arXiv subjects

Yuheng Huang

Publications and source records attributed to Yuheng Huang.

At least 19 recordsLinked to original sources

arXiv2026

Ouroboros: Self-Referential Backdoor Attacks on Speech Enhancement via Clean Audio Triggers

Speech enhancement models are widely deployed as frontend modules in real-time speech services, yet their vulnerability to backdoor attacks remains unexplored. Existing backdoor methods are confined to classification tasks and rely on active trigger injection, an assumption incompatible with the passive processing nature of speech enhancement models. In this paper, we propose Ouroboros, a novel backdoor attack framework that leverages the ideal clean outputs of speech enhancement models as natural triggers, enabling inference-time activation without any external trigger injection. Extensive evaluations show Ouroboros achieves near-perfect attack success rates with minimal performance degradation on diverse models and datasets. Physical-world validations confirm that naturally recorded, unaltered clean audio can reliably activate the backdoor. Moreover, Ouroboros generalizes to targeted content-tampering attacks and remains effective against common filtering and finetuning defenses.

cs.SD↗

arXiv2026

ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research

Open-ended deep research (OEDR) requires systems to acquire knowledge through multi-round retrieval and generate coherent long-form reports. The outline plays a central role as a structural scaffold that coordinates retrieval, evidence organization, and generation. However, existing methods either fix the outline before writing or refine it with local heuristics, leading to scaffold drift under continuous information accumulation and delayed feedback for evaluating outline modifications. We propose ScaffoldAgent, a utility-guided dynamic outline optimization framework for OEDR. ScaffoldAgent models outline evolution as a structured decision process with three operations: Expansion, Contraction, and Revision, enabling controlled updates to the report scaffold. It further introduces a utility-guided feedback mechanism that estimates the downstream value of each outline operation from retrieval gain, structural coherence, and trial-generation quality. The resulting utility signal guides node selection, operation scheduling, and termination during inference. Experiments on DeepResearch Bench and DeepResearch Gym show that ScaffoldAgent consistently improves long-form report generation and factual grounding over existing deep research agents.

cs.AI↗

arXiv2026

AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing

Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs), yet existing RAG systems often struggle with complex, multi-step reasoning that requires adaptive retrieval and continuous revision of intermediate contexts. Recent reinforcement learning (RL)-based agentic RAG methods partially alleviate this issue, but typically rely on coarse-grained action spaces and trajectory-level rewards, resulting in weak reward assignment and a bias toward short-horizon, stereotyped reasoning template. To address, we propose AgenticRag-R1, a RL framework that deeply integrates reasoning, retrieval, and memory via a memory stack and fine-grained action space, supported by hierarchical action-aware rewards and an information-aware trajectory rejection strategy to enable effective long-horizon learning. Experiments across a diverse set of multi-hop, open-domain, and agentic reasoning benchmarks, spanning multiple backbone model sizes, demonstrate that AgenticRag-R1 consistently outperforms strong baselines. Moreover, AgenticRag-R1 learns more robust, interpretable, and memory-aware reasoning behaviors, highlighting the effect of fine-grained action modeling and information-aware optimization for long-horizon reasoning. Our code is anonymous available at https://github.com/jiangxinke/Harness-RL/tree/AgenticRAG-R1-Whitebox.

