Search arXiv⌕ Search

arXiv subjects

Lei Ma

Publications and source records attributed to Lei Ma.

At least 19 recordsLinked to original sources
arXiv2026

Understanding Tool-Mediated Interaction Failures in Agentic GUI Software: An Empirical Study

Large language model (LLM) agents increasingly complete tasks through live graphical user interfaces (GUIs). Because the model cannot directly operate the GUI, these systems often rely on tools to capture screenshots or UI trees, translate model outputs into GUI actions, and report whether the interface changed. We study failures where this tool-mediated interaction makes the agent's view of the task diverge from the live GUI. We construct Malva, a defect library with 335 confirmed real-world failures from 40 open-source applications. These failures fall into 11 defect patterns rooted in state representation, state transition, and synchronization problems. They are widespread: 90% of the studied applications contain more than one defect type. They are also often silent: incorrectness appears in 86.6% of failures, including 119 cases that produce wrong behavior without a fail-stop signal. We operationalize this taxonomy with MalvaGuard, a pre-deployment static contract checker that reaches 57.3% precision and 76.8% recall on an additional 20-application corpus.

cs.SE↗
arXiv2026

Who Improves the Robot? Toward Physical Recursive Self-Improvement

Robots are increasingly autonomous in task execution, yet their improvement remains largely human-driven. This study investigates Physical Recursive Self-Improvement (Physical RSI), in which physical experience guides lasting updates to both a robot's capabilities and its improvement procedure, making subsequent improvement more effective across tasks. Physical RSI faces challenges from noisy observations, continuous dynamics, costly trials, and irreversible consequences. We present an L0-L5 framework that differentiates capability-level from meta-level updates and within-task from across-task gains, reserving L5 for independently verified recursive gain. We study existing methods around harness adaptation and model training, alongside safety and control mechanisms that govern execution and successive updates. Our analysis reveals that, despite substantial progress in self-improvement, the surveyed literature does not yet demonstrate Physical RSI as defined by our framework. We identify research priorities in reliable feedback, causal attribution, safety preservation, and benchmarking, outlining a path toward robots that autonomously improve how they learn while ensuring safety. The GitHub repository for Physical RSI is available at https://github.com/SAIL-Research-Lab/Physical-RSI.

cs.AI↗
arXiv2026

Prime-EVC: One-Step Expressive Emotional Voice Conversion via Emotion-Primed Flow Matching

Recent diffusion- and conditional flow matching (CFM)-based emotional voice conversion (EVC) systems achieve strong conversion quality. However, they typically rely on multiple sampling steps, because the conditioning specifies which emotion to impose while its acoustic realization is left to the sampler. In this paper, we propose Prime-EVC, a one-step expressive EVC architecture based on emotion-primed flow matching. Our key idea is to reallocate the emotional conversion between the conditioning and the sampler: a FiLM-fused speaker-emotion style, an emotional variance adaptor, and direct emotion and spectro-temporal supervision assemble an emotion-rich conditioning upstream, rendering the residual conversion left to the CFM decoder attainable within one Euler step. Experiments on the ESD corpus demonstrate that single-step Prime-EVC surpasses five representative EVC systems on every quality metric and exceeds 4- and 100-step DurFlex-EVC in subjective naturalness and emotion while running 3.4--50 times faster than both.

