agent/papers/items/2026-2605-19604-formal-skill-programmable-runtime-skills-for-efficient-and-accurate-llm-agents.md

Paper: Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents

---

type: paper title: "Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents" authors: Xi Zhang, Meijun Gao, Yuntian Zhao, Xinyu Tan, Yilun Yao, Feiyu Wang, Yanshu Wang, Dingsiyi, et al. year: 2026 venue: arXiv url: https://arxiv.org/abs/2605.19604 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-05-19 updated_at: 2026-05-19 status: queued relevance: high topics:

• rag
• reasoning
• tool-use
• workflow-agent methods:

benchmarks:

models:

datasets:

• cs.AI related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 14 collection_queries: function-calling

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: function-calling
• inferred topics: rag, reasoning, tool-use, workflow-agent
• arXiv categories: cs.AI
• collection score: 14

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2605.19604