Cover Image

Counterfactual Trace Auditing of LLM Agent Skills

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Xiaolin, Liu, Jinbo, Li, Li, Rossi, Ryan A., Hu, Xiyang
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

FORTIS: Benchmarking Over-Privilege in Agent Skills
by: Li, Shawn, et al.
Published: (2026)

Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
by: Wu, Xiyang, et al.
Published: (2026)

When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents
by: Zhou, Xiaolin, et al.
Published: (2026)

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

Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
by: Liu, Dawei, et al.
Published: (2026)

ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation
by: Yuan, Boqin, et al.
Published: (2026)

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

Fairness or Fluency? An Investigation into Language Bias of Pairwise LLM-as-a-Judge
by: Zhou, Xiaolin, et al.
Published: (2026)

Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
by: Ni, Jingwei, et al.
Published: (2026)

SkillsInjector: Dynamic Skill Context Construction for LLM Agents
by: Li, Yanchao, et al.
Published: (2026)

Don't Start What You Can't Finish: A Counterfactual Audit of Support-State Triage in LLM Agents
by: Unlu, Eren
Published: (2026)

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

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

MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments
by: Gao, Yicheng, et al.
Published: (2026)

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

AD-LLM: Benchmarking Large Language Models for Anomaly Detection
by: Yang, Tiankai, et al.
Published: (2024)

Equal Access, Unequal Interaction: A Counterfactual Audit of LLM Fairness
by: Amiri-Margavi, Alireza, et al.
Published: (2026)

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

Auditable Agents
by: Nian, Yi, et al.
Published: (2026)

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

The Scaling Laws of Skills in LLM Agent Systems
by: Chen, Charles, et al.
Published: (2026)

Insider Attacks in Multi-Agent LLM Consensus Systems
by: Sun, Xiaolin, et al.
Published: (2026)

Harnessing LLM Agents with Skill Programs
by: Liu, Hongjun, et al.
Published: (2026)

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

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

Skill-R1: Agent Skill Evolution via Reinforcement Learning
by: Vishe, Yash, et al.
Published: (2026)

Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents
by: Wang, Jingxing, et al.
Published: (2026)

STARS: Skill-Triggered Audit for Request-Conditioned Invocation Safety in Agent Systems
by: Zhang, Guijia, et al.
Published: (2026)

Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs
by: Liu, Jinbo, et al.
Published: (2025)

RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents
by: Xiao, Wenjie, et al.
Published: (2026)

Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries
by: Fan, Linfeng, et al.
Published: (2026)

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

Counterfactual Credit Policy Optimization for Multi-Agent Collaboration
by: Li, Zhongyi, et al.
Published: (2026)

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

Structured Uncertainty guided Clarification for LLM Agents
by: Suri, Manan, et al.
Published: (2025)

Trace2Skill: Verifier-Guided Skill Evolution for Long-Context EDA Agents
by: Du, Zijian, et al.
Published: (2026)

PrefixGuard: From LLM-Agent Traces to Online Failure-Warning Monitors
by: Huang, Xinmiao, et al.
Published: (2026)

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

SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
by: Cho, Hongcheol, et al.
Published: (2026)

Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study
by: Chen, Zhihao, et al.
Published: (2026)