cs.MA↗

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

CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systems

Despite the remarkable success that Multi-Agent Code Generation Systems (MACGS) have achieved, the inherent complexity of multi-agent architectures produces substantial volumes of intermediate outputs. To date, the individual importance of these intermediate outputs to the system correctness remains opaque, which impedes targeted optimization of MACGS designs. To address this challenge, we propose CAM, the first \textbf{C}ausality-based \textbf{A}nalysis framework for \textbf{M}ACGS that systematically quantifies the contribution of different intermediate features for system correctness. By comprehensively categorizing intermediate outputs and systematically simulating realistic errors on intermediate features, we identify the important features for system correctness and aggregate their importance rankings. We conduct extensive empirical analysis on the identified importance rankings. Our analysis reveals intriguing findings: first, we uncover context-dependent features\textemdash features whose importance emerges mainly through interactions with other features, revealing that quality assurance for MACGS should incorporate cross-feature consistency checks; second, we reveal that hybrid backend MACGS with different backend LLMs assigned according to their relative strength achieves up to 7.3\% Pass@1 improvement, underscoring hybrid architectures as a promising direction for future MACGS design. We further demonstrate CAM's practical utility through two applications: (1) failure repair which achieves a 73.6\% success rate by optimizing top-3 importance-ranked features and (2) feature pruning that reduces up to 33.6\% intermediate token consumption while maintaining generation performance. Our work provides actionable insights for MACGS design and deployment, establishing causality analysis as a powerful approach for understanding and improving MACGS.

cs.SE↗

arXiv2026

Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs

As Code Large Language Models (LLMs) become central to modern software engineering, their inherent stochasticity poses significant real-world risks, where even minor errors can lead to severe functional, security, or safety consequences. Reliable automation, therefore, demands the ability to distinguish between confident, well-supported predictions and stochastic guessing. However, existing uncertainty estimation methods face a critical gap: white and grey-box techniques are often inapplicable to closed-source models, while standard "black-box" text metrics fail to capture the unique fragility of code, where syntactic variation does not always imply semantic divergence. To bridge this syntax-semantics gap, we introduce Code-MUE, a purely black-box framework that measures uncertainty through execution-based Semantic Interaction Graphs. Different from prior approaches that rely on superficial textual similarity, Code-MUE grounds uncertainty in observable runtime behavior, calculating the Von Neumann entropy of the solution space to quantify global semantic diversity. A large-scale empirical study across eight state-of-the-art LLMs demonstrates that Code-MUE achieves a strong negative correlation with functional correctness (Spearman's correlation up to -0.98), significantly outperforming lexical and embedding-based baselines while enabling robust risk detection and selective prediction in practical workflows.

cs.SE↗

arXiv2026

Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systems

Retrieval-Augmented Generation (RAG) has emerged as a critical technique for enhancing large language model (LLM) capabilities. However, practitioners face significant challenges when making RAG deployment decisions. While existing research prioritizes algorithmic innovations, a systematic gap persists in understanding fundamental engineering trade-offs that determine RAG success. We present the first comprehensive study of three universal RAG deployment decisions: whether to deploy RAG, how much information to retrieve, and how to integrate retrieved knowledge effectively. Through systematic experiments across three LLMs and six datasets spanning question answering and code generation tasks, we reveal critical insights: (1) RAG deployment must be highly selective, with variable recall thresholds and failure modes affecting up to 12.6\% of samples even with perfect documents. (2) Optimal retrieval volume exhibits task-dependent behavior QA tasks show universal patterns (5-10 documents optimal) while code generation requires scenario-specific optimization. (3) Knowledge integration effectiveness depends on task and model characteristics, with code generation benefiting significantly from prompting methods while question answering shows minimal improvement. These findings demonstrate that universal RAG strategies prove inadequate. Effective RAG systems require context-aware design decisions based on task characteristics and model capabilities. Our analysis provides evidence-based guidance for practitioners and establishes foundational insights for principled RAG deployment. Our code, data and artifacts are publicly available at https://github.com/ShengmingZ/RAG_Benchmark_Code_QA.

