arXiv subjects

Chengcheng Wan

Publications and source records attributed to Chengcheng Wan.

36 records · Page 2Linked to original sources

arXiv2026

LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Services

Recent advances in large reasoning models LRMs have enabled agentic search systems to perform complex multi-step reasoning across multiple sources. However, most studies focus on general information retrieval and rarely explores vertical domains with unique challenges. In this work, we focus on local life services and introduce LocalSearchBench, which encompass diverse and complex business scenarios. Real-world queries in this domain are often ambiguous and require multi-hop reasoning across merchants and products, remaining challenging and not fully addressed. As the first comprehensive benchmark for agentic search in local life services, LocalSearchBench comprises a database of over 1.3M merchant entries across 6 service categories and 9 major cities, and 900 multi-hop QA tasks from real user queries that require multi-step reasoning. We also developed LocalPlayground, a unified environment integrating multiple tools for LRMs interaction. Experiments show that even state-of-the-art LRMs struggle on LocalSearchBench: the best model (DeepSeek-V3.2) achieves only 35.60% correctness, and most models have issues with completeness (average 60.32%) and faithfulness (average 30.72%). This highlights the need for specialized benchmarks and domain-specific agent training in local life services. Code, Benchmark, and Leaderboard are available at https://localsearchbench.github.io/.

cs.AI↗

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

Improving Random Testing via LLM-powered UI Tarpit Escaping for Mobile Apps

Random GUI testing is a widely-used technique for testing mobile apps. However, its effectiveness is limited by the notorious issue -- UI exploration tarpits, where the exploration is trapped in local UI regions, thus impeding test coverage and bug discovery. In this experience paper, we introduce LLM-powered random GUI Testing, a novel hybrid testing approach to mitigating UI tarpits during random testing. Our approach monitors UI similarity to identify tarpits and query LLMs to suggest promising events for escaping the encountered tarpits. We implement our approach on top of two different automated input generation (AIG) tools for mobile apps: (1) HybridMonkey upon Monkey, a state-of-the-practice tool; and (2) HybridDroidbot upon Droidbot, a state-of-the-art tool. We evaluated them on 12 popular, real-world apps. The results show that HybridMonkey and HybridDroidbot outperform all baselines, achieving average coverage improvements of 54.8% and 44.8%, respectively, and detecting the highest number of unique crashes. In total, we found 75 unique bugs, including 34 previously unknown bugs. To date, 26 bugs have been confirmed and fixed. We also applied HybridMonkey on WeChat, a popular industrial app with billions of monthly active users. HybridMonkey achieved higher activity coverage and found more bugs than random testing.

cs.SE↗

arXiv2026

FLARE: Agentic Coverage-Guided Fuzzing for LLM-Based Multi-Agent Systems

Multi-Agent LLM Systems (MAS) have been adopted to automate complex human workflows by breaking down tasks into subtasks. However, due to the non-deterministic behavior of LLM agents and the intricate interactions between agents, MAS applications frequently encounter failures, including infinite loops and failed tool invocations. Traditional software testing techniques are ineffective in detecting such failures due to the lack of LLM agent specification, the large behavioral space of MAS, and semantic-based correctness judgment. This paper presents FLARE, a novel testing framework tailored for MAS. FLARE takes the source code of MAS as input and extracts specifications and behavioral spaces from agent definitions. Based on these specifications, FLARE builds test oracles and conducts coverage-guided fuzzing to expose failures. It then analyzes execution logs to judge whether each test has passed and generates failure reports. Our evaluation on 16 diverse open-source applications demonstrates that FLARE achieves 96.9% inter-agent coverage and 91.1% intra-agent coverage, outperforming baselines by 9.5% and 1.0%. FLARE also uncovers 56 previously unknown failures unique to MAS.

