Paper Detail

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

Chenxi Wang, Zhuoyun Yu, Xin Xie, Wuguannan Yao, Runnan Fang, Shuofei Qiao, Kexin Cao, Guozhou Zheng, Xiang Qi, Peng Zhang, Shumin Deng

huggingface Score 14.0

Published 2026-04-06 · First seen 2026-04-07

General AI

Abstract

Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, repeatedly rediscover similar behaviors from limited experience, resulting in redundant exploration and poor generalization. To address this problem, we propose SkillX, a fully automated framework for constructing a plug-and-play skill knowledge base that can be reused across agents and environments. SkillX operates through a fully automated pipeline built on three synergistic innovations: (i) Multi-Level Skills Design, which distills raw trajectories into three-tiered hierarchy of strategic plans, functional skills, and atomic skills; (ii) Iterative Skills Refinement, which automatically revises skills based on execution feedback to continuously improve library quality; and (iii) Exploratory Skills Expansion, which proactively generates and validates novel skills to expand coverage beyond seed training data. Using a strong backbone agent (GLM-4.6), we automatically build a reusable skill library and evaluate its transferability on challenging long-horizon, user-interactive benchmarks, including AppWorld, BFCL-v3, and τ^2-Bench. Experiments show that SkillKB consistently improves task success and execution efficiency when plugged into weaker base agents, highlighting the importance of structured, hierarchical experience representations for generalizable agent learning. Our code will be publicly available soon at https://github.com/zjunlp/SkillX.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{wang2026skillx,
  title = {SkillX: Automatically Constructing Skill Knowledge Bases for Agents},
  author = {Chenxi Wang and Zhuoyun Yu and Xin Xie and Wuguannan Yao and Runnan Fang and Shuofei Qiao and Kexin Cao and Guozhou Zheng and Xiang Qi and Peng Zhang and Shumin Deng},
  year = {2026},
  abstract = {Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, repeatedly rediscover similar behaviors from limited experience, resulting in redundant exploration and poor generalization. To address this problem, we propose SkillX, a fully automated framework for constructing a plug-and-play skill knowledge base that can be reused across agents and environments. SkillX operates thr},
  url = {https://huggingface.co/papers/2604.04804},
  keywords = {self-evolving paradigms, skill knowledge base, multi-level skills design, iterative skills refinement, exploratory skills expansion, hierarchical experience representations, long-horizon benchmarks, user-interactive benchmarks, GLM-4.6, skill transferability, code available, huggingface daily},
  eprint = {2604.04804},
  archiveprefix = {arXiv},
}

Metadata

{}