Search arXiv⌕ Search

arXiv subjects

Shuai Wang

Publications and source records attributed to Shuai Wang.

At least 235 records · Page 13Linked to original sources
arXiv2026

HoliAntiSpoof: Audio LLM for Holistic Speech Anti-Spoofing

Recent advances in speech synthesis and editing have made speech spoofing increasingly challenging. However, most existing methods treat spoofing as binary classification, overlooking that diverse spoofing techniques manipulate multiple, coupled speech attributes and their semantic effects. In this paper, we introduce HoliAntiSpoof, the first audio large language model (ALLM) framework for holistic speech anti-spoofing analysis. HoliAntiSpoof reformulates spoofing analysis as a unified text generation task, enabling joint reasoning over spoofing methods, affected speech attributes, and their semantic impacts. To support semantic-level analysis, we introduce DailyTalkEdit, a new anti-spoofing benchmark that simulates realistic conversational manipulations and provides annotations of semantic influence. Extensive experiments demonstrate that HoliAntiSpoof outperforms conventional baselines across multiple settings, while preliminary results show that in-context learning further improves out-of-domain generalization. These findings indicate that ALLMs not only enhance speech spoofing detection performance but also enable interpretable analysis of spoofing behaviors and their semantic effects, pointing towards more trustworthy and explainable speech security. Data and code are publicly available.

cs.SD↗
arXiv2026

Photonic spiking reinforcement learning for intelligent routing

Intelligent routing plays a key role in modern communication infrastructure, including data centers, computing networks, and future 6G networks. Although reinforcement learning (RL) has shown great potential for intelligent routing, its practical deployment remains constrained by high energy consumption and decision latency. Here, we propose a photonic spiking RL architecture that implements a proximal policy optimization (PPO)-based intelligent routing algorithm. The performance of the proposed approach is systematically evaluated on a software-defined network (SDN) with a fat-tree topology. The results demonstrate that, under various baseline traffic rate conditions, the PPO-based routing strategy significantly outperforms the conventional Dijkstra algorithm in several key performance metrics. Furthermore, a hardware-software collaborative framework of the spiking Actor network is realized for three typical baseline traffic rates, utilizing a photonic synapse chip based on a Mach-Zehnder interferometer (MZI) array and a photonic spiking neuron chip based on distributed feedback lasers with a saturable absorber (DFB-SAs). Experimental validation on 640 state-action pairs shows that the inference accuracy of the hardware-software collaborative framework is consistent with that of the pure algorithmic implementation. The impacts of different hidden-layer scales in the spiking Actor network and varying network size of fat-tree topology are further analyzed. The integration of photonic spiking RL with SDN-based routing establishes a novel paradigm for intelligent routing optimization, featuring ultra-low latency and high energy efficiency. This approach exhibits broad application prospects in real-time network optimization scenarios, including large-scale data centers, computing networks, satellite Internet systems, and future 6G networks.

physics.optics↗
arXiv2026

From Evaluation to Enhancement: Large Language Models for Zero-Knowledge Proof Code Generation

Zero-knowledge proofs (ZKPs) are increasingly deployed in domains such as privacy-preserving authentication, verifiable computation, and secure finance. However, authoring ZK programs remains challenging: unlike conventional software development, ZK programming manifests a fundamental paradigm shift from \textit{imperative computation} to \textit{declarative verification}. This process requires rigorous reasoning about finite field arithmetic and complex constraint systems (which is rare in common imperative languages), making it knowledge-intensive and error-prone. While large language models (LLMs) have demonstrated strong code generation capabilities in general-purpose languages, their effectiveness for ZK programming, where correctness hinges on both language mastery and constraint-level reasoning, remains unexplored. To address this gap, we propose \textsc{ZK-Eval}, a domain-specific evaluation pipeline that probes LLM capabilities on ZK programming at three levels: language knowledge, algebraic primitive competence, and end-to-end program generation. Our evaluation of four state-of-the-art LLMs reveals that while models demonstrate strong proficiency in language syntax, they struggle when implementing and composing algebraic primitives to specify correct constraint systems, frequently producing incorrect programs. Based on these insights, we introduce \textsc{ZK-Coder}, an agentic framework that augments LLMs with constraint sketching, guided retrieval, and interactive repair. Experiments with GPT-o3 on Circom and Noir show substantial gains, with success rates improving from 20.29\% to 87.85\% and from 28.38\% to 97.79\%, respectively. With \textsc{ZK-Eval} and \textsc{ZK-Coder}, we establish a new basis for systematically measuring and augmenting LLMs in ZK code generation to lower barriers for practitioners and advance privacy computing.

