arXiv subjects

Qiyang Chen

Publications and source records attributed to Qiyang Chen.

4 recordsLinked to original sources

arXiv2026

ATOBench: Tracing How Autonomous Penetration-Testing Agents Verify Vulnerabilities When Target Evidence Lies

Autonomous penetration-testing agents rely on target responses. These responses guide both subsequent actions and the final report. A deceptive response can therefore redirect both the attack trajectory and the agent's verification process. However, final reports reveal little about how an agent interprets conflicting evidence, changes course, decides to stop, or turns observations into a vulnerability claim. We introduce ATOBench, an evaluation framework that makes this verification process observable. ATOBench injects registered response transformations at runtime and pairs each transformed episode with a native episode under the same environment. Each pair is aligned at the first affected response. A source-linked reconstruction then follows later actions, evidence recovery, stopping, and report support. Three frozen observation contracts cover exploit proof, resource ownership, and reusable artifacts. We evaluate five model routes over 450 episodes. The analysis shows that increased activity can mask a broken verification chain, while successful recovery depends on finding usable evidence and preserving it through reporting. ATOBench turns deceptive target observations into a reproducible probe of evidence handling in autonomous penetration testing. This process-level view extends offensive pentest agent evaluation beyond final outcomes by revealing how untrusted observations shape actions, verification, and reporting.

cs.CR↗

arXiv2026

ZoomTable: Interactive Exploration of Data Facts in Hierarchical Tables via Semantic Zooming

Hierarchical tables are an important structure for organizing data with inherent hierarchical relationships. Existing studies have extensively explored methods for data fact exploration from tabular data. In particular, some studies have directly integrated visual data facts into the original table structure to support in-situ exploration, because embedding data facts within the table context can reduce cognitive load by minimizing attention shifts. However, embedding a large amount of extracted data facts into the limited space of hierarchical tables often leads to layout conflicts, hindering effective exploration. To address this issue, we propose an interactive exploration paradigm for hierarchical table data facts based on semantic zooming and develop an interactive visualization system, ZoomTable. The ZoomTable system employs semantic zooming as the interaction method, combined with a data-fact layout method and a data fact recommendation mechanism. This combination not only resolves layout conflicts, but also supports users in coherently exploring multidimensional data facts at different scales. A case study and a user experiment further validate the practicality and efficiency of ZoomTable in real-world data fact exploration scenarios.

cs.HC↗

arXiv2025

InReAcTable: LLM-Powered Interactive Visual Data Story Construction from Tabular Data

Insights in tabular data capture valuable patterns that help analysts understand critical information. Organizing related insights into visual data stories is crucial for in-depth analysis. However, constructing such stories is challenging because of the complexity of the inherent relations between extracted insights. Users face difficulty sifting through a vast number of discrete insights to integrate specific ones into a unified narrative that meets their analytical goals. Existing methods either heavily rely on user expertise, making the process inefficient, or employ automated approaches that cannot fully capture their evolving goals. In this paper, we introduce InReAcTable, a framework that enhances visual data story construction by establishing both structural and semantic connections between data insights. Each user interaction triggers the Acting module, which utilizes an insight graph for structural filtering to narrow the search space, followed by the Reasoning module using the retrieval-augmented generation method based on large language models for semantic filtering, ultimately providing insight recommendations aligned with the user's analytical intent. Based on the InReAcTable framework, we develop an interactive prototype system that guides users to construct visual data stories aligned with their analytical requirements. We conducted a case study and a user experiment to demonstrate the utility and effectiveness of the InReAcTable framework and the prototype system for interactively building visual data stories.

cs.HC↗

arXiv2025

Mixture-of-RAG: Integrating Text and Tables with Large Language Models

Large language models (LLMs) achieve optimal utility when their responses are grounded in external knowledge sources. However, real-world documents, such as annual reports, scientific papers, and clinical guidelines, frequently combine extensive narrative content with complex, hierarchically structured tables. While existing retrieval-augmented generation (RAG) systems effectively integrate LLMs' generative capabilities with external retrieval-based information, their performance significantly deteriorates especially processing such heterogeneous text-table hierarchies. To address this limitation, we formalize the task of Heterogeneous Document RAG, which requires joint retrieval and reasoning across textual and hierarchical tabular data. We propose MixRAG, a novel three-stage framework: (i) hierarchy row-and-column-level (H-RCL) representation that preserves hierarchical structure and heterogeneous relationship, (ii) an ensemble retriever with LLM-based reranking for evidence alignment, and (iii) multi-step reasoning decomposition via a RECAP prompt strategy. To bridge the gap in available data for this domain, we release the dataset DocRAGLib, a 2k-document corpus paired with automatically aligned text-table summaries and gold document annotations. The comprehensive experiment results demonstrate that MixRAG boosts top-1 retrieval by 46% over strong text-only, table-only, and naive-mixture baselines, establishing new state-of-the-art performance for mixed-modality document grounding.

cs.IR↗