Imagen de Portada

STARS: Skill-Triggered Audit for Request-Conditioned Invocation Safety in Agent Systems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Guijia, Yang, Shu, Gong, Xilin, Wang, Di
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Hallucination as Exploit: Evidence-Carrying Multimodal Agents
por: Zhang, Guijia, et al.
Publicado: (2026)

MedSkillAudit: A Domain-Specific Audit Framework for Medical Research Agent Skills
por: Hou, Yingyong, et al.
Publicado: (2026)

Logic Agent: Enhancing Validity with Logic Rule Invocation
por: Liu, Hanmeng, et al.
Publicado: (2024)

Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning
por: Chen, Chishui, et al.
Publicado: (2026)

When Agents Fail to Act: A Diagnostic Framework for Tool Invocation Reliability in Multi-Agent LLM Systems
por: Huang, Donghao, et al.
Publicado: (2026)

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

MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models
por: Hu, Jingyu, et al.
Publicado: (2025)

Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment
por: Xie, Yuchong, et al.
Publicado: (2025)

DroidCall: A Dataset for LLM-powered Android Intent Invocation
por: Xie, Weikai, et al.
Publicado: (2024)

Analyzing Message-Code Inconsistency in AI Coding Agent-Authored Pull Requests
por: Gong, Jingzhi, et al.
Publicado: (2026)

Auditable Agents
por: Nian, Yi, et al.
Publicado: (2026)

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

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
por: Liu, Yuxuan, et al.
Publicado: (2026)

Advancing and Benchmarking Personalized Tool Invocation for LLMs
por: Huang, Xu, et al.
Publicado: (2025)

SkillMaster: Toward Autonomous Skill Mastery in LLM Agents
por: Yang, Min, et al.
Publicado: (2026)

When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs
por: Zhang, Zhuoran, et al.
Publicado: (2025)

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
por: Jin, Chang, et al.
Publicado: (2026)

Request-Only Optimization for Recommendation Systems
por: Guo, Liang, et al.
Publicado: (2025)

GeoMind: An Agentic Workflow for Lithology Classification with Reasoned Tool Invocation
por: Zhou, Yitong, et al.
Publicado: (2026)

Trigger without Trace: Towards Stealthy Backdoor Attack on Text-to-Image Diffusion Models
por: Zhang, Jie, et al.
Publicado: (2025)

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

Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents
por: Zhang, Xi, et al.
Publicado: (2026)

Requesting Expert Reasoning: Augmenting LLM Agents with Learned Collaborative Intervention
por: Wang, Zhiming, et al.
Publicado: (2026)

ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Management
por: Pan, Zaifeng, et al.
Publicado: (2026)

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

Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
por: Wang, Hao, et al.
Publicado: (2026)

From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
por: Huang, Zisu, et al.
Publicado: (2026)

SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents
por: Zhou, Yifan, et al.
Publicado: (2026)

SkillOpt: Executive Strategy for Self-Evolving Agent Skills
por: Yang, Yifan, et al.
Publicado: (2026)

MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection
por: Tan, Zhewen, et al.
Publicado: (2026)

EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents
por: Ju, Ruofei, et al.
Publicado: (2026)

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
por: Liu, Songyang, et al.
Publicado: (2026)

Towards Security-Auditable LLM Agents: A Unified Graph Representation
por: Li, Chaofan, et al.
Publicado: (2026)

Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
por: Mi, Qirui, et al.
Publicado: (2026)

Single-Node Trigger Backdoor Attacks in Graph-Based Recommendation Systems
por: Li, Runze, et al.
Publicado: (2025)

CODESKILL: Learning Self-Evolving Skills for Coding Agents
por: Li, Yanzhou, et al.
Publicado: (2026)

From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
por: Liang, Qiliang, et al.
Publicado: (2026)

Springdrift: An Auditable Persistent Runtime for LLM Agents with Case-Based Memory, Normative Safety, and Ambient Self-Perception
por: Brady, Seamus
Publicado: (2026)

Automated Creation and Enrichment Framework for Improved Invocation of Enterprise APIs as Tools
por: Agarwal, Prerna, et al.
Publicado: (2025)

Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations
por: Liu, Yilong, et al.
Publicado: (2026)