arXiv subjects

Chenyu Zhao

Publications and source records attributed to Chenyu Zhao.

At least 19 recordsLinked to original sources

arXiv2026

You Cannot Optimize What You Cannot Measure: Multitasking Evaluation as the Missing Foundation of AI-Mediated Heads-Up Interaction

AI-mediated heads-up augmented reality (AR) replaces fixed interfaces with dynamically adapting ones that decide what information to present, in what form, and when, based on a continually changing context that cannot be fully anticipated beforehand. Although it remains an interface, its behavior over time is only partially specified at design time. We argue that this shift requires a corresponding change in evaluation: from snapshots to trajectories. A fixed interface is evaluated in a snapshot --- one context, one session, one set of task-performance metrics. A fluid interface must be evaluated over a trajectory --- a sequence of contexts with transitions, sampled from the distribution the interface will actually encounter, and tracked long enough for user trust to form, evolve, and potentially deteriorate. Drawing on the literature for heads-up AR multitasking enabled by optical see-through head-mounted displays (OST-HMDs), we find that current evaluation practice remains largely snapshot-based. Most studies use fixed-condition, single-session designs; interference between concurrent tasks is rarely quantified directly; and commonly used workload measures cannot disentangle cognitive load attributable to individual tasks. To address these limitations, we argue for three shifts: from isolated metrics to Performance Operating Characteristic (POC) interference frontiers, from fixed conditions to evaluation over context trajectories, and from single-session snapshots to longitudinal trust measurement.

cs.HC↗

arXiv2026

Dense Soft Weighting for Radar Ego-Velocity Estimation

Sensing ego-velocity estimation is fundamental to state estimation in visually degraded environments, where camera- and LiDAR-based pipelines can become unreliable. Millimetre-wave radar is well suited to these conditions because it provides direct Doppler velocity sensing and remains robust to poor illumination, textureless scenes, and airborne particulates. However, conventional radar ego-velocity pipelines typically apply constant false alarm rate (CFAR) thresholding to convert dense radar spectra into sparse point clouds, prematurely discarding sub-threshold returns that may still retain useful Doppler motion cues. We present Dense Soft Weighting, an analytic radar front-end that maps every range-Doppler cell to a continuous confidence metric rather than enforcing a binary detection threshold. Ego-velocity is then estimated using a deterministic robust weighted least-squares formulation, while the same weighted measurements provide a closed-form, measurement-derived velocity covariance for integration with a shared inertial back-end. The method requires no platform-specific training data or learning-based uncertainty model, supporting transfer across single-chip radar configurations. Across two public datasets and one self-collected dataset, Dense Soft Weighting reduces mean absolute pose error by 31-45% relative to the strongest CFAR point-cloud baseline under an identical inertial back-end, while running in real time on embedded hardware.

cs.RO↗

arXiv2026

AgentTether: Graph-Guided Diagnosis and Runtime Intervention for Reliable LLM Agent Operation

Large language model (LLM) agents are increasingly used for multi-step, stateful tool-use tasks, yet production reliability remains limited. Unlike static software repair, agent repair must recover dynamic trajectories whose early decisions can propagate into later errors and external state changes. Existing automatic remedies address only part of this problem: blind retry adds no diagnosis, outcome feedback says whether a run failed but not where or why, and self-reflection often lacks grounded evidence to prevent the same failure from recurring. We present AgentTether, a run-time repair framework that automates post-run diagnosis and guided recovery without modifying the underlying agent or environment. AgentTether abstracts each run into Transition Units, links them through a dependency-aware Critical Transition Graph, and localizes failure-critical subtrajectories by combining an offline normal-behavior model with a run-local graph detector. It then converts the localized cause into behavior-scoped guidance backed by cross-iteration Repair Memory, and can optionally apply guarded run-time intervention to keep the correction active during re-execution. The same design can be deployed as an offline diagnostic-and-guidance tool or as an online repair layer. We evaluate AgentTether on 261 tau-bench tasks across three domains with Qwen3.7-max, and test cross-model transfer on Banking with GPT-5.4. On the hardest Banking domain, AgentTether repairs 59.04% (49/83) of initially failed Qwen3.7-max tasks and 65.12% (56/86) of initially failed GPT-5.4 tasks. Overall, AgentTether improves repair effectiveness while reducing agent turns and end-to-end approach tokens, suggesting a practical reliability layer that can wrap existing agent deployments, reduce wasted re-execution, and improve recovery without retraining the agent.