cs.SD↗
arXiv2026

Purpose IR: Compiling User Purpose for Privacy-Preserving Agent Workflow State

LLM-agent workflows routinely transform rich observations into plans, summaries, memories, handoffs, and other reusable state. This creates a privacy boundary that task relevance alone does not capture: an observation may be needed as evidence for a task without its full semantics being authorized to persist. We call this mismatch the purpose-to-state semantic gap. The key distinction is that evidence authority is not release authority. We introduce Purpose IR, a bounded typed intermediate representation that compiles natural-language user purpose into an executable semantic boundary for reusable agent state. A Purpose program is an acyclic semantic dataflow graph in which evidence leaves specify task-required semantics, typed dependencies constrain authorized derivations, and declared sinks determine which values or actions may cross the reusable-state boundary. A deterministic compiler constructs and validates the authoritative program, while a typed runtime reconstructs reusable state only from validated sink outputs. Under explicit execution contracts, this design yields release confinement and purpose noninterference, characterizing what factual semantics may be released and which observation differences must become irrelevant to reusable state. Across 1,200 cases spanning LangGraph, CrewAI, and MobileRun, Purpose IR achieves 99.6% Privacy, 83.3% Task, and 83.3% Privacy-Compliant Success (PCS), outperforming the strongest high-privacy baseline by 27.5 PCS points. On 493 PrivacyLens trajectories, it achieves the highest Safe Action Rate at 77.3%, 10.4 points above the next-best method, extending the same boundary from reusable state to downstream actions. These results show that privacy-preserving agent state requires more than filtering sensitive or task-irrelevant content: it requires an explicit, executable representation of what the user's purpose authorizes to survive.

cs.CR↗
arXiv2026

Conditioned in Training, Dispensable at Inference: Typological Conditioning for Multilingual Speech Translation

Multilingual speech translation frontends built on speech large language models typically condition on language identity, as a learned embedding or a prompted language name. Such a signal, however, is learned separately for each language and transfers nothing between typologically related languages. In this paper, we present TypoCast, a frontend that conditions on the typological profile of the source language rather than on its label alone. A typology-informed hierarchical language encoding represents each language by its morphological type, constituent order and family, so that supervision is shared among related languages. A dual-route mixture-of-experts adapter routes inputs through a shared typological route together with a per-language residual, and a typology-aware prompt conveys the same profile to the decoder. Extensive experiments on CVSS-C demonstrate that TypoCast surpasses state-of-the-art speech-to-speech translation systems on French, German and Spanish to English, averaged over the three directions, and outperforms the identity-conditioned S2ST-Omni on every language of a seven-language inventory, with only 228M trainable parameters. Ablation studies further reveal that the conditioning signal acts during training and is dispensable at inference: a model trained without it is consistently worse, whereas removing it from a trained model changes BLEU by less than 0.2, and expert usage is consistent with the signal shaping how adapter capacity is divided among languages.

cs.CL↗
arXiv2026

An Extensive Empirical Study on Evaluation Metrics for Combinatorial Interaction Testing

Combinatorial interaction testing (CIT) is a black-box testing method that has received extensive attention in both research and practice over recent years. Its primary objective is to construct an effective combinatorial test suite that detects software failures caused by parameter interactions. As a fundamental component of the CIT testing process, the evaluation metric plays a critical role in assessing and comparing combinatorial test suites, as well as in evaluating various test generation techniques. For CIT practitioners, selecting an appropriate evaluation metric is both important and challenging, given the wide variety of available options. Nevertheless, no prior work has systematically addressed this problem. To fill this gap, this paper first provides a comprehensive survey of black-box evaluation metrics for combinatorial test suites, offering rigorous definitions, clear classifications, illustrative examples, and complexity analyses. We then conduct an extensive empirical study involving eight open-source projects, encompassing 32 test scenarios and 295,624 combinatorial test suites. In this study, we examine the correlation between each static evaluation metric and fault-detection effectiveness using two correlation measures. Experimental results show that the Value Combination Coverage (VCC) metric serves as a valid predictor for test-suite evaluation. However, distribution-based metrics generally incur lower computational costs than interaction coverage-based ones. The choice of an appropriate metric should also account for the test suite's inherent properties, as these characteristics can substantially influence the effectiveness of the evaluation. Finally, we provide practical guidelines to assist CIT practitioners in selecting suitable evaluation metrics for assessing or comparing combinatorial test suites.

