Sign InOpen Brain
Back
arXivPaperNeeds ReviewagentNew

Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agents

Store small textual procedures, because subtask-level skills transferred better while whole-task skills often hurt performance.

arXivAug 20, 20262 min
Open SourceOpen MarkdownOpen JSON
Source Summary

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.

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-reliabilityGeneric AgentPrepare Coding Session
Uncertainty
Automatically selected from source material; feed7 has not independently tested the claim.
Rate This Item
Personal Note

No note yet. Notes are included in exported bundles.

Related — Every Edge Explained

No approved edges yet for this post.