cs.SE↗

arXiv2026

EffiSkill: Agent Skill Based Automated Code Efficiency Optimization

Code efficiency is a fundamental aspect of software quality, yet how to harness large language models (LLMs) to optimize programs remains challenging. Prior approaches have sought for one-shot rewriting, retrieved exemplars, or prompt-based search, but they do not explicitly distill reusable optimization knowledge, which limits generalization beyond individual instances. In this paper, we present EffiSkill, a framework for code-efficiency optimization that builds a portable optimization toolbox for LLM-based agents. The key idea is to model recurring slow-to-fast transformations as reusable agent skills that capture both concrete transformation mechanisms and higher-level optimization strategies. EffiSkill adopts a two-stage design: Stage I mines Operator and Meta Skills from large-scale slow/fast program pairs to build a skill library; Stage II applies this library to unseen programs through execution-free diagnosis, skill retrieval, plan composition, and candidate generation, without runtime feedback. Results on EffiBench-X show that EffiSkill achieves higher optimization success rates, improving over the strongest baseline by 3.69 to 12.52 percentage points across model and language settings. These findings suggest that mechanism-level skill reuse provides a useful foundation for execution-free code optimization, and that the resulting skill library can serve as a reusable resource for broader agent workflows.

cs.SE↗

arXiv2026

Pruning the Unsurprising: Efficient LLM Reasoning via First-Token Surprisal

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities by scaling up the length of Chain-of-Thought (CoT). However, excessively long reasoning traces pose substantial challenges for training cost and inference latency. While various CoT compression approaches have emerged to address this challenge, they face inherent trade-offs: token-level methods often disrupt syntactic and logical coherence, while step-level methods based on perplexity fail to reliably capture the logically critical reasoning steps because of the dilution of logical information. In this paper, we propose ASAP (Anchor-guided, SurprisAl-based Pruning), a novel coarse-to-fine framework for CoT compression. ASAP first performs anchor-guided pruning to preserve the core reasoning structure, which efficiently reduces the search space for subsequent processing. Leveraging the insight that logical branching choices are concentrated at the onset of reasoning steps, it then enables logic-aware pruning by selecting logically essential reasoning steps based on a novel first-token surprisal metric. Finally, ASAP distills the models to autonomously generate and leverage these concise CoTs at inference time, enabling efficient reasoning. Experiments show that ASAP achieves state-of-the-art accuracy across multiple benchmarks while substantially reducing training and inference costs.

cs.LG↗

arXiv2025

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

While large language models have made significant strides in code generation, the pass rate of the generated code is bottlenecked on subtle errors, often requiring human intervention to pass tests, especially for complex problems. Existing LLM-based debugging systems treat generated programs as monolithic units, failing to address bugs at multiple levels of granularity, from low-level syntax errors to high-level algorithmic flaws. In this paper, we introduce Multi-Granularity Debugger (MGDebugger), a hierarchical code debugger by isolating, identifying, and resolving bugs at various levels of granularity. MGDebugger decomposes problematic code into a hierarchical tree structure of subfunctions, with each level representing a particular granularity of error. During debugging, it analyzes each subfunction and iteratively resolves bugs in a bottom-up manner. To effectively test each subfunction, we propose an LLM-simulated Python executor, which traces code execution and tracks important variable states to pinpoint errors accurately. Extensive experiments demonstrate that MGDebugger outperforms existing debugging systems, achieving an 18.9% improvement in accuracy over seed generations in HumanEval and a 97.6% repair success rate in HumanEvalFix. Furthermore, MGDebugger effectively fixes bugs across different categories and difficulty levels, demonstrating its robustness and effectiveness.

