paper-with-me

홈 › Papers

Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries

2026-05-07 · Kun Zeng, Yu Huo, Siyu Zhang, Zi Ye, Yuecheng Zhuo, Haoyue Liu, Yuquan Lu, Junhao Wen, Xiaoying Tang arxiv

Skill-augmented agents increasingly rely on large reusable skill libraries, but retrieving relevant skills is not the same as presenting usable context. Existing methods typically return atomic skills or dependency-aware bundles whose internal roles remain implicit, leaving the agent to infer the execution entry point, support skills, visible requirements, and failure-avoidance guidance. We introduce Group of Skills (GoSkills), an inference-time group-structured retrieval method that changes the agent-facing retrieval object from a flat skill list to a compact, role-labeled execution context. GoSkills builds anchor-centered skill groups from a typed skill graph, expands support groups through a group graph, bottlenecks the selected group plan into a bounded set of atomic skill payloads, and renders a fixed execution contract with Start, Support, Check, and Avoid fields, without changing the downstream agent, skill payloads, or execution environment. Experiments on SkillsBench and ALFWorld show that GoSkills preserves visible-requirement coverage under a small skill budget, improves over flat skill-access baselines, and often improves reward and agent-only runtime relative to structural retrieval references.

📄 PDF Abstract BibTeX arXiv:2605.06978

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Co-Evolving Skill Generation and Policy Optimization

2026-06-07 · Zhiwei Zhang, Yudi Lin, Nikki Lijing Kuang, Linlin Wu 외 arxiv

Skill-augmented reinforcement learning improves language agents by storing reusable procedural knowledge acquired from past experience. Existing methods typically use strong language models to analyze trajectories, gener…

Reinforcement Learning

SKILLBERT: “SKILLING” THE BERT TO CLASSIFY SKILLS!

2021-03-08 · Anonymous

In the age of digital recruitment, job posts can attract a large number of applications, and screening them manually can become a very tedious task. We propose a BERT-based model, SkillBERT, the embeddings of which are u…

Multi-Label ClassificationMUlTI-LABEL-ClASSIFICATION

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

2026-04-02 · Zhengxi Lu, Zhiyuan Yao, Jinyang Wu, Chengcheng Han 외 arxiv

Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a reliable mechanism for augmenting LLM agents. Yet inference-time skill augm…

Reinforcement Learning

SkillBERT: “Skilling” the BERT to classify skills!

2021-01-01 · Amber Nigam, Shikha Tyagi, Kuldeep Tyagi, Arpan Saxena

In the age of digital recruitment, job posts can attract a large number of applications, and screening them manually can become a very tedious task. These recruitment records are stored in the form of tables in our recru…

Clustering

Using customized GPT to develop prompting proficiency in architectural AI-generated images

2025-04-16 · Juan David Salazar Rodriguez, Sam Conrad Joyce, Julfendi

This research investigates the use of customized GPT models to enhance prompting proficiency among architecture students when generating AI-driven images. Prompt engineering is increasingly essential in architectural edu…

Experimental DesignPrompt Engineering