Skip to content
All tags

#paper-review

2 posts
ai deep-dive

The Skill Management Revolution for LLM Agents: A Complete Landscape of Skill Lifecycle from Voyager to MUSE-Autoskill

MUSE-Autoskill (2026) introduces a five-stage skill lifecycle framework. Self-created skills achieve 60.35% (+7.16%) on SkillsBench overall, and an impressive 87.94% on tasks where skill generation succeeds — surpassing the human-authored skill ceiling. This post synthesizes six arXiv papers to map the full landscape of skill evolution research.

#agent-skills#ai-agent#llm#self-refinement#memory#arxiv#paper-review
ai deep-dive

Assembling LLM Agent Skills / Tools / Code Interpreter for Real: A Paper Reading Map

The hard part of LLM agents is not building function calling, skills, code interpreter, and document tools individually -- it is assembling them into a system that selects the right tool, writes code when needed, decomposes tasks, verifies results, and resists prompt injection. This post organizes the key papers into six engineering decisions: function calling reliability, tool/skill selection, code-as-action, multi-step planning, skill systems, and safety plus document generation.

#llm#agents#tool-use#skills#code-interpreter#function-calling#paper-review