Cover Image

Towards Security-Auditable LLM Agents: A Unified Graph Representation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Chaofan, Zhang, Lyuye, Zhai, Jintao, Feng, Siyue, Yang, Xichun, Wang, Huahao, Dou, Shihan, Ji, Yu, Hu, Yutao, Wu, Yueming, Liu, Yang, Zou, Deqing
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Detecting Essence Code Clones via Information Theoretic Analysis
by: Zhao, Lida, et al.
Published: (2025)

Semia: Auditing Agent Skills via Constraint-Guided Representation Synthesis
by: Wen, Hongbo, et al.
Published: (2026)

JC-Finder: Detecting Java Clone-based Third-Party Library by Class-level Tree Analysis
by: Zhao, Lida, et al.
Published: (2025)

BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents
by: Feng, Yunhao, et al.
Published: (2026)

CC2Vec: Combining Typed Tokens with Contrastive Learning for Effective Code Clone Detection
by: Dou, Shihan, et al.
Published: (2024)

A Taxonomy of Prompt Defects in LLM Systems
by: Tian, Haoye, et al.
Published: (2025)

SkillClone: Multi-Modal Clone Detection and Clone Propagation Analysis in the Agent Skill Ecosystem
by: Zhu, Jiaying, et al.
Published: (2026)

Agent Audit: A Security Analysis System for LLM Agent Applications
by: Zhang, Haiyue, et al.
Published: (2026)

OPGAgent: An Agent for Auditable Dental Panoramic X-ray Interpretation
by: Yu, Zhaolin, et al.
Published: (2026)

UFO: a Unified and Flexible Framework for Evaluating Factuality of Large Language Models
by: Huang, Zhaoheng, et al.
Published: (2024)

Burn-After-Use for Preventing Data Leakage through a Secure Multi-Tenant Architecture in Enterprise LLM
by: Zhang, Qiang, et al.
Published: (2026)

Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization
by: Wang, Junzhe, et al.
Published: (2026)

LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning
by: Sun, Yuqiang, et al.
Published: (2024)

Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization
by: Zhu, Yutao, et al.
Published: (2025)

EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis
by: Song, Xiaoshuai, et al.
Published: (2026)

FLeW: Facet-Level and Adaptive Weighted Representation Learning of Scientific Documents
by: Dou, Zheng, et al.
Published: (2025)

PortAgent: LLM-driven Vehicle Dispatching Agent for Port Terminals
by: Hu, Jia, et al.
Published: (2025)

Spatial-Functional awareness Transformer-based graph archetype contrastive learning for Decoding Visual Neural Representations from EEG
by: Sun, Yueming, et al.
Published: (2025)

Counterfactual Trace Auditing of LLM Agent Skills
by: Zhou, Xiaolin, et al.
Published: (2026)

LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-based Code Completion
by: Wang, Chong, et al.
Published: (2024)

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills
by: Lv, Lijia, et al.
Published: (2026)

From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning
by: Deng, Zhirui, et al.
Published: (2024)

SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents
by: Shen, Yujiong, et al.
Published: (2026)

EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms
by: Yuan, Siyu, et al.
Published: (2024)

NeuroBind: Towards Unified Multimodal Representations for Neural Signals
by: Yang, Fengyu, et al.
Published: (2024)

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say
by: Zhang, Mingxuan, et al.
Published: (2026)

UniFAR: A Unified Facet-Aware Retrieval Framework for Scientific Documents
by: Dou, Zheng, et al.
Published: (2026)

Empirical Analysis of Vulnerabilities Life Cycle in Golang Ecosystem
by: Hu, Jinchang, et al.
Published: (2023)

Emerging roles of tripartite motif family proteins (TRIMs) in breast cancer
by: Jianing Cao, et al.
Published: (2024)

Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge
by: Yang, Wei, et al.
Published: (2026)

Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning
by: Hu, Yuyang, et al.
Published: (2026)

Towards Unified Alignment Between Agents, Humans, and Environment
by: Yang, Zonghan, et al.
Published: (2024)

Sealing the Audit-Runtime Gap for LLM Skills
by: Shen, Tingda, et al.
Published: (2026)

Towards Unifying Quantitative Security Benchmarking for Multi Agent Systems
by: Sharma, Gauri, et al.
Published: (2025)

Securing LLM Agents Need Intent-to-Execution Integrity
by: Qu, Wenjie, et al.
Published: (2026)

Hypothesis Generation via LLM-Automated Language Bias for ILP
by: Yang, Yang, et al.
Published: (2025)

The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement
by: Yang, Ruihan, et al.
Published: (2025)

RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing
by: Guo, Jinyao, et al.
Published: (2025)

Fixing Outside the Box: Uncovering Tactics for Open-Source Security Issue Management
by: Zhang, Lyuye, et al.
Published: (2025)

Unified Context Evolution for LLM Agents
by: Zhu, Zixuan, et al.
Published: (2026)