cs.SE↗
arXiv2026

Diagnosing On-Policy Self-Distillation for Reasoning Language Models

On-policy self-distillation (OPSD) has attracted growing interest as a promising approach to improve the reasoning ability of language models. Without external rewards nor a separate stronger teacher, the self-teacher with privileged information could provide dense signals on student's trajectories. However, its behavior in language reasoning remains unclear, with reported outcomes ranging from modest gains to behavioral collapse. In this work, we diagnose OPSD for mathematical reasoning across models spanning 0.6B--8B parameters. We conduct controlled experiments and token-level analyses to fully delve into OPSD. We point out that teacher's signal is shaped by reasoning-mode alignment and the complete teacher prefix, rather than by privileged semantics alone. OPSD improves reasoning only in narrow compatibility regimes. Otherwise, it produces ineffective length growth, stable degradation, or behavioral collapse. Token-level analysis shows that teacher's signal is not stable and does not predict downstream performance. Based on these results, we argue that OPSD is a sensitive algorithm rather than a generally reliable reasoning-improvement post-training method.

cs.CL↗
arXiv2026

MAADBench: The Refreshable Paradigm for Anomaly Detection in Multi-Agent Systems

Recent studies report that LLM-based multi-agent systems (MAS) fail at rates of 41%-87%, yet to our knowledge, no benchmark to date supports systematic anomaly detection (AD) for them. Building MAS AD benchmarks is hard because they must remain fresh as LLM systems evolve: tasks may leak into training data and thus be memorized by LLMs, traces and anomaly patterns expire as backbones evolve, and labels must be provided reliably for each refresh. To address these challenges, we present MAADBench (MA: multi-agent; AD: anomaly detection), the first refreshable MAS AD benchmark designed for diverse, evolving LLM backbones underlying the agents. MAADBench combines (1) sampled-and-coupled generative tasks over an approximately 10^37-task space to mitigate task leakage, (2) refreshable trace generation under configurable LLM backbones, and (3) automated provision of cost-free, deterministic step-level labels for fine-grained AD evaluation. Beyond offering the paradigm itself, we run MAADBench with five state-of-the-art LLM backbones and release the MAADBench-Full dataset with 5,200 step-labeled traces. Benchmarking 25 AD methods on the MAADBench dataset reveals substantial limitations in current approaches: they rely heavily on supervision, struggle with subtle MAS-specific anomalies, and lack robustness across LLM backbones. These gaps point to a rich research agenda for MAS-specific anomaly detection, with MAADBench providing a systematic and refreshable testbed for method development and evaluation. We open-source MAADBench-Full at https://huggingface.co/datasets/hww123/MAADBench-full.

cs.AI↗
arXiv2026

SaplingGuard: A Multidimensional-Profile-Aware Multi-Agent Guardrail for Developmentally Safe Adolescent-LLM Interaction

As adolescents increasingly use LLMs in everyday life, ensuring safe and developmentally appropriate responses has become essential. However, existing LLM guardrails primarily target explicit harmful content in isolated prompts or responses and are less effective at identifying implicit, context-dependent developmental risks. To address this limitation, we propose SaplingGuard, a plug-and-play, profile-aware and dialogue-aware guardrail that requires no modification to downstream model parameters. SaplingGuard decomposes adolescent safety intervention into three specialized agents for user profile construction, context-aware risk assessment, and intent-preserving prompt optimization. Together, these agents leverage the current prompt, preceding dialogue, and structured user characteristics to identify contextual risks and guide downstream response generation. We evaluate SaplingGuard on SaplingBench, which contains 276 three-turn dialogues spanning seven categories of developmental risk. Across ten adolescent profile conditions and nine open- and closed-source downstream LLMs, profile-aware retrieval improves the Major Hit rate from 50.8% to 63.7+/-1.1%. End-to-end intervention further reduces the average harmful response rate from 17.10% to 5.27% and increases the average safety score from 0.7017 to 1.0043. These results show that user-profile and dialogue context provide complementary signals for identifying implicit developmental risks, and that SaplingGuard can serve as an effective external safety layer for adolescent-LLM interaction.