cs.SE↗

arXiv2026

Muse Spark Safety & Preparedness Report

Muse Spark is the latest large language model developed by Meta. In this report, we first present evaluations for catastrophic risk domains under Meta's Advanced AI Scaling Framework, along with the evidence that informed our launch decision. We then discuss additional considerations, such as Muse Spark's broader content safety and behavioral profile, that are relevant to overall safety but fall outside the catastrophic risk domains governed by the Framework. Our preparedness results covering Chemical and Biological, Cybersecurity, and Loss of Control risks assess Muse Spark's deployment within Meta AI as presenting acceptable levels of residual risks under our Advanced AI Scaling Framework. We conducted a broad set of evaluations targeting dual-use and high-risk capabilities across these catastrophic risk domains. Those evaluations identified elevated risks prior to mitigations, with Chemical and Biological capabilities assessed as likely reaching the "high risk" category under the Advanced AI Scaling Framework before safeguards were applied. We have implemented a multi-layered set of mitigations that address the identified risks, and Muse Spark demonstrates state-of-the-art refusal across a range of benchmarks related to hazardous workflows in chemistry and biology. We therefore release Muse Spark as the underlying model of Meta AI.

cs.CY↗

arXiv2026

Foundation Models for Autonomous Driving System: An Initial Roadmap

Recent advances in foundation models (FMs), including large language models (LLMs), vision-language models (VLMs), and world models, have opened new opportunities for autonomous driving systems (ADSs) in perception, reasoning, decision-making, and interaction. However, ADSs are safety-critical cyber-physical systems, and integrating FMs into them raises substantial software engineering challenges in data curation, system design, deployment, evaluation, and assurance. To clarify this rapidly evolving landscape, we present an initial roadmap, grounded in a structured literature review, for integrating FMs into autonomous driving across three dimensions: FM infrastructure, in-vehicle integration, and practical deployment. For each dimension, we summarize the state of the art, identify key challenges, and highlight open research opportunities. Based on this analysis, we outline research directions for building reliable, safe, and trustworthy FM-enabled ADSs.

cs.SE↗

arXiv2026

Evaluating Implicit Regulatory Compliance in LLM Tool Invocation via Logic-Guided Synthesis

The integration of large language models (LLMs) into autonomous agents has enabled complex tool use, yet in high-stakes domains, these systems must strictly adhere to regulatory standards beyond simple functional correctness. However, existing benchmarks often overlook implicit regulatory compliance, thus failing to evaluate whether LLMs can autonomously enforce mandatory safety constraints. To fill this gap, we introduce LogiSafetyGen, a framework that converts unstructured regulations into Linear Temporal Logic oracles and employs logic-guided fuzzing to synthesize valid, safety-critical traces. Building on this framework, we construct LogiSafetyBench, a benchmark comprising 240 human-verified tasks that require LLMs to generate Python programs that satisfy both functional objectives and latent compliance rules. Evaluations of 13 state-of-the-art (SOTA) LLMs reveal that larger models, despite achieving better functional correctness, frequently prioritize task completion over safety, which results in non-compliant behavior.

cs.CL↗

arXiv2025

Evaluating LLMs on Sequential API Call Through Automated Test Generation

By integrating tools from external APIs, Large Language Models (LLMs) have expanded their promising capabilities in a diverse spectrum of complex real-world tasks. However, testing, evaluation, and analysis of LLM tool use remain in their early stages. Most existing benchmarks rely on manually collected test cases, many of which cannot be automatically checked for semantic correctness and instead depend on static methods such as string matching. Additionally, these benchmarks often overlook the complex interactions that occur between sequential API calls, which are common in real-world applications. To fill the gap, in this paper, we introduce StateGen, an automated framework designed to generate diverse coding tasks involving sequential API interactions. StateGen combines state-machine-based API constraint solving and validation, energy-based sampling, and control-flow injection to generate executable programs. These programs are then translated into human-like natural language task descriptions through a collaboration of two LLM agents. Utilizing StateGen, we construct StateEval, a benchmark encompassing 120 verified test cases spanning across three representative scenarios: Session Service, Tensor Operation, and ElevenLabs MCP. Experimental results confirm that StateGen can effectively generate challenging and realistic API-oriented tasks, highlighting areas for improvement in current LLMs incorporating APIs.We make our framework and benchmark publicly available to support future research.

