Image de couverture de livre

SkillReducer: Optimizing LLM Agent Skills for Token Efficiency

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gao, Yudong, Li, Zongjie, Yuanyuanyuan, Ji, Zimo, Ma, Pingchuan, Wang, Shuai
Format:	Preprint
Publié:	2026
Sujets:	Software Engineering
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode
par: Ji, Zimo, et autres
Publié: (2026)

EffiSkill: Agent Skill Based Automated Code Efficiency Optimization
par: Wang, Zimu, et autres
Publié: (2026)

How Multi-Modal LLMs Reshape Visual Deep Learning Testing? A Comprehensive Study Through the Lens of Image Mutation
par: Wang, Liwen, et autres
Publié: (2024)

Reasoning as a Resource: Optimizing Fast and Slow Thinking in Code Generation Models
par: Li, Zongjie, et autres
Publié: (2025)

SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?
par: Chen, Shiqi, et autres
Publié: (2026)

Digging Into the Internal: Causality-Based Analysis of LLM Function Calling
par: Ji, Zhenlan, et autres
Publié: (2025)

Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries
par: Fan, Linfeng, et autres
Publié: (2026)

Low-Cost and Comprehensive Non-textual Input Fuzzing with LLM-Synthesized Input Generators
par: Zhang, Kunpeng, et autres
Publié: (2025)

SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
par: Gong, Jingzhi, et autres
Publié: (2026)

Scaling Coding Agents via Atomic Skills
par: Ma, Yingwei, et autres
Publié: (2026)

SkillClone: Multi-Modal Clone Detection and Clone Propagation Analysis in the Agent Skill Ecosystem
par: Zhu, Jiaying, et autres
Publié: (2026)

SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces
par: Xu, Duling, et autres
Publié: (2026)

RUM: Rule+LLM-Based Comprehensive Assessment on Testing Skills
par: Wang, Yue, et autres
Publié: (2025)

Skilled AI Agents for Embedded and IoT Systems Development
par: Li, Yiming, et autres
Publié: (2026)

ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents
par: Lu, Zijian, et autres
Publié: (2026)

Exploiting LLM Agent Supply Chains via Payload-less Skills
par: Liu, Xinyu, et autres
Publié: (2026)

SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration
par: Guo, Zihan, et autres
Publié: (2026)

API-guided Dataset Synthesis to Finetune Large Code Models
par: Li, Zongjie, et autres
Publié: (2024)

More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries
par: Song, Hongwen, et autres
Publié: (2026)

SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems
par: Pu, Hongji, et autres
Publié: (2026)

Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
par: Zhou, Chenyu, et autres
Publié: (2026)

Reducing Token Usage of State-in-Context Agents using Minification
par: Hrubec, Nicolas, et autres
Publié: (2026)

From Evaluation to Enhancement: Large Language Models for Zero-Knowledge Proof Code Generation
par: Xue, Zhantong, et autres
Publié: (2025)

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
par: Han, Tingxu, et autres
Publié: (2026)

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems
par: Wang, Su, et autres
Publié: (2026)

ClarEval: A Benchmark for Evaluating Clarification Skills of Code Agents under Ambiguous Instructions
par: Li, Jialin, et autres
Publié: (2026)

Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents
par: Yang, Zonghan, et autres
Publié: (2025)

SPVR: syntax-to-prompt vulnerability repair based on large language models
par: Wang, Ruoke, et autres
Publié: (2024)

Reducing Cost of LLM Agents with Trajectory Reduction
par: Xiao, Yuan-An, et autres
Publié: (2025)

Exploring Multi-Lingual Bias of Large Code Models in Code Generation
par: Wang, Chaozheng, et autres
Publié: (2024)

Skill-Adpative Imitation Learning for UI Test Reuse
par: Wu, Mengzhou, et autres
Publié: (2024)

Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality
par: Ling, George, et autres
Publié: (2026)

PyBench: Evaluating LLM Agent on various real-world coding tasks
par: Zhang, Yaolun, et autres
Publié: (2024)

From User Interface to Agent Interface: Efficiency Optimization of UI Representations for LLM Agents
par: Ran, Dezhi, et autres
Publié: (2025)

Optimizing Token Consumption in LLMs: A Nano Surge Approach for Code Reasoning Efficiency
par: Hu, Junwei, et autres
Publié: (2025)

TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human Skills
par: Sun, Qiushi, et autres
Publié: (2023)

Industry Expectations and Skill Demands in Quantum Software Testing
par: Santos, Ronnie de Souza, et autres
Publié: (2025)

Unveiling the Skills and Responsibilities of Serverless Practitioners: An Empirical Investigation
par: Hamza, Muhammad, et autres
Publié: (2024)

Establishing Software Engineering Design Competence with Soft Skills
par: Capretz, Luiz Fernando
Publié: (2024)

JSProtect: A Scalable Obfuscation Framework for Mini-Games in WeChat
par: Li, Zhihao, et autres
Publié: (2025)