cs.CR↗
arXiv2026

SameFact: The Same Safety Facts Lead to Different Responses Across Interfaces

Safety evaluations often ask whether a model recognizes that an action is unsafe, whereas agent evaluations ask what the model chooses to do. Using safety judgments as evidence about action selection therefore raises a measurement question: does the influence of the same safety-relevant fact persist across response interfaces? We introduce SameFact, a matched-counterfactual benchmark that tests this question directly. SameFact contains 300 safe/unsafe pairs that hold the task, prior observations, candidate action, identifiers, and non-target facts fixed while changing a single state-grounded safety fact. Across six LLM backbones, we measure the effect of this matched intervention through three interfaces at the same candidate-action boundary: explicit safety judgment, checkpoint candidate admission, and open first-action selection. All six backbones show lower aggregate sensitivity under open first-action selection than under judgment, but the change is not a uniform attenuation: across 24 model-factor cells, Spearman agreement falls from 0.817 between judgment and checkpoint admission to 0.470 between judgment and open first-action selection, while pairwise ordering disagreement rises from 18.5% to 32.6%. A follow-up 2x2 first-response experiment shows that a checkpoint-style protocol increases measured sensitivity in all six backbones by 8.4-29.3 percentage points, whereas action-space effects and their interactions with protocol vary in magnitude and direction across models. These results show that the response interface is part of the measured quantity: judgment and action interfaces share safety signal, but do not provide interchangeable measurements of how safety-relevant facts shape model responses.

cs.CR↗
arXiv2026

LiteTex-GS: Fast and Lightweight Texturing for Gaussian Splatting

Gaussian Splatting has enabled real-time novel view synthesis, but its tightly coupled geometry and appearance representation often require a large number of primitives to reproduce high-frequency texture details, leading to substantial memory and optimization costs. Recent textured 2D Gaussian methods alleviate this limitation by attaching texture maps to Gaussian primitives. However, bridging the fundamental structural gap between discrete Gaussians and continuous 2D grids requires complex parameterizations that introduce severe computational overhead. This overhead fundamentally compromises the original efficiency of Gaussian Splatting, making the balance between detailed texturing and computational agility an unresolved challenge. To address these challenges, we propose LiteTex-GS, a fast and lightweight texturing framework for Gaussian Splatting. Our method initializes an extremely compact representation, assigning minimal local texture to each Gaussian and progressively allocates higher resolution only to primitives with significant reconstruction errors. To maintain a streamlined geometric scaffold, we introduce a contribution- and area-aware pruning strategy that eliminates low-utility Gaussians. Furthermore, to mitigate the gradient dilution caused by texture upsampling, we design a resolution-aware update rule that preserves rapid and stable convergence. Extensive experiments on standard novel view synthesis benchmarks demonstrate that our method achieves competitive or superior rendering quality while using substantially fewer parameters and less training time than existing textured Gaussian baselines.

cs.CV↗
arXiv2026

Earth System World Model for What-If Simulations: A Case Study for Terrestrial Ecosystems

Machine learning emulators have become essential for accelerating expensive Earth-system simulations, but most existing approaches remain passive forecasters: they reproduce simulator trajectories under prescribed forcings without an explicit interaction mechanism for user-specified interventions. This limits their use in interactive scientific workflows and Earth-system digital twins, where users often need to explore how a system would respond if selected state components were changed. We propose an action-conditioned world-modeling framework for Earth-system emulation that reformulates simulator trajectories as supervision for controllable state-transition learning. The key idea is transition-action pretraining: naturally observed state changes are treated as label-free action supervision, allowing the model to learn both prescribed dynamics and action-conditioned responses without manually annotated interventions. We further introduce masked response learning to infer unobserved variables under partial state edits and learn coupled system dependencies. We test this framework on ecosystem dynamics across six global regions and multiple stand ages. Experiments show that the model preserves competitive long-horizon emulation accuracy while enabling controllable structural interventions and coherent responses in coupled ecosystem-cycle variables. These results suggest a practical route from passive Earth-system emulators toward interactive, intervention-aware scientific surrogates.

