SkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale
cs.IR, cs.AI, cs.MA
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/guanqun-yang/SkillSeek
Sources
- SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses
- SkillReducer: Optimizing LLM Agent Skills for Token Efficiency
- SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
- SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
- SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
- SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance
- How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
- Tools are under-documented: Simple Document Expansion Boosts Tool Retrieval
- In Defense of Cross-Encoders for Zero-Shot Retrieval
- SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources
- Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward
- SkillRouter: Skill Routing for LLM Agents at Scale
Related papers
- The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
- SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
- MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
- How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
- MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
- Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition