Topically relevant skills can make LLM agents implement required elements incorrectly, omit them, or add expensive verification work, causing functional failures and efficiency regressions.
Differential testing for software,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Agent Skills Can Be Harmful: An Empirical Study of Skill-Induced Failures in LLM Agents
Topically relevant skills can make LLM agents implement required elements incorrectly, omit them, or add expensive verification work, causing functional failures and efficiency regressions.