arXiv subjects

Zhongwen Li

Publications and source records attributed to Zhongwen Li.

12 recordsLinked to original sources

arXiv2026

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its importance, the open-source community lacks a principled, end-to-end ecosystem to streamline agent development. We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimizes the production pipeline for agentic model. ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering. We release ROME, an open-source agent grounded by ALE and trained on over one million trajectories. Our approach includes data composition protocols for synthesizing complex behaviors and a novel policy optimization algorithm, Interaction-Perceptive Agentic Policy Optimization (IPA), which assigns credit over semantic interaction chunks rather than individual tokens to improve long-horizon training stability. Empirically, we evaluate ROME within a structured setting and introduce Terminal Bench Pro, a benchmark with improved scale and contamination control. ROME demonstrates strong performance across benchmarks like SWE-bench Verified and Terminal Bench, proving the effectiveness of ALE.

cs.AI↗

arXiv2026

MoveScanner: Analysis of Security Risks of Move Smart Contracts

As blockchain technology continues to evolve, the security of smart contracts has increasingly drawn attention from both academia and industry. The Move language, with its unique resource model and linear type system, provides a solid foundation for the security of digital assets. However, smart contracts still face new security challenges due to developer programming errors and the potential risks associated with cross-module interactions. This paper systematically analyzes the limitations of existing security tools within the Move ecosystem and reveals their unique vulnerability patterns. To address these issues, it introduces MoveScanner, a static analysis tool based on a control flow graph and data flow analysis architecture. By incorporating cross-module call graph tracking, MoveScanner can effectively identify five key types of security vulnerabilities, including resource leaks, weak permission management, and arithmetic overflows. In terms of design, MoveScanner adheres to a modular principle, supports bytecode-level analysis and multi-chain adaptation, and introduces innovative resource trajectory tracking algorithms and capability matrix analysis methods, thereby significantly reducing the false positive rate. Empirical results show that MoveScanner achieved 88.2% detection accuracy in benchmark testing, filling the gap in security tools in the Move ecosystem. Furthermore, this paper identifies twelve new types of security risks based on the resource-oriented programming paradigm and provides a theoretical foundation and practical experience for the development of smart contract security mechanisms. Future work will focus on combining formal verification and dynamic analysis techniques to build a security protection framework covering the entire contract lifecycle

cs.CR↗

arXiv2026

Security Analysis of Web Applications Based on Gruyere

With the rapid development of Internet technologies, web systems have become essential infrastructures for modern information exchange and business operations. However, alongside their expansion, numerous security vulnerabilities have emerged, making web security a critical research focus within the broader field of cybersecurity. These issues are closely related to data protection, privacy preservation, and business continuity, and systematic research on web security is crucial for mitigating malicious attacks and enhancing the reliability and robustness of network systems. This paper first reviews the OWASP Top 10, summarizing the types, causes, and impacts of common web vulnerabilities, and illustrates their exploitation mechanisms through representative cases. Building upon this, the Gruyere platform is adopted as an experimental subject for analyzing known vulnerabilities. The study presents detailed reproduction steps for specific vulnerabilities, proposes comprehensive remediation strategies, and further compares Gruyere's vulnerabilities with contemporary real-world cases. The findings suggest that, although Gruyere's vulnerabilities are relatively outdated, their underlying principles remain highly relevant for explaining a wide range of modern security flaws. Overall, this research demonstrates that web system security analysis based on Gruyere not only deepens the understanding of vulnerability mechanisms but also provides practical support for technological innovation and security defense.

cs.CR↗

arXiv2026

System Password Security: Attack and Defense Mechanisms

System passwords serve as critical credentials for user authentication and access control when logging into operating systems or applications. Upon entering a valid password, users pass verification to access system resources and execute corresponding operations. In recent years, frequent password cracking attacks targeting system passwords have posed a severe threat to information system security. To address this challenge, in-depth research into password cracking attack methods and defensive technologies holds significant importance. This paper conducts systematic research on system password security, focusing on analyzing typical password cracking methods such as brute force attacks, dictionary attacks, and rainbow table attacks, while evaluating the effectiveness of existing defensive measures. The experimental section utilizes common cryptanalysis tools, such as John the Ripper and Hashcat, to simulate brute force and dictionary attacks. Five test datasets, each generated using Message Digest Algorithm 5 (MD5), Secure Hash Algorithm 256-bit (SHA 256), and bcrypt hash functions, are analyzed. By comparing the overall performance of different hash algorithms and password complexity strategies against these attacks, the effectiveness of defensive measures such as salting and slow hashing algorithms is validated. Building upon this foundation, this paper further evaluates widely adopted defense mechanisms, including account lockout policies, multi-factor authentication, and risk adaptive authentication. By integrating experimental data with recent research findings, it analyzes the strengths and limitations of each approach while proposing feasible improvement recommendations and optimization strategies.