cs.SE↗
arXiv2026

Understanding and Bridging the Planner-Coder Gap: A Systematic Study on the Robustness of Multi-Agent Systems for Code Generation

Multi-agent systems (MASs) have emerged as a promising paradigm for automated code generation, demonstrating impressive performance on established benchmarks. Despite their prosperous development, the fundamental mechanisms underlying their robustness remain poorly understood, raising critical concerns for real-world deployment. This paper conducts a systematic empirical study to uncover the internal robustness flaws of MASs using a mutation-based methodology. By designing a testing pipeline incorporating semantic-preserving mutation operators and a novel fitness function, we assess mainstream MASs across multiple datasets and LLMs. Our findings reveal substantial robustness flaws: semantically equivalent inputs cause drastic performance drops, with MASs failing to solve 7.9\%--83.3\% of problems they initially resolved successfully. Through comprehensive failure analysis, we discover a fundamental cause underlying these robustness issues: the \textit{planner-coder gap}, which accounts for 75.3\% of failures. This gap arises from information loss in the multi-stage transformation process where planning agents decompose requirements into underspecified plans, and coding agents subsequently misinterpret intricate logic during code generation. Based on this formulated information transformation process, we propose a \textit{repairing method} that mitigates information loss through multi-prompt generation and introduces a monitor agent to bridge the planner-coder gap. Evaluation shows that our repairing method effectively enhances the robustness of MASs by solving 40.0\%--88.9\% of identified failures. Our work uncovers critical robustness flaws in MASs and provides effective mitigation strategies, contributing essential insights for developing more reliable MASs for code generation.

cs.SE↗
arXiv2026

Diffusion Language Model Inference with Monte Carlo Tree Search

Diffusion language models (DLMs) have recently emerged as a compelling alternative to autoregressive generation, offering parallel generation and improved global coherence. During inference, DLMs generate text by iteratively denoising masked sequences in parallel; however, determining which positions to unmask and which tokens to commit forms a large combinatorial search problem. Existing inference methods approximate this search using heuristics, which often yield suboptimal decoding paths; other approaches instead rely on additional training to guide token selection. To introduce a principled search mechanism for DLMs inference, we introduce MEDAL, an inference-time scaling framework that integrates Monte Carlo Tree SEarch initialization for Diffusion LAnguage Model inference. We employ Monte Carlo Tree Search at the initialization stage to explore promising unmasking trajectories, providing a robust starting point for subsequent refinement. This design enables efficient inference-time scaling, allowing generation quality to improve as the search budget increases, without additional training. Across multiple benchmarks, MEDAL achieves up to 22.0% improvement over existing inference strategies, establishing a new paradigm for search-based inference in DLMs.

cs.CL↗
arXiv2026

Edge Collaborative Gaussian Splatting with Integrated Rendering and Communication

Gaussian splatting (GS) struggles with degraded rendering quality on low-cost devices. To address this issue, we present edge collaborative GS (ECO-GS), where each user can switch between a local small GS model to guarantee timeliness and a remote large GS model to guarantee fidelity. However, deciding how to engage the large GS model is nontrivial, due to the interdependency between rendering requirements and resource conditions. To this end, we propose integrated rendering and communication (IRAC), which jointly optimizes collaboration status (i.e., deciding whether to engage large GS) and edge power allocation (i.e., enabling remote rendering) under communication constraints across different users by minimizing a newly-derived GS switching function. Despite the nonconvexity of the problem, we propose an efficient penalty majorization minimization (PMM) algorithm to obtain the critical point solution. Furthermore, we develop an imitation learning optimization (ILO) algorithm, which reduces the computational time by over 100x compared to PMM. Experiments demonstrate the superiority of PMM and the real-time execution capability of ILO.

cs.IT↗
arXiv2026

HPTune: Hierarchical Proactive Tuning for Collision-Free Model Predictive Control