cs.LG↗
arXiv2026

SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce

E-commerce search often suffers from vocabulary mismatch between user queries and merchant-authored product titles, since short titles cannot fully cover diverse user expressions or visual product attributes. Although Doc2Query alleviates this issue by generating pseudo-queries for document expansion, traditional methods are text-only and not optimized for e-commerce business objectives. As a result, they may produce semantically plausible but commercially ineffective expansions and miss key attributes present in product images. To this end, we propose E-commerce Search-Aligned Multimodal Doc2Query (SAM-D2Q), a business-aligned multimodal document expansion framework for e-commerce search under Boolean retrieval constraints. SAM-D2Q consists of three stages: (1) task-adapted multimodal supervised fine-tuning to enhance vision-language understanding of product titles, images, and user queries; (2) multimodal data augmentation to improve perception of key visual attributes and expansion coverage; and (3) reinforcement-learning-based preference alignment toward search business objectives, encouraging the model to generate pseudo-queries that better match user intent and commercial value. Offline experiments show that SAM-D2Q substantially improves retrieval performance over traditional Doc2Query methods. Deployed in the AliExpress production search system, SAM-D2Q improves online business metrics, increasing GMV by +3.38% and Pay Count by +2.27%.

cs.IR↗
arXiv2026

Schrödinger Bridges on Lie Group Manifolds for Probabilistic Intrinsic Generation

Generative modeling directly on geometric manifolds can avoid errors introduced by flattening non-Euclidean data, repeated ambient projection, and coordinate inconsistency in Euclidean representations. Schrodinger bridges provide a probabilistic generative framework for entropy-regularized transport between prescribed endpoint distributions. We study Schrodinger bridges for kinetic dynamics on Lie group manifolds with state X_t = (g_t, xi_t) in G x g, allowing endpoint observations to constrain only the variables that are actually measured. In particular, the entropy projection determines the conditional law of the unobserved endpoint velocities. For the same observed endpoint bridge, we develop two computational realizations: Wrapped-Kernel Bridge Calibration (WKBC) uses an explicit periodized kinetic kernel on compact Abelian groups, whereas Reciprocal Conditional-Control Bridge Matching (RCCBM) handles compact non-Abelian groups through two-sided endpoint calibration and mollified conditional-control matching. The canonical teacher-mixture path law is itself a Markov reciprocal law, so forward generation uses a calibrated initial law and one learned Doob controller. Moreover, we establish a modular error bound in the bounded-Lipschitz path metric that provides a clean separation of errors due to endpoints, control regression, initialization, discretization, and related approximations. Experiments on multiple Lie group manifold datasets validate the feasibility and consistency of our proposed method, covering protein and RNA torsions, SO(3), U(n), and the Protein Conformational Transition Pathway Generation task using mdCATH trajectories in a compact reduced representation. The source code is publicly available at https://github.com/cafferyzhang12/Schr-dinger_Bridge_on_LieGroup.

stat.ML↗
arXiv2026

A Survey on Web Application Testing: Over a Decade of Evolution

As one of the most popular software applications, a web application is a program accessible through the web that dynamically generates content based on user interactions or contextual data; examples include online shopping platforms, social networking sites, and financial services. Web applications operate in diverse environments and leverage web technologies such as HTML, CSS, JavaScript, and Ajax, often incorporating features like asynchronous operations to enhance user experience. Due to the growing number of users and the popularity of web applications, the quality of these applications has become increasingly important. Web Application Testing (WAT) plays a vital role in ensuring the functionality, security, and reliability of web applications. Given the speed with which web technologies are evolving, WAT is especially important. In the last twelve years, various WAT approaches have been developed. The diversity of approaches reflects the many aspects of web applications, such as dynamic content, asynchronous operations, and diverse user environments. This paper provides a comprehensive overview of the main achievements over the last twelve years: It examines the main steps involved in WAT, including test case generation and execution, as well as evaluation and assessment. The currently available tools for WAT are also examined. The paper also discusses open research challenges and potential future work in WAT.

