Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries
Fuente:
arXiv
Saved in:
| Main Authors: | Fan, Linfeng, Tian, Yuan, Li, Ziwei, Lu, Zhiwu |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents
by: Lu, Zijian, et al.
Published: (2026)
by: Lu, Zijian, et al.
Published: (2026)
Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries
by: Zhang, Xing, et al.
Published: (2026)
by: Zhang, Xing, et al.
Published: (2026)
More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries
by: Song, Hongwen, et al.
Published: (2026)
by: Song, Hongwen, et al.
Published: (2026)
SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces
by: Xu, Duling, et al.
Published: (2026)
by: Xu, Duling, et al.
Published: (2026)
SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
by: Gong, Jingzhi, et al.
Published: (2026)
by: Gong, Jingzhi, et al.
Published: (2026)
Scaling Coding Agents via Atomic Skills
by: Ma, Yingwei, et al.
Published: (2026)
by: Ma, Yingwei, et al.
Published: (2026)
Skilled AI Agents for Embedded and IoT Systems Development
by: Li, Yiming, et al.
Published: (2026)
by: Li, Yiming, et al.
Published: (2026)
SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
by: Han, Tingxu, et al.
Published: (2026)
by: Han, Tingxu, et al.
Published: (2026)
When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems
by: Wang, Su, et al.
Published: (2026)
by: Wang, Su, et al.
Published: (2026)
Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents
by: Liu, Ting
Published: (2026)
by: Liu, Ting
Published: (2026)
Cleaning Maintenance Logs with LLM Agents for Improved Predictive Maintenance
by: Dimidov, Valeriu, et al.
Published: (2025)
by: Dimidov, Valeriu, et al.
Published: (2025)
Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents
by: Yang, Zonghan, et al.
Published: (2025)
by: Yang, Zonghan, et al.
Published: (2025)
RIVA: Leveraging LLM Agents for Reliable Configuration Drift Detection
by: Abuzakuk, Sami, et al.
Published: (2026)
by: Abuzakuk, Sami, et al.
Published: (2026)
TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human Skills
by: Sun, Qiushi, et al.
Published: (2023)
by: Sun, Qiushi, et al.
Published: (2023)
Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs
by: Xu, Paiheng, et al.
Published: (2025)
by: Xu, Paiheng, et al.
Published: (2025)
Towards Secure Program Partitioning for Smart Contracts with LLM's In-Context Learning
by: Liu, Ye, et al.
Published: (2025)
by: Liu, Ye, et al.
Published: (2025)
Drift-Bench: Diagnosing Cooperative Breakdowns in LLM Agents under Input Faults via Multi-Turn Interaction
by: Bao, Han, et al.
Published: (2026)
by: Bao, Han, et al.
Published: (2026)
On LLM-Assisted Generation of Smart Contracts from Business Processes
by: Stiehle, Fabian, et al.
Published: (2025)
by: Stiehle, Fabian, et al.
Published: (2025)
Capability-Driven Skill Generation with LLMs: A RAG-Based Approach for Reusing Existing Libraries and Interfaces
by: da Silva, Luis Miguel Vieira, et al.
Published: (2025)
by: da Silva, Luis Miguel Vieira, et al.
Published: (2025)
Reducing Cost of LLM Agents with Trajectory Reduction
by: Xiao, Yuan-An, et al.
Published: (2025)
by: Xiao, Yuan-An, et al.
Published: (2025)
HarnessAPI: A Skill-First Framework for Unified Streaming APIs and MCP Tools
by: Jose, Edwin
Published: (2026)
by: Jose, Edwin
Published: (2026)
AI2Apps: A Visual IDE for Building LLM-based AI Agent Applications
by: Pang, Xin, et al.
Published: (2024)
by: Pang, Xin, et al.
Published: (2024)
SkillReducer: Optimizing LLM Agent Skills for Token Efficiency
by: Gao, Yudong, et al.
Published: (2026)
by: Gao, Yudong, et al.
Published: (2026)
PARCER as an Operational Contract to Reduce Variance, Cost, and Risk in LLM Systems
by: Filho, Elzo Brito dos Santos
Published: (2026)
by: Filho, Elzo Brito dos Santos
Published: (2026)
From User Interface to Agent Interface: Efficiency Optimization of UI Representations for LLM Agents
by: Ran, Dezhi, et al.
Published: (2025)
by: Ran, Dezhi, et al.
Published: (2025)
Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
by: Liu, Yi, et al.
Published: (2026)
by: Liu, Yi, et al.
Published: (2026)
AgenticTCAD: A LLM-based Multi-Agent Framework for Automated TCAD Code Generation and Device Optimization
by: Fan, Guangxi, et al.
Published: (2025)
by: Fan, Guangxi, et al.
Published: (2025)
An Empirical Study of Proactive Coding Assistants in Real-World Software Development
by: Li, Lehui, et al.
Published: (2026)
by: Li, Lehui, et al.
Published: (2026)
Ethics Testing: Proactive Identification of Generative AI System Harms
by: Tan, Shin Hwei, et al.
Published: (2026)
by: Tan, Shin Hwei, et al.
Published: (2026)
Help Without Being Asked: A Deployed Proactive Agent System for On-Call Support with Continuous Self-Improvement
by: Liu, Fengrui, et al.
Published: (2026)
by: Liu, Fengrui, et al.
Published: (2026)
PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation
by: Liu, Ye, et al.
Published: (2024)
by: Liu, Ye, et al.
Published: (2024)
iPanda: An LLM-based Agent for Automated Conformance Testing of Communication Protocols
by: Sun, Xikai, et al.
Published: (2025)
by: Sun, Xikai, et al.
Published: (2025)
BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills
by: Sonwane, Atharv, et al.
Published: (2025)
by: Sonwane, Atharv, et al.
Published: (2025)
Deploy-Master: Automating the Deployment of 50,000+ Agent-Ready Scientific Tools in One Day
by: Wang, Yi, et al.
Published: (2026)
by: Wang, Yi, et al.
Published: (2026)
Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling
by: Trae Research Team, et al.
Published: (2025)
by: Trae Research Team, et al.
Published: (2025)
Agentic Coding Needs Proactivity, Not Just Autonomy
by: Bui, Nghi D. Q., et al.
Published: (2026)
by: Bui, Nghi D. Q., et al.
Published: (2026)
Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networks
by: Hoppe, Fabian, et al.
Published: (2026)
by: Hoppe, Fabian, et al.
Published: (2026)
Evaluation-Driven Development and Operations of LLM Agents: A Process Model and Reference Architecture
by: Xia, Boming, et al.
Published: (2024)
by: Xia, Boming, et al.
Published: (2024)
RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
by: Bouzenia, Islem, et al.
Published: (2024)
by: Bouzenia, Islem, et al.
Published: (2024)
TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignment
by: Yuan, Zhiqiang, et al.
Published: (2024)
by: Yuan, Zhiqiang, et al.
Published: (2024)
Similar Items
-
ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents
by: Lu, Zijian, et al.
Published: (2026) -
Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries
by: Zhang, Xing, et al.
Published: (2026) -
More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries
by: Song, Hongwen, et al.
Published: (2026) -
SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces
by: Xu, Duling, et al.
Published: (2026) -
SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
by: Gong, Jingzhi, et al.
Published: (2026)