Parameter tuning is a powerful approach to enhance adaptability in model predictive control (MPC) motion planners. However, existing methods typically operate in a myopic fashion that only evaluates executed actions, leading to inefficient parameter updates due to the sparsity of failure events (e.g., obstacle nearness or collision). To cope with this issue, we propose to extend evaluation from executed to non-executed actions, yielding a hierarchical proactive tuning (HPTune) framework that combines both a fast-level tuning and a slow-level tuning. The fast one adopts risk indicators of predictive closing speed and predictive proximity distance, and the slow one leverages an extended evaluation loss for closed-loop backpropagation. Additionally, we integrate HPTune with the Doppler LiDAR that provides obstacle velocities apart from position-only measurements for enhanced motion predictions, thus facilitating the implementation of HPTune. Extensive experiments on high-fidelity simulator demonstrate that HPTune achieves efficient MPC tuning and outperforms various baseline schemes in complex environments. It is found that HPTune enables situation-tailored motion planning by formulating a safe, agile collision avoidance strategy.

cs.RO↗
arXiv2026

LLM-Driven Scenario-Aware Planning for Autonomous Driving

Hybrid planner switching framework (HPSF) for autonomous driving needs to reconcile high-speed driving efficiency with safe maneuvering in dense traffic. Existing HPSF methods often fail to make reliable mode transitions or sustain efficient driving in congested environments, owing to heuristic scene recognition and low-frequency control updates. To address the limitation, this paper proposes LAP, a large language model (LLM) driven, adaptive planning method, which switches between high-speed driving in low-complexity scenes and precise driving in high-complexity scenes, enabling high qualities of trajectory generation through confined gaps. This is achieved by leveraging LLM for scene understanding and integrating its inference into the joint optimization of mode configuration and motion planning. The joint optimization is solved using tree-search model predictive control and alternating minimization. We implement LAP by Python in Robot Operating System (ROS). High-fidelity simulation results show that the proposed LAP outperforms other benchmarks in terms of both driving time and success rate.

cs.RO↗
arXiv2026

Predicting Mortgage Default with Machine Learning: AutoML, Class Imbalance, and Leakage Control

Mortgage default prediction is a core task in financial risk management, and machine learning models are increasingly used to estimate default probabilities and provide interpretable signals for downstream decisions. In real-world mortgage datasets, however, three factors frequently undermine evaluation validity and deployment reliability: ambiguity in default labeling, severe class imbalance, and information leakage arising from temporal structure and post-event variables. We compare multiple machine learning approaches for mortgage default prediction using a real-world loan-level dataset, with emphasis on leakage control and imbalance handling. We employ leakage-aware feature selection, a strict temporal split that constrains both origination and reporting periods, and controlled downsampling of the majority class. Across multiple positive-to-negative ratios, performance remains stable, and an AutoML approach (AutoGluon) achieves the strongest AUROC among the models evaluated. An extended and pedagogical version of this work will appear as a book chapter.

cs.LG↗
arXiv2026

SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL

While large language models (LLMs) have substantially improved Text-to-SQL generation, a pronounced gap remains between AI systems and human experts on challenging benchmarks such as BIRD-SQL. We argue this gap stems largely from the prevailing single-pass paradigm, which lacks the iterative reasoning, schema exploration, and error-correction behaviors that humans naturally employ. To address this limitation, we introduce SQL-Trail, a multi-turn reinforcement learning (RL) agentic framework for Text-to-SQL. Rather than producing a query in one shot, SQL-Trail interacts with the database environment and uses execution feedback to iteratively refine its predictions. Our approach centers on two key ideas: (i) an adaptive turn-budget allocation mechanism that scales the agent's interaction depth to match question difficulty, and (ii) a composite reward panel that jointly incentivizes SQL correctness and efficient exploration. Across benchmarks, SQL-Trail sets a new state of the art and delivers strong data efficiency--up to 18x higher than prior single-pass RL state-of-the-art methods. Notably, our 7B and 14B models outperform substantially larger proprietary systems by 5% on average, underscoring the effectiveness of interactive, agentic workflows for robust Text-to-SQL generation.