cs.SE↗

arXiv2026

EvidenT: An Evidence-Preserving Framework for Iterative System-Level Package Repair

Frequent toolchain updates and growing ISA diversity have made system-level software package repair increasingly important. Diagnosing and repairing build failures remains challenging because failures involve heterogeneous evidence, dependency constraints, and architecture-specific build conventions. While recent LLM-based repair methods show promise for project-level source fixes, they struggle with system-level repair, where failures span multi-language artifacts such as build recipes, scripts, and source archives, and require iterative validation through external build services. In this paper, we first conduct a systematic empirical study of real-world system-level build failures. We find that 72% of failures stem from dependency and environment misconfigurations rather than isolated code defects, suggesting that effective repair must prioritize packaging logic and iterative feedback. Motivated by these insights, we propose EvidenT, an evidence-preserving repair framework that decouples iteration-aware evidence management from tool execution. EvidenT includes: (1) an external Build Service for reproducible execution and feedback; (2) an Evidence-Preserving Repair Controller that fuses repair history, knowledge context, and build artifacts; and (3) an automated Repair Orchestrator that invokes modular tools for failure localization and system-level repair in a closed-loop validation environment. We evaluate EvidenT on 219 real-world RISC-V package build failures. EvidenT repairs 118 packages (53.88%), outperforming state-of-the-art agentic baselines (20.55%) and direct LLM-based repair (1.83%). To assess architectural generality, we extend EvidenT to legacy ISAs by updating only ISA-specific knowledge context. Preliminary experiments achieve success rates of 41.77% on aarch64 and 46.99% on x86_64, demonstrating robustness across diverse hardware ecosystems.

cs.SE↗

arXiv2026

Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents

Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad hoc. Existing systems expose traces or generate follow-up feedback, but they do not convert heterogeneous runtime evidence into grounded, bounded recovery guidance for a subsequent attempt. We present PROBE, a failure-anchored framework for structured recovery in software engineering agents. PROBE organizes failed-run telemetry into structured evidence, structured diagnosis, and bounded recovery guidance through a Telemetry Layer, a Diagnosis Layer, and a Guidance Gate. The Telemetry Layer preserves fine-grained runtime signals, the Diagnosis Layer fuses cross-signal evidence into grounded diagnoses, and the Guidance Gate produces diagnosis-derived guidance only when it is evidence-grounded, actionable, and within the scope of agent-side behavior. We evaluate PROBE across three settings: repository-level software repair, enterprise workflow recovery, and AIOps service mitigation. On 257 initially unresolved cases, PROBE achieves 65.37% Top-1 diagnosis accuracy and a 21.79% recovery rate, outperforming the strongest non-PROBE baseline by 43.58 and 12.45 percentage points. The results reveal a diagnosis-recovery gap: accurate diagnosis is necessary but insufficient unless translated into bounded guidance that a subsequent attempt can execute and verify. Beyond controlled evaluation, a Microsoft IcM prototype shows that PROBE can attach as a non-intrusive side channel to existing service-diagnosis workflows without changing the agent policy, toolset, or execution budget. These results suggest that telemetry-grounded, failure-anchored recovery can improve post-failure recoverability under realistic engineering constraints.

cs.SE↗

arXiv2026

Breaking the Communication-Accuracy Trade-off: A Sparsified Information Diffusion Framework for Multi-Agent Collaborative Perception

The growing relevance of multi-agent systems has drawn increasing focus on communication-efficient filters for collaborative perception to alleviate the system's communication burden. While the event-triggered (ET) mechanism can improve communication efficiency in collaborative state estimation, an inevitable trade-off exists between estimation accuracy and communication cost in ET filters. This paper proposes a fast and accurate ET diffusion-based filter for real-time multi-agent collaborative target tracking, aiming to reduce the system's data transmission without compromise in tracking performance. The proposed filter achieves improved tracking accuracy, reduced data transmission, and accelerated convergence using an error-minimized ET cubature information filter (CIF) for local estimation, and a correlation-aware diffusion strategy for global fusion. The experimental results confirm the scalability of the proposed EDC-CIF algorithm and demonstrate its efficacy in simultaneously reducing estimation error and computation time while significantly enhancing communication efficiency.

cs.MA↗

arXiv2026

Which Types of Heterogeneity Matter for Root Cause Localization in Microservice Systems ?

