arXiv subjects

Ling Jiang

Publications and source records attributed to Ling Jiang.

16 recordsLinked to original sources

arXiv2026

Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction

We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model leaderboard. At its core is a unified evaluation framework for constructing and running distribution-informed coding-agent tasks across four work domains - Code, Web, Office, and Security. Rather than adapting public issue text, every task is reverse-engineered from a real commit, pull request, or business scenario and rewritten as a short, colloquial, role-played request, so that a task's prompt is not recoverable by web-searching the underlying issue, pull request, or commit thread. Because the dataset is released openly - task directories, environment images, evaluation harness, tests, and reference solutions - contamination resistance rests on this construction together with dataset versioning rather than on secrecy. The four subsets - repository-level engineering, front-end development, office and business workflows, and red-/blue-team security - probe complementary facets of real work, each with its own verification style. All are packaged in a uniform task-directory format and run, under a uniform and reproducible protocol, on two agent harnesses (CodeBuddy Code and Claude Code); the full open release makes the benchmark reproducible end to end and directly auditable, since any third party can re-run each task and inspect its content. Because each subset uses a different scoring instrument, scores are not comparable across subsets and the suite reports no suite-wide average. We report a cross-model leaderboard across several model families.

cs.CL↗

arXiv2026

SherAgent: Scaling Attack Investigation in the Wild via LLM-Empowered Iterative Query-Filter Backtracking

Provenance-based attack investigation enables viable automation by standardizing data and query logic; however, it is critically hindered in practice by dependency explosions and fragmented causal chains in the wild. Towards designing a robust and automated investigation tool, we collaborated with the SOC of a major Internet corporation serving billions of users. By engaging in real-world incident response, we are able to evaluate and refine their existing LLM-based investigation workflows, which processes tens of thousands of raw alerts daily, leaving thousands for manual triage, to find out the root causes of investigation failures and major challenges in their existing tools. Motivated by these findings, we propose SherAgent, an LLM-empowered automated investigation system. Operating on an iterative ``query-filter'' backtracking paradigm over provenance graphs, SherAgent leverages the semantic reasoning capabilities of LLMs to process unstructured data, such as investigation context and threat intelligence. To overcome fragmented causal chains caused by missing events, the system dynamically calibrates query conditions to broaden the search scope. Concurrently, it performs precision result filtering and strategic nodes selection for subsequent exploration, thereby mitigating dependency explosions. Extensive evaluations in the wild demonstrate that SherAgent improves the end-to-end investigation success rate by 31.1% and 63.7% compared to both legacy enterprise baselines and SOTA approaches, respectively. Furthermore, it operates with remarkable efficiency, incurring under $0.10 in API costs and requiring less than 4 minutes per investigation. Finally, our user study confirms that SherAgent provides accurate and clear insights, significantly reducing the analytical overhead for security experts.

cs.CR↗

arXiv2026

How Far Should We Need to Go : Evaluate Provenance-based Intrusion Detection Systems in Industrial Scenarios

Provenance-based Intrusion Detection Systems (PIDSes) have been widely used to detect Advanced Persistent Threats (APTs). Although many studies achieve high performance in the evaluations of their original papers, their performance in industrial scenarios remains unclear. To fill this gap, we conduct the first systematic evaluation and analysis of PIDSes in industrial scenarios. We first analyze the differences between the data from DARPA datasets and that collected in industrial scenarios, identifying three main new characteristics in industry: heterogeneous multi-source inputs, more powerful attackers, and increasing benign activity complexity. We then build several datasets to evaluate five state-of-the-art PIDSes. The evaluation results reveal challenges for existing PIDSes, including poor portability across different hosts and platforms, low detection performance against real-world attacks, and high false positive rates with ever-changing benign activities. Based on the evaluation results and our industrial practices, we provide several insights to solve or explain the above problems. For example, we propose a method to mitigate the high false positives, which reduces manual effort by 2/3. Finally, we propose several research suggestions to improve PIDSes.