cs.AI↗
arXiv2026

A Large-Scale IPv6-Based Measurement of the Starlink Network

Low Earth Orbit (LEO) satellite networks have attracted considerable attention for their ability to deliver global, low-latency broadband Internet services. In this paper, we present a large-scale measurement study of the Starlink network, the largest LEO satellite constellation to date. We first propose an efficient method for discovering active Starlink user routers, identifying approximately 5.98 million IPv6 addresses across 208 regions in 165 countries. Compared to general-purpose IPv6 target generation algorithms, our router-centric approach achieves near-complete coverage and, to the best of our knowledge, yields the most comprehensive known set of active IPv6 addresses for Starlink user routers. Based on the discovered user routers, we further propose an efficient method for mapping the Starlink backbone network and uncover a topology consisting of 49 Points of Presence (PoPs) interconnected by 98 links. We conduct a detailed statistical analysis of active Starlink user routers and PoPs, and further characterize the IPv6 address assignment strategy adopted by the Starlink network. Finally, we analyze the latency of Starlink user routers, propose a method to distinguish different types of users within the same region using outside-in measurement, and identify the ongoing V2 Mini satellite deployment as a potential driver of the performance improvements. The dataset of the Starlink backbone network is publicly available at https://ki3.org.cn/#/starlink-network.

cs.NI↗
arXiv2026

PromptPrism: A Linguistically-Inspired Taxonomy for Prompts

Prompts are the interface for eliciting the capabilities of large language models (LLMs). Understanding their structure and components is critical for analyzing LLM behavior and optimizing performance. However, the field lacks a comprehensive framework for systematic prompt analysis and understanding. We introduce PromptPrism, a linguistically-inspired taxonomy that enables prompt analysis across three hierarchical levels: functional structure, semantic component, and syntactic pattern. By applying linguistic concepts to prompt analysis, PromptPrism bridges traditional language understanding and modern LLM research, offering insights that purely empirical approaches might miss. We show the practical utility of PromptPrism by applying it to three applications: (1) a taxonomy-guided prompt refinement approach that automatically improves prompt quality and enhances model performance across a range of tasks; (2) a multi-dimensional dataset profiling method that extracts and aggregates structural, semantic, and syntactic characteristics from prompt datasets, enabling comprehensive analysis of prompt distributions and patterns; (3) a controlled experimental framework for prompt sensitivity analysis by quantifying the impact of semantic reordering and delimiter modifications on LLM performance. Our experimental results validate the effectiveness of our taxonomy across these applications, demonstrating that PromptPrism provides a foundation for refining, profiling, and analyzing prompts.

cs.CL↗
arXiv2026

IB-GRPO: Aligning LLM-based Learning Path Recommendation with Educational Objectives via Indicator-Based Group Relative Policy Optimization

Learning Path Recommendation (LPR) aims to generate personalized sequences of learning items that maximize long-term learning effect while respecting pedagogical principles and operational constraints. Although large language models (LLMs) offer rich semantic understanding for free-form recommendation, applying them to long-horizon LPR is challenging due to (i) misalignment with pedagogical objectives such as the Zone of Proximal Development (ZPD) under sparse, delayed feedback, (ii) scarce and costly expert demonstrations, and (iii) multi-objective interactions among learning effect, difficulty scheduling, length controllability, and trajectory diversity. To address these issues, we propose IB-GRPO (Indicator-Based Group Relative Policy Optimization), an indicator-guided alignment approach for LLM-based LPR. To mitigate data scarcity, we construct hybrid expert demonstrations via Genetic Algorithm search and teacher RL agents and warm-start the LLM with supervised fine-tuning. Building on this warm-start, we design a within-session ZPD alignment score for difficulty scheduling. IB-GRPO then uses the $I_{ε+}$ dominance indicator to compute group-relative advantages over multiple objectives, avoiding manual scalarization and improving Pareto trade-offs. Experiments on ASSIST09 and Junyi using the KES simulator with a Qwen2.5-7B backbone show consistent improvements over representative RL and LLM baselines.

cs.AI↗
arXiv2026

WeDefense: A Toolkit to Defend Against Fake Audio

The advances in generative AI have enabled the creation of synthetic audio which is perceptually indistinguishable from real, genuine audio. Although this stellar progress enables many positive applications, it also raises risks of misuse, such as for impersonation, disinformation and fraud. Despite a growing number of open-source fake audio detection codes released through numerous challenges and initiatives, most are tailored to specific competitions, datasets or models. A standardized and unified toolkit that supports the fair benchmarking and comparison of competing solutions with not just common databases, protocols, metrics, but also a shared codebase, is missing. To address this, we propose WeDefense, the first open-source toolkit to support both fake audio detection and localization. Beyond model training, WeDefense emphasizes critical yet often overlooked components: flexible input and augmentation, calibration, score fusion, standardized evaluation metrics, and analysis tools for deeper understanding and interpretation. The toolkit is publicly available at https://github.com/zlin0/wedefense with interactive demos for fake audio detection and localization.