cs.CL↗

arXiv2025

Automated detection of atomicity violations in large-scale systems

Atomicity violations in interrupt-driven programs pose a significant threat to software reliability in safety-critical systems. These violations occur when the execution sequence of operations on shared resources is disrupted by asynchronous interrupts. Detecting atomicity violations is challenging due to the vast program state space, application-level code dependencies, and complex domain-specific knowledge. In this paper, we propose CLOVER, a multi-agent framework for detecting atomicity violations in real-world interrupt-driven programs. Its plan agent orchestrates four static analysis tools to extract key information and generate code summaries. CLOVER then initializes several Expert-Judge agent pairs to detect and validate different patterns of atomicity violation, through an iterative manner. Evaluations on RaceBench, SV-COMP, and RWIP demonstrate that CLOVER achieves a precision/recall of 91.0%/96.4%, outperforming existing approaches by 33.0-117.2% on F1-score. Additionally, it identifies 12 atomicity violations in 11 real-world aerospace software projects, one of which is previously unknown.

cs.SE↗

arXiv2025

On the Effectiveness of Large Language Models in Domain-Specific Code Generation

Large language models (LLMs) such as ChatGPT have shown remarkable capabilities in code generation. Despite significant achievements, they rely on enormous training data to acquire a broad spectrum of open-domain knowledge. Besides, their evaluation revolves around open-domain benchmarks like HumanEval, which primarily consist of programming contests. Therefore, it is hard to fully characterize the intricacies and challenges associated with particular domains (e.g., web, game, and math). In this paper, we conduct an in-depth study of the LLMs in domain-specific code generation. Our results demonstrate that LLMs exhibit sub-optimal performance in generating domain-specific code, due to their limited proficiency in utilizing domain-specific libraries. We further observe that incorporating API knowledge as prompts can empower LLMs to generate more professional code. Based on these findings, we further investigate how to effectively incorporate API knowledge into the code generation process. We experiment with three strategies for incorporating domain knowledge, namely, external knowledge inquirer, chain-of-thought prompting, and chain-of-thought fine-tuning. We refer to these strategies as a new code generation approach called DomCoder. Experimental results show that all strategies of DomCoder lead to improvement in the effectiveness of domain-specific code generation under certain settings.

cs.SE↗

arXiv2025

Are LLMs Correctly Integrated into Software Systems?

Large language models (LLMs) provide effective solutions in various application scenarios, with the support of retrieval-augmented generation (RAG). However, developers face challenges in integrating LLM and RAG into software systems, due to lacking interface specifications, various requirements from software context, and complicated system management. In this paper, we have conducted a comprehensive study of 100 open-source applications that incorporate LLMs with RAG support, and identified 18 defect patterns. Our study reveals that 77% of these applications contain more than three types of integration defects that degrade software functionality, efficiency, and security. Guided by our study, we propose systematic guidelines for resolving these defects in software life cycle. We also construct an open-source defect library Hydrangea.

cs.SE↗

arXiv2024

CodeCipher: Learning to Obfuscate Source Code Against LLMs

While large code language models have made significant strides in AI-assisted coding tasks, there are growing concerns about privacy challenges. The user code is transparent to the cloud LLM service provider, inducing risks of unauthorized training, reading, and execution of the user code. In this paper, we propose CodeCipher, a novel method that perturbs privacy from code while preserving the original response from LLMs. CodeCipher transforms the LLM's embedding matrix so that each row corresponds to a different word in the original matrix, forming a token-to-token confusion mapping for obfuscating source code. The new embedding matrix is optimized by minimizing the task-specific loss function. To tackle the challenge of the discrete and sparse nature of word vector spaces, CodeCipher adopts a discrete optimization strategy that aligns the updated vector to the nearest valid token in the vocabulary before each gradient update. We demonstrate the effectiveness of our approach on three AI-assisted coding tasks including code completion, summarization, and translation. Results show that our model successfully confuses the privacy in source code while preserving the original LLM's performance.

cs.CL↗

arXiv2024

BinPRE: Enhancing Field Inference in Binary Analysis Based Protocol Reverse Engineering