cs.CR↗

arXiv2025

Xmodel-2.5: 1.3B Data-Efficient Reasoning SLM

Large language models deliver strong reasoning and tool-use skills, yet their computational demands make them impractical for edge or cost-sensitive deployments. We present \textbf{Xmodel-2.5}, a 1.3-billion-parameter small language model designed as a \emph{drop-in agent core}. Training with maximal-update parameterization ($\mu$P) allows hyper-parameters tuned on a 20M-parameter proxy to transfer directly to the full model, even under the parameter-tied \emph{tie-word-embedding} architecture. A 1.4T-token Warmup--Stable--Decay curriculum is used, and we further show that \textbf{switching from AdamW to Muon during the decay phase} improves the 13-task reasoning average by 4.58\,\% while keeping every other hyper-parameter fixed, verifying that early AdamW stability can be paired with late Muon sharpening for better downstream performance. FP8-mixed-precision training balances accuracy and throughput. All checkpoints, recipes, and evaluation code are released under the Apache-2.0 license.\footnote{https://huggingface.co/XiaoduoAILab/Xmodel-2.5 and https://huggingface.co/XiaoduoAILab/Xmodel-2.5-history (training checkpoints).} Training code and evaluation harness: https://github.com/XiaoduoAILab/Xmodel-2.5.

cs.LG↗

arXiv2025

MemOrb: A Plug-and-Play Verbal-Reinforcement Memory Layer for E-Commerce Customer Service

Large Language Model-based agents(LLM-based agents) are increasingly deployed in customer service, yet they often forget across sessions, repeat errors, and lack mechanisms for continual self-improvement. This makes them unreliable in dynamic settings where stability and consistency are critical. To better evaluate these properties, we emphasize two indicators: task success rate as a measure of overall effectiveness, and consistency metrics such as Pass$^k$ to capture reliability across multiple trials. To address the limitations of existing approaches, we propose MemOrb, a lightweight and plug-and-play verbal reinforcement memory layer that distills multi-turn interactions into compact strategy reflections. These reflections are stored in a shared memory bank and retrieved to guide decision-making, without requiring any fine-tuning. Experiments show that MemOrb significantly improves both success rate and stability, achieving up to a 63 percentage-point gain in multi-turn success rate and delivering more consistent performance across repeated trials. Our results demonstrate that structured reflection is a powerful mechanism for enhancing long-term reliability of frozen LLM agents in customer service scenarios.

cs.CL↗

arXiv2025

Survey of Specialized Large Language Model

The rapid evolution of specialized large language models (LLMs) has transitioned from simple domain adaptation to sophisticated native architectures, marking a paradigm shift in AI development. This survey systematically examines this progression across healthcare, finance, legal, and technical domains. Besides the wide use of specialized LLMs, technical breakthrough such as the emergence of domain-native designs beyond fine-tuning, growing emphasis on parameter efficiency through sparse computation and quantization, increasing integration of multimodal capabilities and so on are applied to recent LLM agent. Our analysis reveals how these innovations address fundamental limitations of general-purpose LLMs in professional applications, with specialized models consistently performance gains on domain-specific benchmarks. The survey further highlights the implications for E-Commerce field to fill gaps in the field.

cs.CL↗

arXiv2025

ECom-Bench: Can LLM Agent Resolve Real-World E-commerce Customer Support Issues?

In this paper, we introduce ECom-Bench, the first benchmark framework for evaluating LLM agent with multimodal capabilities in the e-commerce customer support domain. ECom-Bench features dynamic user simulation based on persona information collected from real e-commerce customer interactions and a realistic task dataset derived from authentic e-commerce dialogues. These tasks, covering a wide range of business scenarios, are designed to reflect real-world complexities, making ECom-Bench highly challenging. For instance, even advanced models like GPT-4o achieve only a 10-20% pass^3 metric in our benchmark, highlighting the substantial difficulties posed by complex e-commerce scenarios. The code and data have been made publicly available at https://github.com/XiaoduoAILab/ECom-Bench to facilitate further research and development in this domain.

cs.CL↗

arXiv2025

MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents

Recent advances in large language models (LLMs) have enabled new applications in e-commerce customer service. However, their capabilities remain constrained in complex, multimodal scenarios. We present MindFlow, the first open-source multimodal LLM agent tailored for e-commerce. Built on the CoALA framework, it integrates memory, decision-making, and action modules, and adopts a modular "MLLM-as-Tool" strategy for effect visual-textual reasoning. Evaluated via online A/B testing and simulation-based ablation, MindFlow demonstrates substantial gains in handling complex queries, improving user satisfaction, and reducing operational costs, with a 93.53% relative improvement observed in real-world deployments.

cs.CL↗

arXiv2024

Microwave-activated two-qubit gates for fixed-coupling and fixed-frequency transmon qubits