Microservice root cause localization is fundamentally challenged by the inherent heterogeneity of cloud-native systems, which encompasses diverse observability data and multiple system entities. Existing approaches typically focus on only one aspect of heterogeneity and thus fail to capture its full diagnostic value. In this work, we systematically examine the multifaceted role of heterogeneity within both microservice systems and the RCL process. This analysis motivates a deeper investigation into how entity-level distinctions and their asymmetric dependencies influence fault behavior. Our empirical analysis of two microservice benchmarks reveals that entity-level heterogeneity naturally gives rise to heterogeneous fault propagation, which is highly asymmetric and dominated by cross-layer interactions between services and hosts. In light of this, we propose NexusRCL, a semi-supervised framework that internalizes these propagation patterns by formalizing services and hosts as distinct node types within a heterogeneous graph. This design, coupled with an event-based abstraction mechanism, allows NexusRCL to effectively capture both data level and entity-level heterogeneity while minimizing labeling costs through active learning. Comprehensive evaluations on two industrial benchmark datasets demonstrate NexusRCL's superior performance, achieving improvements of up to 49.85\% in Top-1 accuracy (A@1) and 32.70\% in Average Top-5 accuracy (A@5) compared to state-of-the-art methods.

cs.SE↗

arXiv2026

FreeScale: Distributed Training for Sequence Recommendation Models with Minimal Scaling Cost

Modern industrial Deep Learning Recommendation Models typically extract user preferences through the analysis of sequential interaction histories, subsequently generating predictions based on these derived interests. The inherent heterogeneity in data characteristics frequently result in substantial under-utilization of computational resources during large-scale training, primarily due to computational bubbles caused by severe stragglers and slow blocking communications. This paper introduces FreeScale, a solution designed to (1) mitigate the straggler problem through meticulously load balanced input samples (2) minimize the blocking communication by overlapping prioritized embedding communications with computations (3) resolve the GPU resource competition during computation and communication overlapping by communicating through SM-Free techniques. Empirical evaluation demonstrates that FreeScale achieves up to 90.3% reduction in computational bubbles when applied to real-world workloads running on 256 H100 GPUs.

cs.LG↗

arXiv2026

A Benchmark for Language Models in Real-World System Building

During migration across instruction set architectures (ISAs), software package build repair is a critical task for ensuring the reliability of software deployment and the stability of modern operating systems. While Large Language Models (LLMs) have shown promise in tackling this challenge, prior work has primarily focused on single instruction set architecture (ISA) and homogeneous programming languages. To address this limitation, we introduce a new benchmark designed for software package build repair across diverse architectures and languages. Comprising 268 real-world software package build failures, the benchmark provides a standardized evaluation pipeline. We evaluate six state-of-the-art LLMs on the benchmark, and the results show that cross-ISA software package repair remains difficult and requires further advances. By systematically exposing this challenge, the benchmark establishes a foundation for advancing future methods aimed at improving software portability and bridging architectural gaps.

cs.SE↗

arXiv2025

LLM-driven Knowledge Enhancement for Multimodal Cancer Survival Prediction

Current multimodal survival prediction methods typically rely on pathology images (WSIs) and genomic data, both of which are high-dimensional and redundant, making it difficult to extract discriminative features from them and align different modalities. Moreover, using a simple survival follow-up label is insufficient to supervise such a complex task. To address these challenges, we propose KEMM, an LLM-driven Knowledge-Enhanced Multimodal Model for cancer survival prediction, which integrates expert reports and prognostic background knowledge. 1) Expert reports, provided by pathologists on a case-by-case basis and refined by large language model (LLM), offer succinct and clinically focused diagnostic statements. This information may typically suggest different survival outcomes. 2) Prognostic background knowledge (PBK), generated concisely by LLM, provides valuable prognostic background knowledge on different cancer types, which also enhances survival prediction. To leverage these knowledge, we introduce the knowledge-enhanced cross-modal (KECM) attention module. KECM can effectively guide the network to focus on discriminative and survival-relevant features from highly redundant modalities. Extensive experiments on five datasets demonstrate that KEMM achieves state-of-the-art performance. The code will be released upon acceptance.

cs.CV↗

arXiv2025

Words to Describe What I'm Feeling: Exploring the Potential of AI Agents for High Subjectivity Decisions in Advance Care Planning

Loss of decisional capacity, coupled with the increasing absence of reliable human proxies, raises urgent questions about how individuals' values can be represented in Advance Care Planning (ACP). To probe this fraught design space of high-risk, high-subjectivity decision support, we built an experience prototype (\acpagent{}) and asked 15 participants in 4 workshops to train it to be their personal ACP proxy. We analysed their coping strategies and feature requests and mapped the results onto axes of agent autonomy and human control. Our findings show a surprising 86.7\% agreement with \acpagent{}, arguing for a potential new role of AI in ACP where agents act as personal advocates for individuals, building mutual intelligibility over time. We propose that the key areas of future risk that must be addressed are the moderation of users' expectations and designing accountability and oversight over agent deployment and cutoffs.