cs.CR↗

arXiv2026

Information Security Based on LLM Approaches: A Review

Information security is facing increasingly severe challenges, and traditional protection means are difficult to cope with complex and changing threats. In recent years, as an emerging intelligent technology, large language models (LLMs) have shown a broad application prospect in the field of information security. In this paper, we focus on the key role of LLM in information security, systematically review its application progress in malicious behavior prediction, network threat analysis, system vulnerability detection, malicious code identification, and cryptographic algorithm optimization, and explore its potential in enhancing security protection performance. Based on neural networks and Transformer architecture, this paper analyzes the technical basis of large language models and their advantages in natural language processing tasks. It is shown that the introduction of large language modeling helps to improve the detection accuracy and reduce the false alarm rate of security systems. Finally, this paper summarizes the current application results and points out that it still faces challenges in model transparency, interpretability, and scene adaptability, among other issues. It is necessary to explore further the optimization of the model structure and the improvement of the generalization ability to realize a more intelligent and accurate information security protection system.

cs.CR↗

arXiv2026

Security Analysis of ChatGPT: Threats and Privacy Risks

As artificial intelligence technology continues to advance, chatbots are becoming increasingly powerful. Among them, ChatGPT, launched by OpenAI, has garnered widespread attention globally due to its powerful natural language processing capabilities based on the GPT model, which enables it to engage in natural conversations with users, understand various forms of linguistic expressions, and generate useful information and suggestions. However, as its application scope expands, user demand grows, and malicious attacks related to it become increasingly frequent, the security threats and privacy risks faced by ChatGPT are gradually coming to the forefront. In this paper, the security of ChatGPT is mainly studied from two aspects, security threats and privacy risks. The article systematically analyzes various types of vulnerabilities involved in the above two types of problems and their causes. Briefly, we discuss the controversies that ChatGPT may cause at the ethical and moral levels. In addition, this paper reproduces several network attack and defense test scenarios by simulating the attacker's perspective and methodology. Simultaneously, it explores the feasibility of using ChatGPT for security vulnerability detection and security tool generation from the defender's perspective.

cs.CR↗

arXiv2026

Facial Recognition Leveraging Generative Adversarial Networks

Face recognition performance based on deep learning heavily relies on large-scale training data, which is often difficult to acquire in practical applications. To address this challenge, this paper proposes a GAN-based data augmentation method with three key contributions: (1) a residual-embedded generator to alleviate gradient vanishing/exploding problems, (2) an Inception ResNet-V1 based FaceNet discriminator for improved adversarial training, and (3) an end-to-end framework that jointly optimizes data generation and recognition performance. Experimental results demonstrate that our approach achieves stable training dynamics and significantly improves face recognition accuracy by 12.7% on the LFW benchmark compared to baseline methods, while maintaining good generalization capability with limited training samples.

cs.CV↗

arXiv2026

When Blockchain Meets Crawlers: Real-time Market Analytics in Solana NFT Markets

In this paper, we design and implement a web crawler system based on the Solana blockchain for the automated collection and analysis of market data for popular non-fungible tokens (NFTs) on the chain. Firstly, the basic information and transaction data of popular NFTs on the Solana chain are collected using the Selenium tool. Secondly, the transaction records of the Magic Eden trading market are thoroughly analyzed by combining them with the Scrapy framework to examine the price fluctuations and market trends of NFTs. In terms of data analysis, this paper employs time series analysis to examine the dynamics of the NFT market and seeks to identify potential price patterns. In addition, the risk and return of different NFTs are evaluated using the mean-variance optimization model, taking into account their characteristics, such as illiquidity and market volatility, to provide investors with data-driven portfolio recommendations. The experimental results show that the combination of crawler technology and financial analytics can effectively analyze NFT data on the Solana blockchain and provide timely market insights and investment strategies. This study provides a reference for further exploration in the field of digital currencies.

