arXiv subjects

Zhiqiang Dong

Publications and source records attributed to Zhiqiang Dong.

8 recordsLinked to original sources

arXiv2026

CAIRN: Dynamic Fact-Intent DAGs for Multi-Agent Exploration

LLM-powered autonomous systems have demonstrated promising capabilities in mathematical reasoning, engineering, and cybersecurity. Yet how to organize these systems for effective, reliable, and sustained performance remains an open question. In this paper, we present CAIRN, a fact-intent-driven multi-agent paradigm for goal-directed exploration. CAIRN represents observations and planned investigations as a dynamic directed acyclic graph (DAG). A reasoner interprets facts to propose intents, which workers execute to produce new facts. Each intent references its supporting facts and defines a potential exploration branch. The persistent graph preserves goals, dependencies and findings across workers, supporting knowledge reuse and parallel exploration. The graph also makes execution trajectories traceable and auditable, providing a basis for human verification and intervention. We evaluate CAIRN across cybersecurity and mathematical reasoning tasks, examining task success, time to solution, and token consumption. DAG-based coordination can incur higher token costs with no observable performance gains on tasks that require little effort. However, on high-effort tasks (at least 1M tokens), we observe faster solutions in 76.5% of cases, with speedups of up to 3.08x. Moreover, as task effort increases, these time gains become more pronounced while relative token overhead declines, highlighting the potential of DAG-guided parallel exploration.

cs.AI↗

arXiv2026

"Tab, Tab, Bug": Security Pitfalls of Next Edit Suggestions in AI-Integrated IDEs

Modern AI-integrated IDEs are shifting from passive code completion to proactive Next Edit Suggestions (NES). Unlike traditional autocompletion, NES is designed to construct a richer context from both recent user interactions and the broader codebase to suggest multi-line, cross-line, or even cross-file modifications. This evolution significantly streamlines the programming workflow into a tab-by-tab interaction and enhances developer productivity. Consequently, NES introduces a more complex context retrieval mechanism and sophisticated interaction patterns. However, existing studies focus almost exclusively on the security implications of standalone LLM-based code generation, ignoring the potential attack vectors posed by NES in modern AI-integrated IDEs. The underlying mechanisms of NES remain under-explored, and their security implications are not yet fully understood. In this paper, we conduct the first systematic security study of NES systems. First, we perform an in-depth dissection of the NES mechanisms to understand the newly introduced threat vectors. It is found that NES retrieves a significantly expanded context, including inputs from imperceptible user actions and global codebase retrieval, which increases the attack surfaces. Second, we conduct a comprehensive in-lab study to evaluate the security implications of NES. The evaluation results reveal that NES is susceptible to context poisoning and is sensitive to transactional edits and human-IDE interactions. Third, we perform a large-scale online survey involving over 200 professional developers to assess the perceptions of NES security risks in real-world development workflows. The survey results indicate a general lack of awareness regarding the potential security pitfalls associated with NES, highlighting the need for increased education and improved security countermeasures in AI-integrated IDEs.

cs.CR↗

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

Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning

Offline goal-conditioned reinforcement learning (GCRL) is a practical reinforcement learning paradigm that aims to learn goal-conditioned policies from reward-free offline data. Despite recent advances in hierarchical architectures such as HIQL, long-horizon control in offline GCRL remains challenging due to the limited expressiveness of Gaussian policies and the inability of high-level policies to generate effective subgoals. To address these limitations, we propose the goal-conditioned mean flow policy, which introduces an average velocity field into hierarchical policy modeling for offline GCRL. Specifically, the mean flow policy captures complex target distributions for both high-level and low-level policies through a learned average velocity field, enabling efficient action generation via one-step sampling. Furthermore, considering the insufficiency of goal representation, we introduce a LeJEPA loss that repels goal representation embeddings during training, thereby encouraging more discriminative representations and improving generalization. Experimental results show that our method achieves strong performance across both state-based and pixel-based tasks in the OGBench benchmark.