cs.SE↗
arXiv2026

FiSeR: Fine-Grained Source Representations for Cross-Domain AI Image Detection

Real-world synthetic image detectors often generalize poorly under domain shift despite strong in-domain performance. Using unsupervised UMAP projections, we find that natural and synthetic features remain partially separable on unseen datasets, yet performance still drops, suggesting that the classification head overfits to training-domain artifacts. Therefore, the key is to learn more transferable representations so that the decision criterion is more stable and robust to domain shifts. Based on the structural fact that synthetic images are produced by diverse generators, we propose a hierarchical contrastive learning framework that improves the separability between natural and synthetic images while preserving generator identity information. It jointly optimizes (i) a coarse contrastive objective between natural and synthetic images and (ii) a fine contrastive objective among synthetic images using generator identities. Trained on WildFake, our method achieves an average AUROC gain of +10.22 on cross-domain evaluation over Chameleon, AIGIBench, Community Forensics, and GenImage under the same settings as the strong baseline DIRE. For few-shot adaptation, we freeze the backbone and fit an SVM head on 10 labeled samples per class, improving AUROC by +10.64 on AIGIBench and +17.41 on Chameleon, averaged over 12 widely used detectors. Our code is publicly available at: https://github.com/heyongxin233/FiSeR.

cs.CV↗
arXiv2026

NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video

Long-form video understanding encompasses tasks that go beyond retrieving isolated events, including tracking an evolving narrative and interpreting social meaning that may remain implicit. However, existing benchmarks rarely evaluate these capabilities jointly, particularly in high-context, non-English media. To address this gap, we introduce NARU, a benchmark designed to evaluate Narrative evolution and Reasoning on cultural Understanding in Japanese long-form video. NARU consists of 1,481 questions grounded in 155 videos totaling 146.8 hours, spanning four narrative and five cultural dimensions. To construct the benchmark at this scale, we propose a hierarchical memory-based annotation pipeline that transforms raw video into structured event, narrative, and cultural annotations, then generates questions via task-oriented synthesis and iterative shortcut removal. The construction process includes two native-speaker verification stages involving 68 annotators. Evaluations across eight model configurations reveal substantial limitations in both long-range narrative integration and culturally grounded reasoning. By exposing these persistent gaps, NARU offers a systematic testing ground for developing MLLMs capable of reliably interpreting long-form, high-context video.

cs.CV↗
arXiv2026

Autonomous Exploration-Based Precise Mapping for Mobile Robots through Stepwise and Consistent Motions

This paper presents an autonomous exploration framework. It is designed for indoor ground mobile robots that utilize laser Simultaneous Localization and Mapping (SLAM), ensuring process completeness and precise mapping results. For frontier search, the local-global sampling architecture based on multiple Rapidly Exploring Random Trees (RRTs) is employed. Traversability checks during RRT expansion and global RRT pruning upon map updates eliminate unreachable frontiers, reducing potential collisions and deadlocks. Adaptive sampling density adjustments, informed by obstacle distribution, enhance exploration coverage potential. For frontier point navigation, a stepwise consistent motion strategy is adopted, wherein the robot strictly drives straight on approximately equidistant line segments in the polyline path and rotates in place at segment junctions. This simplified, decoupled motion pattern improves scan-matching stability and mitigates map drift. For process control, the framework serializes frontier point selection and navigation, avoiding oscillation caused by frequent goal changes in conventional parallelized processes. The waypoint retracing mechanism is introduced to generate repeated observations, triggering loop closure detection and backend optimization in graph-based SLAM, thereby improving map consistency and precision. Experiments in both simulation and real-world scenarios validate the effectiveness of the framework. It achieves improved mapping coverage and precision in more challenging environments compared to baseline 2D exploration algorithms. It also shows robustness in supporting resource-constrained robot platforms and maintaining mapping consistency across various LiDAR field-of-view (FoV) configurations.

cs.RO↗