cs.CR↗

arXiv2026

ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants

Large language model (LLM)-based agents are increasingly deployed in e-commerce shopping. To perform thorough, user-tailored product searches, agents should interpret personal preferences, engage in multi-turn dialogues, and ultimately retrieve and discriminate among highly similar products. However, existing research has yet to provide a unified simulation environment that consistently captures all of these aspects, and always focuses solely on evaluation benchmarks without training support. In this paper, we introduce ShopSimulator, a large-scale and challenging Chinese shopping environment. Leveraging ShopSimulator, we evaluate LLMs across diverse scenarios, finding that even the best-performing models achieve less than 40% full-success rate. Error analysis reveals that agents struggle with deep search and product selection in long trajectories, fail to balance the use of personalization cues, and to effectively engage with users. Further training exploration provides practical guidance for overcoming these weaknesses, with the combination of supervised fine-tuning (SFT) and reinforcement learning (RL) yielding significant performance improvements. Code and data will be released at https://github.com/ShopAgent-Team/ShopSimulator.

cs.AI↗

arXiv2017

High density array of epitaxial BiFeO3 nanodots with robust and reversibly switchable topological domain states

The exotic topological domains in ferroelectrics and multiferroics have attracted extensive interest in recent years due to their novel functionalities and potential applications in nanoelectronic devices. One of the key challenges for such applications is a realization of robust yet reversibly switchable nanoscale topological domain states with high density, wherein spontaneous topological structures can be individually addressed and controlled. This has been accomplished in our work using high density arrays of epitaxial BiFeO3 (BFO) nanodots with lateral size as small as ~60 nm. We demonstrate various types of spontaneous topological domain structures, including center-convergent domains, center-divergent domains, and double-center domains, which are stable over sufficiently long time yet can be manipulated and reversibly switched by electric field. The formation mechanisms of these topological domain states, assisted by the accumulation of compensating charges on the surface, have also been revealed. These result demonstrated that these reversibly switchable topological domain arrays are promising for applications in high density nanoferroelectric devices such as nonvolatile memories

cond-mat.mtrl-sci↗

arXiv2015

Ultrafast transmission electron microscopy on dynamic process of a CDW transition in 1T-TaSe2

Four-dimensional ultrafast transmission electron microscopy (4D-UTEM) measurements reveal a rich variety of structural dynamic phenomena at a phase transition in the charge-density-wave (CDW) 1T-TaSe2. Through the photoexcitation, remarkable changes on both the CDW intensity and orientation are clearly observed associated with the transformation from a commensurate (C) into an incommensurate (IC) phase in a time-scale of about 3 ps. Moreover, the transient states show up a notable "structurally isosbestic point" at a wave vector of qiso where the C and IC phases yield their diffracting efficiencies in an equally ratio. This fact demonstrates that the crystal planes parallel to qiso adopts visibly common structural features in these two CDW phases. The second-order characters observed in this nonequilibrium phase transition have been also analyzed based on the time-resolved structural data.

cond-mat.str-el↗

arXiv2014

Clocking the anisotropic lattice dynamics of multi-walled carbon nanotubes by four-dimensional ultrafast transmission electron microscopy

Recent advances in the four-dimensional ultrafast transmission electron microscope (4D-UTEM) with combined spatial and temporal resolutions have made it possible to directly visualize structural dynamics of materials at the atomic level. Herein, we report on our development on a 4D-UTEM which can be operated properly on either the photo-emission or the thermionic mode. We demonstrate its ability to obtain sequences of snapshots with high spatial and temporal resolutions in the study of lattice dynamics of the multi-walled carbon nanotubes (MWCNTs). This investigation provides an atomic level description of remarkable anisotropic lattice dynamics at the picosecond timescales. Moreover, our UTEM measurements clearly reveal that distinguishable lattice relaxations appear in intra-tubular sheets on an ultrafast timescale of a few picoseconds and after then an evident lattice expansion along the radical direction. These anisotropic behaviors in the MWCNTs are considered arising from the variety of chemical bonding, i.e. the weak van der Waals bonding between the tubular planes and the strong covalent sp2-hybridized bonds in the tubular sheets.

cond-mat.mes-hall↗