All-microwave control of fixed-frequency superconducting quantum systems offers the potential to reduce control circuit complexity and increase system coherence. Nevertheless, due to the limited control flexibility in qubit parameters, one has to address several issues, such as quantum crosstalk and frequency crowding, for scaling up qubit architecture with non-tunable elements. This study proposes a microwave-activated two-qubit gate scheme for two fixed-frequency transmon qubits coupled via a fixed-frequency transmon coupler. The protocol relies on applying a microwave pulse exclusively to the coupler, enabling the implementation of a controlled-Z (CZ) gate. We show that the gate fidelity exceeding 0.999 can be achieved within 150 ns, excluding decoherence effects. Moreover, we also show that leakage from the computational subspace to non-computational states can also be effectively suppressed.

quant-ph↗

arXiv2024

Xmodel-LM Technical Report

We introduce Xmodel-LM, a compact and efficient 1.1B language model pre-trained on around 2 trillion tokens. Trained on our self-built dataset (Xdata), which balances Chinese and English corpora based on downstream task optimization, Xmodel-LM exhibits remarkable performance despite its smaller size. It notably surpasses existing open-source language models of similar scale. Our model checkpoints and code are publicly accessible on GitHub at https://github.com/XiaoduoAILab/XmodelLM.

cs.CL↗

arXiv2024

Xmodel-VLM: A Simple Baseline for Multimodal Vision Language Model

We introduce Xmodel-VLM, a cutting-edge multimodal vision language model. It is designed for efficient deployment on consumer GPU servers. Our work directly confronts a pivotal industry issue by grappling with the prohibitive service costs that hinder the broad adoption of large-scale multimodal systems. Through rigorous training, we have developed a 1B-scale language model from the ground up, employing the LLaVA paradigm for modal alignment. The result, which we call Xmodel-VLM, is a lightweight yet powerful multimodal vision language model. Extensive testing across numerous classic multimodal benchmarks has revealed that despite its smaller size and faster execution, Xmodel-VLM delivers performance comparable to that of larger models. Our model checkpoints and code are publicly available on GitHub at https://github.com/XiaoduoAILab/XmodelVLM.

cs.CV↗

arXiv2024

Prompt-based Code Completion via Multi-Retrieval Augmented Generation

Automated code completion, aiming at generating subsequent tokens from unfinished code, has been significantly benefited from recent progress in pre-trained Large Language Models (LLMs). However, these models often suffer from coherence issues and hallucinations when dealing with complex code logic or extrapolating beyond their training data. Existing Retrieval Augmented Generation (RAG) techniques partially address these issues by retrieving relevant code with a separate encoding model where the retrieved snippet serves as contextual reference for code completion. However, their retrieval scope is subject to a singular perspective defined by the encoding model, which largely overlooks the complexity and diversity inherent in code semantics. To address this limitation, we propose ProCC, a code completion framework leveraging prompt engineering and the contextual multi-armed bandits algorithm to flexibly incorporate and adapt to multiple perspectives of code. ProCC first employs a prompt-based multi-retriever system which crafts prompt templates to elicit LLM knowledge to understand code semantics with multiple retrieval perspectives. Then, it adopts the adaptive retrieval selection algorithm to incorporate code similarity into the decision-making process to determine the most suitable retrieval perspective for the LLM to complete the code. Experimental results demonstrate that ProCC outperforms state-of-the-art code completion technique by 8.6% on our collected open-source benchmark suite and 10.1% on the private-domain benchmark suite collected from a billion-user e-commerce company in terms of Exact Match. ProCC also allows augmenting fine-tuned techniques in a plug-and-play manner, yielding 5.6% improvement over our studied fine-tuned model.

cs.SE↗

arXiv2024

Consecutive Detecting Arrays for Interaction Faults

The concept of detecting arrays was developed to locate and detect interaction faults arising between the factors in a component-based system during software testing. In this paper, we propose a family of consecutive detecting arrays (CDAs) in which the interactions between factors are considered to be ordered. CDAs can be used to generate test suites for locating and detecting interaction faults between neighboring factors. We establish a general criterion for measuring the optimality of CDAs in terms of their size. Based on this optimality criterion, the equivalence between optimum CDAs and consecutive orthogonal arrays with prescribed properties is explored. Using the advantages of this equivalence, a great number of optimum CDAs are presented. In particular, the existence of optimum CDAs with few factors is almost completely determined.

