Skill++: Towards Lifelong Agents via Routing-Aware Skill Refinement
cs.AI, cs.CL
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/oneal2000/SR-Agents
Terminology
Sources
- SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale
- The Scaling Laws of Skills in LLM Agent Systems
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Scaling Enterprise Agent Routing: Degradation, Diagnosis, and Recovery
- Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use
- One Skill, Two Masters: Serving Users and Attackers through Skill Injection
- When Continual Learning Moves to Memory: A Study of Experience Reuse in LLM Agents
- SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
- How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
- DOCSCHISEL: Adaptive Tool Documentation Optimization Framework for LLM Agents
- When Synthetic Data Hurts: On Catastrophic Forgetting in Skill Retrieval for LLM Agents
- More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries
- Skill Retrieval Augmentation for Agentic AI
- Representation Learning with Contrastive Predictive Coding
- Skill Is Not Document: Query-Conditioned Compatibility for LLM Agent Skill Routing
- Skills Know Their Neighbors: Cluster-Contrastive Capability Pages for Skill Retrieval
- TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent
- What Keeps Agent Skills from Being Reusable? Evidence from 138K SKILL.md Files
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents