GoSkills converts flat skill lists into role-labeled execution contexts via anchor-centered groups and graph expansion, preserving coverage and improving rewards on SkillsBench and ALFWorld under small skill budgets.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Re-analysis of MCP-grounded CTF agent runs shows Skills add only 8.9 pp (p=0.71) when tool feedback is strict and low-latency, supporting the hypothesis that high environment-feedback bandwidth reduces the marginal value of curated procedural knowledge.
citing papers explorer
-
Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
GoSkills converts flat skill lists into role-labeled execution contexts via anchor-centered groups and graph expansion, preserving coverage and improving rewards on SkillsBench and ALFWorld under small skill budgets.
-
When Skills Don't Help: A Negative Result on Procedural Knowledge for Tool-Grounded Agents in Offensive Cybersecurity
Re-analysis of MCP-grounded CTF agent runs shows Skills add only 8.9 pp (p=0.71) when tool feedback is strict and low-latency, supporting the hypothesis that high environment-feedback bandwidth reduces the marginal value of curated procedural knowledge.