cs.SD↗
arXiv2026

MMEDIT: A Unified Framework for Multi-Type Audio Editing via Audio Language Model

Text-guided audio editing aims to modify specific acoustic events while strictly preserving non-target content. Despite recent progress, existing approaches remain fundamentally limited. Training-free methods often suffer from signal degradation caused by diffusion inversion, while training-based methods, although achieving higher generation quality, are severely constrained by the scarcity of high-quality paired data and task formulations that cover only a narrow subset of editing operations. In addition, standard architectures typically decouple text and audio processing, limiting the ability to align instructions with specific acoustic contexts. To address these challenges, we propose MMEdit, an audio-language-model-driven framework for unified audio editing. We systematically extend task definitions to cover a comprehensive range of editing operations, including addition, replacement, removal, reordering, and attribute modification. Furthermore, we design a scalable data synthesis pipeline to construct large-scale paired datasets with fine-grained event-level annotations. To capture complex editing semantics, we integrate a Qwen2-Audio encoder with an MMDiT-based generator, enabling precise cross-modal alignment and localized editing. Experimental results demonstrate that our method achieves superior editing localization accuracy, robust instruction following, and high fidelity in non-edited regions.

cs.SD↗
arXiv2026

Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Framework

Large Language Model (LLM)-based agent systems are increasingly deployed for complex real-world tasks but remain vulnerable to natural language-based attacks that exploit over-privileged tool use. This paper aims to understand and mitigate such attacks through the lens of privilege escalation, defined as agent actions exceeding the least privilege required for a user's intended task. Based on a formal model of LLM agent systems, we identify novel privilege escalation scenarios, particularly in multi-agent systems, including a variant akin to the classic confused deputy problem. To defend against both known and newly demonstrated privilege escalation, we propose SEAgent, a mandatory access control (MAC) framework built upon attribute-based access control (ABAC). SEAgent monitors agent-tool interactions via an information flow graph and enforces customizable security policies based on entity attributes. Our evaluations show that SEAgent effectively blocks various privilege escalation while maintaining a low false positive rate and negligible system overhead. This demonstrates its robustness and adaptability in securing LLM-based agent systems.

cs.CR↗
arXiv2026

1/2 order convergence rate of Euler-type methods for time-changed stochastic differential equations with super-linearly growing drift and diffusion coefficients

This paper investigates the strong convergence properties of two Euler-type methods for a class of time-changed stochastic differential equations (TCSDEs) with super-linearly growing drift and diffusion coefficients. Building upon existing research, we propose a backward Euler method (BEM) and introduce its explicit counterpart -- the projected Euler method (PEM). We prove that both methods converge strongly in the $L_2$-sense at the optimal rate of 1/2. This result extends the applicability of both the BEM and the PEM to a broader class of TCSDEs. Moreover, the two methods offer complementary strengths: while BEM possesses wide applicability, PEM is computationally more efficient. Numerical simulations confirm our theoretical findings and illustrate practical performance of both schemes.

math.NA↗
arXiv2026

QueryIPI: Query-agnostic Indirect Prompt Injection on Coding Agents

Modern coding agents integrated into IDEs orchestrate powerful tools and high-privilege system access, creating a high-stakes attack surface. Prior work on Indirect Prompt Injection (IPI) is mainly query-specific, requiring particular user queries as triggers and leading to poor generalizability. We propose query-agnostic IPI, a new attack paradigm that reliably executes malicious payloads under arbitrary user queries. Our key insight is that malicious payloads should leverage the invariant prompt context (i.e., system prompt and tool descriptions) rather than variant user queries. We present QueryIPI, an automated framework that uses tool descriptions as optimizable payloads and refines them via iterative, prompt-based blackbox optimization. QueryIPI leverages system invariants for initial seed generation aligned with agent conventions, and iterative reflection to resolve instruction-following failures and safety refusals. Experiments on five simulated agents show that QueryIPI achieves up to 87% success rate, outperforming the best baseline (50%). Crucially, generated malicious descriptions transfer to real-world coding agents, highlighting a practical security risk.

cs.CR↗