for DL compilers because doing so requires the time-consuming and error-prone task of jointly constructing operators, tensors, and oracles. The central challenge is no longer generating well-formed inputs for fuzzing DL compilers, but bootstrapping executable PBTs with such inputs and correct oracles based on tensor algebra. We realize this vision in Propilot, an LLM-driven agentic property-based testing framework for DL compilers. First, Propilot represents tensor algebra knowledge as reusable property skeletons, each coupled with operator constraints and oracle templates. Second, given a target compiler, Propilot instantiates these skeletons into executable PBTs by generating paired tensor computation graphs, tensor inputs, and expected semantic relations as oracles. Third, to prevent generated tests from degenerating into invalid or uninformative PBTs, Propilot validates each PBT candidate before execution for applicability and safety. Validation feedback, execution results, and coverage signals guide subsequent generation. We evaluate Propilot on TVM with 212 operators and 20 property skeletons, generating 4,579 PBTs. Compared with direct LLM-based PBT generation, Propilot reduces redundancy by 49% and eliminates invalid tests through explicit property skeletons. This effectiveness translates into finding semantic errors and numerical discrepancies.

cs.SE↗

arXiv2026

PowerAgentBench-Dyn: A Benchmark for Agentic AI in Power System Dynamic Studies

Large Language Model (LLM)-based agents are increasingly being used to automate multi-step engineering work flows by interacting with software tools, interpreting intermediate results, and autonomously planning subsequent actions. Power system dynamic studies represent a particularly promising yet largely unexplored application domain for these agents. Unlike static computational tasks, dynamic studies often require more time on model parameter calibration, engineering judgment, and decision making under constrained action spaces. This paper introduces PowerAgentBench-Dyn, a benchmark designed to evaluate Agentic AI systems on power system dynamic-analysis tasks. The benchmark targets problems that cannot be reduced to a single optimization or coding task, but instead require a type of reasoning, tool usage, and iterative experimentation routinely performed by experienced power system engineers. The proposed framework includes two initial benchmark tasks. The first, the Dynamic Model Quality Review Benchmark, evaluates agents' ability to validate and diagnose dynamic models based on model-quality compliance criteria specified by system operators. The second, the Dynamic Security Risk Screening Benchmark, assesses agents' capability to leverage semantic memory and a limited simulation budget to identify, rank, and analyze the most critical short-circuit contingencies from an unseen fault dataset, as well as propose and evaluate possible mitigation measures. For each task, we define the simulation environment, observation and action spaces, and evaluation metrics. The benchmark is reproducible in a metric-based sense: released cases and simulator settings define a deterministic evaluator, while stochastic agent behavior is assessed over repeated runs using success rates and other metrics. The benchmark supports the development of future Agentic AI for power system operation and planning.

eess.SY↗

arXiv2026

PowerAgentBench-SS: A Benchmark for Agentic AI in Power System Steady-State Studies

Power system benchmarks usually evaluate numerical solvers, prediction models, or sequential controllers. These benchmarks are necessary, but they do not directly test whether a Large Language Model (LLM) agent can execute an engineering workflow: inspect a grid case, select tools, call simulators, screen contingencies, propose admissible mitigations, validate results, and produce an auditable evidence trail. This paper introduces PowerAgentBench-SS, a steady-state benchmark framework for evaluating tool-using agents in power system operation and planning studies. The benchmark exposes public case data, action constraints, a tool API, and a validation budget to an agent, while a hidden evaluator recomputes physical validity and scores the submitted report. We define the agent interface, tool contract, evidence log, and risk-sensitive metrics, including submitted recall, evidence-backed recall, found recall, false-safe penalties, severity regret, residual violation score, action cost, tool-use efficiency, and workflow diagnostics. To make the framework concrete, we instantiate the protocol in a reproducible DC thermal N-2 contingency-search pilot on deterministic IEEE 39-bus operating-point variants, with scripted baselines, an LLM JSON-command adapter, three locally hosted Ollama LLM agents, and one OpenAI API agent. The results show why solver-only or answer-only evaluation is insufficient: agents are distinguished not only by top-contingency discovery, but also by validation-budget use, explicit submission, type coercions, duplicate validations, evidence-backed reporting, and mitigation behavior.

eess.SY↗

arXiv2026

Finding Compiler-Platform Interaction Bugs in Deep Learning Pipelines via Cross-Layer Constraints

The growing deployment of artificial intelligence (AI) necessitates robust deep learning (DL) compilers, such as TVM and ONNX-MLIR. These compilers take as input high-level AI models, lower them through multi-layer transformations, and specialize them to diverse hardware. Testing such compilers is uniquely challenging as correctness depends on implicit constraints embedded throughout the compilation stack. Existing testing approaches largely take type constraints to restrict input model generation and therefore emphasize type validation and monitor compilation crashes or coverage gains. This focus overlooks compiler-platform interaction bugs that arise from interleaved effects across compilation and execution environments. In this work, we propose a scalable, automated DL compiler testing framework for, in tandem, (1) finding compiler-platform interaction bugs and (2) enabling behavior equivalence partitioning. Our key insight is that these bugs are caused by violated assumptions arising from interactions across compilation passes and hardware platforms. Therefore, we move beyond constraining input generation and derive full-stack constraints. Our approach is three-fold. First, we design an automated approach to extract full-stack constraints that jointly guide model generation and characterize compilation behaviors. Second, we prioritize constraints that expose interaction-sensitive behaviors, so our generated models are capable of exercising deep compilation logic. Third, we enable behavior equivalence partitioning by automatically inserting assertions to monitor distinct compilation symptoms that coverage or pass/fail signals miss. We evaluated our tool, XCheck, on three widely-used DL compilers and found 2,034 bug-revealing cases, including memory overflows, integer overflows, and silent unexpected compilations that were rooted in compiler-platform interactions.