cs.HC↗

arXiv2025

Real-Time 3D Object Detection with Inference-Aligned Learning

Real-time 3D object detection from point clouds is essential for dynamic scene understanding in applications such as augmented reality, robotics and navigation. We introduce a novel Spatial-prioritized and Rank-aware 3D object detection (SR3D) framework for indoor point clouds, to bridge the gap between how detectors are trained and how they are evaluated. This gap stems from the lack of spatial reliability and ranking awareness during training, which conflicts with the ranking-based prediction selection used as inference. Such a training-inference gap hampers the model's ability to learn representations aligned with inference-time behavior. To address the limitation, SR3D consists of two components tailored to the spatial nature of point clouds during training: a novel spatial-prioritized optimal transport assignment that dynamically emphasizes well-located and spatially reliable samples, and a rank-aware adaptive self-distillation scheme that adaptively injects ranking perception via a self-distillation paradigm. Extensive experiments on ScanNet V2 and SUN RGB-D show that SR3D effectively bridges the training-inference gap and significantly outperforms prior methods in accuracy while maintaining real-time speed.

cs.CV↗

arXiv2025

Can Language Models Go Beyond Coding? Assessing the Capability of Language Models to Build Real-World Systems

Large language models (LLMs) have shown growing potential in software engineering, yet few benchmarks evaluate their ability to repair software during migration across instruction set architectures (ISAs). Cross-ISA migration, such as between x86_64 and aarch64, requires handling complex dependencies, heterogeneous toolchains, and long build logs while ensuring executable verification. To address this challenge, we present Build-bench, an end-to-end benchmark that systematically evaluates the capability of LLMs to repair build failures in cross-ISA settings. Build-bench collects 268 real-world failed packages and integrates auxiliary tools including Structure Extraction, File Content Extraction, Content Modification, and Build Verification to support autonomous, tool-augmented reasoning. The repair process operates in an iterative loop where, upon failure, the model receives updated build logs and previous repair outcomes to refine subsequent attempts. Through a comparative evaluation across the studied models, Build-bench reveals that current models achieve a maximum build success rate of 63.19% and tool usage patterns differ significantly across models. By coupling real build environments with verifiable outcomes, Build-bench establishes the first architecture-aware benchmark for studying LLM-based software build and repair.

cs.SE↗

arXiv2025

Massive Memorization with Hundreds of Trillions of Parameters for Sequential Transducer Generative Recommenders

Modern large-scale recommendation systems rely heavily on user interaction history sequences to enhance the model performance. The advent of large language models and sequential modeling techniques, particularly transformer-like architectures, has led to significant advancements recently (e.g., HSTU, SIM, and TWIN models). While scaling to ultra-long user histories (10k to 100k items) generally improves model performance, it also creates significant challenges on latency, queries per second (QPS) and GPU cost in industry-scale recommendation systems. Existing models do not adequately address these industrial scalability issues. In this paper, we propose a novel two-stage modeling framework, namely VIrtual Sequential Target Attention (VISTA), which decomposes traditional target attention from a candidate item to user history items into two distinct stages: (1) user history summarization into a few hundred tokens; followed by (2) candidate item attention to those tokens. These summarization token embeddings are then cached in storage system and then utilized as sequence features for downstream model training and inference. This novel design for scalability enables VISTA to scale to lifelong user histories (up to one million items) while keeping downstream training and inference costs fixed, which is essential in industry. Our approach achieves significant improvements in offline and online metrics and has been successfully deployed on an industry leading recommendation platform serving billions of users.

cs.IR↗

arXiv2025

Flight Dynamics to Sensing Modalities: Exploiting Drone Ground Effect for Accurate Edge Detection

