arXivPaperNeeds Review
Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agents
Reusable agent skills transferred better when induced from subtasks and stored as text. Whole-task skills often hurt versus no memory, so retrieval alone is not evidence that a memory helps.
arXiv
Source Summary
The study compares task-level against subtask-level skill induction and text against code formats. **Task-level skills often fell below the no-memory baseline**, while **subtask-level skills improved performance on average**; text transferred better than code.
Practical Implication
Build agent memory from small, reusable procedures and prefer textual guidance unless execution requires code. Before retrieval, score candidates for both task specificity and breadth of relevance rather than assuming any prior solution will help.
Agent-Ready Context
The study compares task-level against subtask-level skill induction and text against code formats. **Task-level skills often fell below the no-memory baseline**, while **subtask-level skills improved performance on average**; text transferred better than code. Build agent memory from small, reusable procedures and prefer textual guidance unless execution requires code. Before retrieval, score candidates for both task specificity and breadth of relevance rather than assuming any prior solution will help. Neither specificity nor abstractness predicted outcomes alone. Their combined **skill utility score** correlated with transfer performance and requires only skills plus task descriptions, but the supplied material gives no tasks, models, or effect sizes for judging generality.
Context Map
agent#skills#agent-memory#agent-reliabilityUncertainty
Neither specificity nor abstractness predicted outcomes alone. Their combined **skill utility score** correlated with transfer performance and requires only skills plus task descriptions, but the supplied material gives no tasks, models, or effect sizes for judging generality.