math.CO↗

arXiv2024

BinaryAI: Binary Software Composition Analysis via Intelligent Binary Source Code Matching

While third-party libraries are extensively reused to enhance productivity during software development, they can also introduce potential security risks such as vulnerability propagation. Software composition analysis, proposed to identify reused TPLs for reducing such risks, has become an essential procedure within modern DevSecOps. As one of the mainstream SCA techniques, binary-to-source SCA identifies the third-party source projects contained in binary files via binary source code matching, which is a major challenge in reverse engineering since binary and source code exhibit substantial disparities after compilation. The existing binary-to-source SCA techniques leverage basic syntactic features that suffer from redundancy and lack robustness in the large-scale TPL dataset, leading to inevitable false positives and compromised recall. To mitigate these limitations, we introduce BinaryAI, a novel binary-to-source SCA technique with two-phase binary source code matching to capture both syntactic and semantic code features. First, BinaryAI trains a transformer-based model to produce function-level embeddings and obtain similar source functions for each binary function accordingly. Then by applying the link-time locality to facilitate function matching, BinaryAI detects the reused TPLs based on the ratio of matched source functions. Our experimental results demonstrate the superior performance of BinaryAI in terms of binary source code matching and the downstream SCA task. Specifically, our embedding model outperforms the state-of-the-art model CodeCMR, i.e., achieving 22.54% recall@1 and 0.34 MRR compared with 10.75% and 0.17 respectively. Additionally, BinaryAI outperforms all existing binary-to-source SCA tools in TPL detection, increasing the precision from 73.36% to 85.84% and recall from 59.81% to 64.98% compared with the well-recognized commercial SCA product.

cs.SE↗

arXiv2022

Consistency of Implicit and Explicit Features Matters for Monocular 3D Object Detection

Low-cost autonomous agents including autonomous driving vehicles chiefly adopt monocular 3D object detection to perceive surrounding environment. This paper studies 3D intermediate representation methods which generate intermediate 3D features for subsequent tasks. For example, the 3D features can be taken as input for not only detection, but also end-to-end prediction and/or planning that require a bird's-eye-view feature representation. In the study, we found that in generating 3D representation previous methods do not maintain the consistency between the objects' implicit poses in the latent space, especially orientations, and the explicitly observed poses in the Euclidean space, which can substantially hurt model performance. To tackle this problem, we present a novel monocular detection method, the first one being aware of the poses to purposefully guarantee that they are consistent between the implicit and explicit features. Additionally, we introduce a local ray attention mechanism to efficiently transform image features to voxels at accurate 3D locations. Thirdly, we propose a handcrafted Gaussian positional encoding function, which outperforms the sinusoidal encoding function while retaining the benefit of being continuous. Results show that our method improves the state-of-the-art 3D intermediate representation method by 3.15%. We are ranked 1st among all the reported monocular methods on both 3D and BEV detection benchmark on KITTI leaderboard as of th result's submission time.

cs.CV↗

arXiv2019

A Multi-Scale Mapping Approach Based on a Deep Learning CNN Model for Reconstructing High-Resolution Urban DEMs

The shortage of high-resolution urban digital elevation model (DEM) datasets has been a challenge for modelling urban flood and managing its risk. A solution is to develop effective approaches to reconstruct high-resolution DEMs from their low-resolution equivalents that are more widely available. However, the current high-resolution DEM reconstruction approaches mainly focus on natural topography. Few attempts have been made for urban topography which is typically an integration of complex man-made and natural features. This study proposes a novel multi-scale mapping approach based on convolutional neural network (CNN) to deal with the complex characteristics of urban topography and reconstruct high-resolution urban DEMs. The proposed multi-scale CNN model is firstly trained using urban DEMs that contain topographic features at different resolutions, and then used to reconstruct the urban DEM at a specified (high) resolution from a low-resolution equivalent. A two-level accuracy assessment approach is also designed to evaluate the performance of the proposed urban DEM reconstruction method, in terms of numerical accuracy and morphological accuracy. The proposed DEM reconstruction approach is applied to a 121 km2 urbanized area in London, UK. Compared with other commonly used methods, the current CNN based approach produces superior results, providing a cost-effective innovative method to acquire high-resolution DEMs in other data-scarce environments.

cs.CV↗