Drone-based rapid and accurate environmental edge detection is highly advantageous for tasks such as disaster relief and autonomous navigation. Current methods, using radars or cameras, raise deployment costs and burden lightweight drones with high computational demands. In this paper, we propose AirTouch, a system that transforms the ground effect from a stability "foe" in traditional flight control views, into a "friend" for accurate and efficient edge detection. Our key insight is that analyzing drone basic attitude sensor readings and flight commands allows us to detect ground effect changes. Such changes typically indicate the drone flying over a boundary of two materials, making this information valuable for edge detection. We approach this insight through theoretical analysis, algorithm design, and implementation, fully leveraging the ground effect as a new sensing modality without compromising drone flight stability, thereby achieving accurate and efficient scene edge detection. We also compare this new sensing modality with vision-based methods to clarify its exclusive advantages in resource efficiency and detection capability. Extensive evaluations demonstrate that our system achieves a high detection accuracy with mean detection distance errors of 0.051m, outperforming the baseline method performance by 86%. With such detection performance, our system requires only 43 mW power consumption, contributing to this new sensing modality for low-cost and highly efficient edge detection.

cs.RO↗

arXiv2025

Aerial Shepherds: Enabling Hierarchical Localization in Heterogeneous MAV Swarms

A heterogeneous micro aerial vehicles (MAV) swarm consists of resource-intensive but expensive advanced MAVs (AMAVs) and resource-limited but cost-effective basic MAVs (BMAVs), offering opportunities in diverse fields. Accurate and real-time localization is crucial for MAV swarms, but current practices lack a low-cost, high-precision, and real-time solution, especially for lightweight BMAVs. We find an opportunity to accomplish the task by transforming AMAVs into mobile localization infrastructures for BMAVs. However, translating this insight into a practical system is challenging due to issues in estimating locations with diverse and unknown localization errors of BMAVs, and allocating resources of AMAVs considering interconnected influential factors. This work introduces TransformLoc, a new framework that transforms AMAVs into mobile localization infrastructures, specifically designed for low-cost and resource-constrained BMAVs. We design an error-aware joint location estimation model to perform intermittent joint estimation for BMAVs and introduce a similarity-instructed adaptive grouping-scheduling strategy to allocate resources of AMAVs dynamically. TransformLoc achieves a collaborative, adaptive, and cost-effective localization system suitable for large-scale heterogeneous MAV swarms. We implement and validate TransformLoc on industrial drones. Results show it outperforms all baselines by up to 68\% in localization performance, improving navigation success rates by 60\%. Extensive robustness and ablation experiments further highlight the superiority of its design.

cs.NI↗

arXiv2025

Distilled Prompt Learning for Incomplete Multimodal Survival Prediction

The integration of multimodal data including pathology images and gene profiles is widely applied in precise survival prediction. Despite recent advances in multimodal survival models, collecting complete modalities for multimodal fusion still poses a significant challenge, hindering their application in clinical settings. Current approaches tackling incomplete modalities often fall short, as they typically compensate for only a limited part of the knowledge of missing modalities. To address this issue, we propose a Distilled Prompt Learning framework (DisPro) to utilize the strong robustness of Large Language Models (LLMs) to missing modalities, which employs two-stage prompting for compensation of comprehensive information for missing modalities. In the first stage, Unimodal Prompting (UniPro) distills the knowledge distribution of each modality, preparing for supplementing modality-specific knowledge of the missing modality in the subsequent stage. In the second stage, Multimodal Prompting (MultiPro) leverages available modalities as prompts for LLMs to infer the missing modality, which provides modality-common information. Simultaneously, the unimodal knowledge acquired in the first stage is injected into multimodal inference to compensate for the modality-specific knowledge of the missing modality. Extensive experiments covering various missing scenarios demonstrated the superiority of the proposed method. The code is available at https://github.com/Innse/DisPro.

cs.LG↗

arXiv2024

Multimodal Data Integration for Precision Oncology: Challenges and Future Directions

The essence of precision oncology lies in its commitment to tailor targeted treatments and care measures to each patient based on the individual characteristics of the tumor. The inherent heterogeneity of tumors necessitates gathering information from diverse data sources to provide valuable insights from various perspectives, fostering a holistic comprehension of the tumor. Over the past decade, multimodal data integration technology for precision oncology has made significant strides, showcasing remarkable progress in understanding the intricate details within heterogeneous data modalities. These strides have exhibited tremendous potential for improving clinical decision-making and model interpretation, contributing to the advancement of cancer care and treatment. Given the rapid progress that has been achieved, we provide a comprehensive overview of about 300 papers detailing cutting-edge multimodal data integration techniques in precision oncology. In addition, we conclude the primary clinical applications that have reaped significant benefits, including early assessment, diagnosis, prognosis, and biomarker discovery. Finally, derived from the findings of this survey, we present an in-depth analysis that explores the pivotal challenges and reveals essential pathways for future research in the field of multimodal data integration for precision oncology.

q-bio.QM↗