cs.SE↗

arXiv2025

TRUSTVIS: A Multi-Dimensional Trustworthiness Evaluation Framework for Large Language Models

As Large Language Models (LLMs) continue to revolutionize Natural Language Processing (NLP) applications, critical concerns about their trustworthiness persist, particularly in safety and robustness. To address these challenges, we introduce TRUSTVIS, an automated evaluation framework that provides a comprehensive assessment of LLM trustworthiness. A key feature of our framework is its interactive user interface, designed to offer intuitive visualizations of trustworthiness metrics. By integrating well-known perturbation methods like AutoDAN and employing majority voting across various evaluation methods, TRUSTVIS not only provides reliable results but also makes complex evaluation processes accessible to users. Preliminary case studies on models like Vicuna-7b, Llama2-7b, and GPT-3.5 demonstrate the effectiveness of our framework in identifying safety and robustness vulnerabilities, while the interactive interface allows users to explore results in detail, empowering targeted model improvements. Video Link: https://youtu.be/k1TrBqNVg8g

cs.SE↗

arXiv2025

RecIS: Sparse to Dense, A Unified Training Framework for Recommendation Models

In this paper, we propose RecIS, a unified Sparse-Dense training framework designed to achieve two primary goals: 1. Unified Framework To create a Unified sparse-dense training framework based on the PyTorch ecosystem that meets the training needs of industrial-grade recommendation models that integrated with large models. 2.System Optimization To optimize the sparse component, offering superior efficiency over the TensorFlow-based recommendation models. The dense component, meanwhile, leverages existing optimization technologies within the PyTorch ecosystem. Currently, RecIS is being used in Alibaba for numerous large-model enhanced recommendation training tasks, and some traditional sparse models have also begun training in it.

cs.IR↗

arXiv2025

End4: End-to-end Denoising Diffusion for Diffusion-Based Inpainting Detection

The powerful generative capabilities of diffusion models have significantly advanced the field of image synthesis, enhancing both full image generation and inpainting-based image editing. Despite their remarkable advancements, diffusion models also raise concerns about potential misuse for malicious purposes. However, existing approaches struggle to identify images generated by diffusion-based inpainting models, even when similar inpainted images are included in their training data. To address this challenge, we propose a novel detection method based on End-to-end denoising diffusion (End4). Specifically, End4 designs a denoising reconstruction model to improve the alignment degree between the latent spaces of the reconstruction and detection processes, thus reconstructing features that are more conducive to detection. Meanwhile, it leverages a Scale-aware Pyramid-like Fusion Module (SPFM) that refines local image features under the guidance of attention pyramid layers at different scales, enhancing feature discriminability. Additionally, to evaluate detection performance on inpainted images, we establish a comprehensive benchmark comprising images generated from five distinct masked regions. Extensive experiments demonstrate that our End4 effectively generalizes to unseen masking patterns and remains robust under various perturbations. Our code and dataset will be released soon.

cs.CV↗

arXiv2025

AcTracer: Active Testing of Large Language Model via Multi-Stage Sampling

Performance evaluation plays a crucial role in the development life cycle of large language models (LLMs). It estimates the model's capability, elucidates behavior characteristics, and facilitates the identification of potential issues and limitations, thereby guiding further improvement. Given that LLMs' diverse task-handling abilities stem from large volumes of training data, a comprehensive evaluation also necessitates abundant, well-annotated, and representative test data to assess LLM performance across various downstream tasks. However, the demand for high-quality test data often entails substantial time, computational resources, and manual efforts, sometimes causing the evaluation to be inefficient or impractical. To address these challenges, researchers propose active testing, which estimates the overall performance by selecting a subset of test data. Nevertheless, the existing active testing methods tend to be inefficient, even inapplicable, given the unique new challenges of LLMs (e.g., diverse task types, increased model complexity, and unavailability of training data). To mitigate such limitations and expedite the development cycle of LLMs, in this work, we introduce AcTracer, an active testing framework tailored for LLMs that strategically selects a small subset of test data to achieve a more accurate performance estimation for LLMs. AcTracer utilizes both internal and external information from LLMs to guide the test sampling process, reducing variance through a multi-stage pool-based active selection. Our experiment results demonstrate that AcTracer achieves state-of-the-art performance compared to existing methods across various tasks.