Protocol reverse engineering (PRE) aims to infer the specification of network protocols when the source code is not available. Specifically, field inference is one crucial step in PRE to infer the field formats and semantics. To perform field inference, binary analysis based PRE techniques are one major approach category. However, such techniques face two key challenges - (1) the format inference is fragile when the logics of processing input messages may vary among different protocol implementations, and (2) the semantic inference is limited by inadequate and inaccurate inference rules. To tackle these challenges, we present BinPRE, a binary analysis based PRE tool. BinPRE incorporates (1) an instruction-based semantic similarity analysis strategy for format extraction; (2) a novel library composed of atomic semantic detectors for improving semantic inference adequacy; and (3) a cluster-and-refine paradigm to further improve semantic inference accuracy. We have evaluated BinPRE against five existing PRE tools, including Polyglot, AutoFormat, Tupni, BinaryInferno and DynPRE. The evaluation results on eight widely-used protocols show that BinPRE outperforms the prior PRE tools in both format and semantic inference. BinPRE achieves the perfection of 0.73 on format extraction and the F1-score of 0.74 (0.81) on semantic inference of types (functions), respectively. The field inference results of BinPRE have helped improve the effectiveness of protocol fuzzing by achieving 5-29% higher branch coverage, compared to those of the best prior PRE tool. BinPRE has also helped discover one new zero-day vulnerability, which otherwise cannot be found.

cs.SE↗

arXiv2024

Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers

Large language models have catalyzed an unprecedented wave in code generation. While achieving significant advances, they blur the distinctions between machine- and human-authored source code, causing integrity and authenticity issues of software artifacts. Previous methods such as DetectGPT have proven effective in discerning machine-generated texts, but they do not identify and harness the unique patterns of machine-generated code. Thus, its applicability falters when applied to code. In this paper, we carefully study the specific patterns that characterize machine- and human-authored code. Through a rigorous analysis of code attributes such as lexical diversity, conciseness, and naturalness, we expose unique patterns inherent to each source. We particularly notice that the syntactic segmentation of code is a critical factor in identifying its provenance. Based on our findings, we propose DetectCodeGPT, a novel method for detecting machine-generated code, which improves DetectGPT by capturing the distinct stylized patterns of code. Diverging from conventional techniques that depend on external LLMs for perturbations, DetectCodeGPT perturbs the code corpus by strategically inserting spaces and newlines, ensuring both efficacy and efficiency. Experiment results show that our approach significantly outperforms state-of-the-art techniques in detecting machine-generated code.

cs.SE↗

arXiv2023

Automatic and Efficient Customization of Neural Networks for ML Applications

ML APIs have greatly relieved application developers of the burden to design and train their own neural network models -- classifying objects in an image can now be as simple as one line of Python code to call an API. However, these APIs offer the same pre-trained models regardless of how their output is used by different applications. This can be suboptimal as not all ML inference errors can cause application failures, and the distinction between inference errors that can or cannot cause failures varies greatly across applications. To tackle this problem, we first study 77 real-world applications, which collectively use six ML APIs from two providers, to reveal common patterns of how ML API output affects applications' decision processes. Inspired by the findings, we propose ChameleonAPI, an optimization framework for ML APIs, which takes effect without changing the application source code. ChameleonAPI provides application developers with a parser that automatically analyzes the application to produce an abstract of its decision process, which is then used to devise an application-specific loss function that only penalizes API output errors critical to the application. ChameleonAPI uses the loss function to efficiently train a neural network model customized for each application and deploys it to serve API invocations from the respective application via existing interface. Compared to a baseline that selects the best-of-all commercial ML API, we show that ChameleonAPI reduces incorrect application decisions by 43%.