cs.SE↗

arXiv2026

Latent Structural Categorical Matrix Completion with Application to Quasispecies Analysis

Matrix completion has been extensively studied for real-valued data, but existing methods are often limited in handling categorical variables. We propose LCMC, a double-loop optimization framework for categorical matrix completion via latent factorization based on a binary tensor representation. In this setting, each categorical entry is encoded as a one-hot vector along a third tensor mode, thereby preserving its discrete, non-ordinal nature. The outer loop adaptively estimates the latent dimension by iteratively updating it with feedback from the inner loop, while the inner loop reconstructs the categorical matrix through tensor factorization, supported by a corresponding theoretical analysis. To further improve scalability and robustness, we introduce enhancements including a split-merge-refine strategy and an adaptive data reduction technique. Experiments on synthetic and real-world datasets in viral quasispecies reconstruction, demonstrate that LCMC achieves superior accuracy and efficiency compared to existing methods.

math.OC↗

arXiv2026

Reformulating Energy Storage Capacity Accreditation Problem with Marginal Reliability Impact

To enhance the efficiency of capacity markets, many electricity markets in the U.S. are adopting or planning to implement marginal capacity accreditation reforms. This paper provides new insights into energy storage capacity accreditation using Marginal Reliability Impact (MRI). We reformulate the commonly used reliability-based storage dispatch model as an optimization problem, enabling direct calculation of the MRI from the Lagrange multipliers, rather than using brute-force perturbation analysis. The analysis demonstrates that the EUE is a piecewise linear function and the storage MRI retains a non-negative property across various system scenarios. We further explore the influence of qualified capacity (QC), storage dispatch rules, and other key factors on storage accreditation, providing practical insights for system operators. Additionally, comparisons of storage capacity accreditation under different reliability criteria offer valuable guidance for policymakers in setting future standards. Numerical results from a modified California system validate our findings and highlight several important phenomena associated with the MRI-based accreditation scheme.

eess.SY↗

arXiv2026

Modeling Coincident Peak Pricing in Electricity Markets: Challenges and Peak Shaving Effectiveness

Coincident Peak (CP) pricing is widely used in U.S. electricity markets to allocate capacity and transmission costs. This paper develops a behavioral game-theoretic framework for CP-driven load shifting that couples a nonlinear cost-allocation model with day-ahead (one-shot) and real-time (sequential-learning) decision processes. We examine two update rules, namely best-response dynamics (BRD) and fictitious-play dynamics (FPD), across continuous and finite action spaces to quantify how flexibility, action resolution, and participation influence peak outcomes. Using ERCOT peak-day data, we find that FPD reliably reduces system peaks, whereas BRD is more variable and can increase peaks under tight-capacity conditions. Finer action resolution improves peak shaving, while the number of participants is largely neutral when aggregate flexibility is fixed. Meanwhile, information-provider signals can induce herding, whereas response-aware or diverse signals improve peak shaving. These results highlight both the potential and limits of CP pricing: smoothing information and enabling granular control are as important as the amount of available flexibility. The framework offers practical guidance for system operators and consumers: For ISOs, broadcasting smoothed CP signals and setting minimum controllable-capacity thresholds enhance coordination. For consumers, greater flexibility and finer control resolution improve both cost savings and peak-shaving performance.

eess.SY↗

arXiv2026

MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks

Large Language Models (LLMs) have achieved great success in many real-world applications, especially the one serving as the cognitive backbone of Multi-Agent Systems (MAS) to orchestrate complex workflows in practice. Since many deployment scenarios preclude MAS workflow modifications and its performance is highly sensitive to the input prompts, prompt optimization emerges as a more natural approach to improve its performance. However, real-world prompt optimization for MAS is impeded by three key challenges: (1) the need of sample efficiency due to prohibitive evaluation costs, (2) topology-induced coupling among prompts, and (3) the combinatorial explosion of the search space. To address these challenges, we introduce MASPOB (Multi-Agent System Prompt Optimization via Bandits), a novel sample-efficient framework based on bandits. By leveraging Upper Confidence Bound (UCB) to quantify uncertainty, the bandit framework balances exploration and exploitation, maximizing gains within a strictly limited budget. To handle topology-induced coupling, MASPOB integrates Graph Neural Networks (GNNs) to capture structural priors, learning topology-aware representations of prompt semantics. Furthermore, it employs coordinate ascent to decompose the optimization into univariate sub-problems, reducing search complexity from exponential to linear. Extensive experiments across diverse benchmarks demonstrate that MASPOB achieves state-of-the-art performance, consistently outperforming existing baselines.

cs.LG↗