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

Source: [arXiv](https://arxiv.org/abs/2608.20274v1)  
Feed7 permalink: https://feed7.dev/p/2608-20274v1-08ujug8  
Published: 2026-08-20T17:12:08.000Z  
Trust: Needs Review (needs_review)

## Why Included

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.

## 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.

## Connected Context

Feed7 judgment across 525 accumulated Signals:

This makes accumulated agent learning more selective than the prior “capture every lesson” pattern: reusable memory should be decomposed into small textual procedures and retrieved by joint specificity and breadth. It also gives a structural explanation for skill regressions—whole-task solutions can transfer worse than no memory—while leaving the proposed utility score’s generality unresolved without task and effect-size details.

- [The Regression Tax: Decomposing Why Skills Help and Hurt LLM Agents](https://feed7.dev/p/2607-22520v1-0mz9wnf) — It reinforces the documented regression tax and narrows a likely cause: task-level skills often hurt, whereas smaller subtask procedures transfer better on average.
- [SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent](https://feed7.dev/p/2608-07449v1-1co8km3) — SkillProx supplies the maintenance consequence of this result: candidate procedures should be tested for transfer, rolled back on regression, and pruned when utility is low.
- [The Era of Compound Engineering — Kieran Klaassen, Every/Cora](https://feed7.dev/p/the-era-of-compound-engineering-kieran-klaassen-every-cora-053chml) — It qualifies compound engineering’s lesson-capture strategy by showing that persistence alone is insufficient; lessons need subtask-level decomposition and relevance-aware retrieval.
- [EveryInc/compound-engineering-plugin](https://feed7.dev/p/compound-engineering-plugin-06exf60) — The plugin is a concrete repository workflow for durable skills, while this study suggests its captured plans and solved-problem notes should be distilled into small textual procedures rather than reused wholesale.

## Context Map

- Layer: agent
- Domains: None
- Topics: skills, agent-memory, agent-reliability

## Uncertainty

- 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.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.