cs.LG↗

arXiv2026

Value-Guidance MeanFlow for Offline Multi-Agent Reinforcement Learning

Offline multi-agent reinforcement learning (MARL) aims to learn the optimal joint policy from pre-collected datasets, requiring a trade-off between maximizing global returns and mitigating distribution shift from offline data. Recent studies use diffusion or flow generative models to capture complex joint policy behaviors among agents; however, they typically rely on multi-step iterative sampling, thereby reducing training and inference efficiency. Although further research improves sampling efficiency through methods like distillation, it remains sensitive to the behavior regularization coefficient. To address the above-mentioned issues, we propose Value Guidance Multi-agent MeanFlow Policy (VGM$^2$P), a simple yet effective flow-based policy learning framework that enables efficient action generation with coefficient-insensitive conditional behavior cloning. Specifically, VGM$^2$P uses global advantage values to guide agent collaboration, treating optimal policy learning as conditional behavior cloning. Additionally, to improve policy expressiveness and inference efficiency in multi-agent scenarios, it leverages classifier-free guidance MeanFlow for both policy training and execution. Experiments on tasks with both discrete and continuous action spaces demonstrate that, even when trained solely via conditional behavior cloning, VGM$^2$P efficiently achieves performance comparable to state-of-the-art methods.

cs.LG↗

arXiv2026

Equivariant Efficient Joint Discrete and Continuous MeanFlow for Molecular Graph Generation

Graph-structured data jointly contain discrete topology and continuous geometry, which poses fundamental challenges for generative modeling due to heterogeneous distributions, incompatible noise dynamics, and the need for equivariant inductive biases. Existing flow-matching approaches for graph generation typically decouple structure from geometry, lack synchronized cross-domain dynamics, and rely on iterative sampling, often resulting in physically inconsistent molecular conformations and slow sampling. To address these limitations, we propose Equivariant MeanFlow (EQUIMF), a unified SE(3)-equivariant generative framework that jointly models discrete and continuous components through synchronized MeanFlow dynamics. EQUIMF introduces a unified time bridge and average-velocity updates with mutual conditioning between structure and geometry, enabling efficient few-step generation while preserving physical consistency. Moreover, we develop a novel discrete MeanFlow formulation with a simple yet effective parameterization to support efficient generation over discrete graph structures. Extensive experiments demonstrate that EQUIMF consistently outperforms prior diffusion and flow-matching methods in generation quality, physical validity, and sampling efficiency.

cs.LG↗

arXiv2024

Patch2QL: Discover Cognate Defects in Open Source Software Supply Chain With Auto-generated Static Analysis Rules

In the open source software (OSS) ecosystem, there exists a complex software supply chain, where developers upstream and downstream widely borrow and reuse code. This results in the widespread occurrence of recurring defects, missing fixes, and propagation issues. These are collectively referred to as cognate defects, and their scale and threats have not received extensive attention and systematic research. Software composition analysis and code clone detection methods are unable to cover the various variant issues in the supply chain scenario, while code static analysis, or static application security testing (SAST) techniques struggle to target specific defects. In this paper, we propose a novel technique for detecting cognate defects in OSS through the automatic generation of SAST rules. Specifically, it extracts key syntax and semantic information from pre- and post-patch versions of code through structural comparison and control flow to data flow analysis, and generates rules that matches these key elements. We have implemented a prototype tool called Patch2QL and applied it to fundamental OSS in C/C++. In experiments, we discovered 7 new vulnerabilities with medium to critical severity in the most popular upstream software, as well as numerous potential security issues. When analyzing downstream projects in the supply chain, we found a significant number of representative cognate defects, clarifying the threat posed by this issue. Additionally, compared to general-purpose SAST and signature-based mechanisms, the generated rules perform better at discover all variants of cognate defects.

cs.CR↗

arXiv2023

LEAPS: End-to-End One-Step Person Search With Learnable Proposals

We propose an end-to-end one-step person search approach with learnable proposals, named LEAPS. Given a set of sparse and learnable proposals, LEAPS employs a dynamic person search head to directly perform person detection and corresponding re-id feature generation without non-maximum suppression post-processing. The dynamic person search head comprises a detection head and a novel flexible re-id head. Our flexible re-id head first employs a dynamic region-of-interest (RoI) operation to extract discriminative RoI features of the proposals. Then, it generates re-id features using a plain and a hierarchical interaction re-id module. To better guide discriminative re-id feature learning, we introduce a diverse re-id sample matching strategy, instead of bipartite matching in detection head. Comprehensive experiments reveal the benefit of the proposed LEAPS, achieving a favorable performance on two public person search benchmarks: CUHK-SYSU and PRW. When using the same ResNet50 backbone, our LEAPS obtains a mAP score of 55.0%, outperforming the best reported results in literature by 1.7%, while achieving around a two-fold speedup on the challenging PRW dataset. Our source code and models will be released.

cs.CV↗