cs.SE↗

arXiv2023

Self-Supervised Query Reformulation for Code Search

Automatic query reformulation is a widely utilized technology for enriching user requirements and enhancing the outcomes of code search. It can be conceptualized as a machine translation task, wherein the objective is to rephrase a given query into a more comprehensive alternative. While showing promising results, training such a model typically requires a large parallel corpus of query pairs (i.e., the original query and a reformulated query) that are confidential and unpublished by online code search engines. This restricts its practicality in software development processes. In this paper, we propose SSQR, a self-supervised query reformulation method that does not rely on any parallel query corpus. Inspired by pre-trained models, SSQR treats query reformulation as a masked language modeling task conducted on an extensive unannotated corpus of queries. SSQR extends T5 (a sequence-to-sequence model based on Transformer) with a new pre-training objective named corrupted query completion (CQC), which randomly masks words within a complete query and trains T5 to predict the masked content. Subsequently, for a given query to be reformulated, SSQR identifies potential locations for expansion and leverages the pre-trained T5 model to generate appropriate content to fill these gaps. The selection of expansions is then based on the information gain associated with each candidate. Evaluation results demonstrate that SSQR outperforms unsupervised baselines significantly and achieves competitive performance compared to supervised methods.

cs.SE↗

arXiv2022

Doppler: Automated SKU Recommendation in Migrating SQL Workloads to the Cloud

Selecting the optimal cloud target to migrate SQL estates from on-premises to the cloud remains a challenge. Current solutions are not only time-consuming and error-prone, requiring significant user input, but also fail to provide appropriate recommendations. We present Doppler, a scalable recommendation engine that provides right-sized Azure SQL Platform-as-a-Service (PaaS) recommendations without requiring access to sensitive customer data and queries. Doppler introduces a novel price-performance methodology that allows customers to get a personalized rank of relevant cloud targets solely based on low-level resource statistics, such as latency and memory usage. Doppler supplements this rank with internal knowledge of Azure customer behavior to help guide new migration customers towards one optimal target. Experimental results over a 9-month period from prospective and existing customers indicate that Doppler can identify optimal targets and adapt to changes in customer workloads. It has also found cost-saving opportunities among over-provisioned cloud customers, without compromising on capacity or other requirements. Doppler has been integrated and released in the Azure Data Migration Assistant v5.5, which receives hundreds of assessment requests daily.

cs.DB↗

arXiv2020

Orthogonalized SGD and Nested Architectures for Anytime Neural Networks

We propose a novel variant of SGD customized for training network architectures that support anytime behavior: such networks produce a series of increasingly accurate outputs over time. Efficient architectural designs for these networks focus on re-using internal state; subnetworks must produce representations relevant for both immediate prediction as well as refinement by subsequent network stages. We consider traditional branched networks as well as a new class of recursively nested networks. Our new optimizer, Orthogonalized SGD, dynamically re-balances task-specific gradients when training a multitask network. In the context of anytime architectures, this optimizer projects gradients from later outputs onto a parameter subspace that does not interfere with those from earlier outputs. Experiments demonstrate that training with Orthogonalized SGD significantly improves generalization accuracy of anytime networks.

cs.LG↗

arXiv2020

ALERT: Accurate Learning for Energy and Timeliness

An increasing number of software applications incorporate runtime Deep Neural Networks (DNNs) to process sensor data and return inference results to humans. Effective deployment of DNNs in these interactive scenarios requires meeting latency and accuracy constraints while minimizing energy, a problem exacerbated by common system dynamics. Prior approaches handle dynamics through either (1) system-oblivious DNN adaptation, which adjusts DNN latency/accuracy tradeoffs, or (2) application-oblivious system adaptation, which adjusts resources to change latency/energy tradeoffs. In contrast, this paper improves on the state-of-the-art by coordinating application- and system-level adaptation. ALERT, our runtime scheduler, uses a probabilistic model to detect environmental volatility and then simultaneously select both a DNN and a system resource configuration to meet latency, accuracy, and energy constraints. We evaluate ALERT on CPU and GPU platforms for image and speech tasks in dynamic environments. ALERT's holistic approach achieves more than 13% energy reduction, and 27% error reduction over prior approaches that adapt solely at the application or system level. Furthermore, ALERT incurs only 3% more energy consumption and 2% higher DNN-inference error than an oracle scheme with perfect application and system knowledge.

cs.PF↗