cs.SE↗

arXiv2025

VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation

The rapid advancement of generative AI and multi-modal foundation models has shown significant potential in advancing robotic manipulation. Vision-language-action (VLA) models, in particular, have emerged as a promising approach for visuomotor control by leveraging large-scale vision-language data and robot demonstrations. However, current VLA models are typically evaluated using a limited set of hand-crafted scenes, leaving their general performance and robustness in diverse scenarios largely unexplored. To address this gap, we present VLATest, a fuzzing framework designed to generate robotic manipulation scenes for testing VLA models. Based on VLATest, we conducted an empirical study to assess the performance of seven representative VLA models. Our study results revealed that current VLA models lack the robustness necessary for practical deployment. Additionally, we investigated the impact of various factors, including the number of confounding objects, lighting conditions, camera poses, unseen objects, and task instruction mutations, on the VLA model's performance. Our findings highlight the limitations of existing VLA models, emphasizing the need for further research to develop reliable and trustworthy VLA applications.

cs.SE↗

arXiv2025

Risk Assessment Framework for Code LLMs via Leveraging Internal States

The pre-training paradigm plays a key role in the success of Large Language Models (LLMs), which have been recognized as one of the most significant advancements of AI recently. Building on these breakthroughs, code LLMs with advanced coding capabilities bring huge impacts on software engineering, showing the tendency to become an essential part of developers' daily routines. However, the current code LLMs still face serious challenges related to trustworthiness, as they can generate incorrect, insecure, or unreliable code. Recent exploratory studies find that it can be promising to detect such risky outputs by analyzing LLMs' internal states, akin to how the human brain unconsciously recognizes its own mistakes. Yet, most of these approaches are limited to narrow sub-domains of LLM operations and fall short of achieving industry-level scalability and practicability. To address these challenges, in this paper, we propose PtTrust, a two-stage risk assessment framework for code LLM based on internal state pre-training, designed to integrate seamlessly with the existing infrastructure of software companies. The core idea is that the risk assessment framework could also undergo a pre-training process similar to LLMs. Specifically, PtTrust first performs unsupervised pre-training on large-scale unlabeled source code to learn general representations of LLM states. Then, it uses a small, labeled dataset to train a risk predictor. We demonstrate the effectiveness of PtTrust through fine-grained, code line-level risk assessment and demonstrate that it generalizes across tasks and different programming languages. Further experiments also reveal that PtTrust provides highly intuitive and interpretable features, fostering greater user trust. We believe PtTrust makes a promising step toward scalable and trustworthy assurance for code LLMs.

cs.SE↗

arXiv2025

Towards Understanding the Characteristics of Code Generation Errors Made by Large Language Models

Large Language Models (LLMs) have demonstrated unprecedented capabilities in code generation. However, there remains a limited understanding of code generation errors that LLMs can produce. To bridge the gap, we conducted an in-depth analysis of code generation errors across six representative LLMs on the HumanEval dataset. Specifically, we first employed open coding and thematic analysis to distill a comprehensive taxonomy of code generation errors. We analyzed two dimensions of error characteristics -- semantic characteristics and syntactic characteristics. Our analysis revealed that LLMs often made non-trivial, multi-line code generation errors in various locations and with various root causes. We further analyzed the correlation between these errors and task complexity as well as test pass rate. Our findings highlighted several challenges in locating and fixing code generation errors made by LLMs. In the end, we discussed several future directions to address these challenges.

cs.SE↗