SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents
cs.AI
Submitted: 2026-05-08
Updated: 2026-10-01
Terminology
Sources
- EvoSkill: Automated Skill Discovery for Multi-Agent Systems
- Towards Explorative IRBL: Combining Semantic Retrieval with LLM-driven Iterative Code Exploration
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
- Memp: Exploring Agent Procedural Memory
- How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
- Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
- Agentless: Demystifying LLM-based Software Engineering Agents
- Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward
- A-MEM: Agentic Memory for LLM Agents
- AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
- CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
- A Benchmark for Localizing Code and Non-Code Issues in Software Projects
- A Survey on the Memory Mechanism of Large Language Model based Agents
- SkillRouter: Skill Routing for LLM Agents at Scale
- MemoryBank: Enhancing Large Language Models with Long-Term Memory
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems