Newest papers

Adaptive Skill Granularity for Coding Agents: Runtime Routing and Macro-to-Micro Recovery

Dingxuan Zhang, Yanhui Jiang, Jun Wang, Hefeng Zhou · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31461 · cited by 0 works (OpenAlex) · open-access PDF

Korean

재사용 가능한 기술은 대형 언어 모델 에이전트가 작업 특정 절차, 도구 affordances 및 구현 지침을 모듈 단위로 포장할 수 있도록 허용합니다. 이전 작업은 에이전트가 실행 전에 기술을 복구, 컴포지 또는 합성하는 방법을 크게 연구했습니다. 코딩 에이전트에서 실행은 작업 구조, 실행 상태 및 매크로 기술의 실패에 따라 추가적인 실행 시간 제어 문제를 제기합니다. 마크로를 시작하고 미세 수준 복구로 돌아 오는 원시 도구 호출, 마크로 기술 또는 하이브리드 실행을 통해 동일한 작업이 해결 될 수 있습니다. 우리는 기술의 granularity를 실행 구조, 실행 상태 및 마크로 기술 실패에 따라 조정된 액션 추상 정책으로 처리하는 프레임

Machine translation (Meta M2M100); the English original follows.

Abstract

Reusable skills allow large language model agents to package task-specific procedures, tool affordances, and execution guidance into modular units. Prior work has largely studied how agents retrieve, compose, or synthesize skills before execution. In coding agents, however, execution poses an additional runtime control problem: the same task may be solved through primitive tool calls, macro skills, or hybrid execution that starts with a macro and falls back to micro-level recovery. We introduce Adaptive Skill Granularity, a framework that treats skill granularity as an action-abstraction policy conditioned on task structure, execution state, and macro-skill failures. The system combines a feature-based granularity controller and a finite-state recovery executor. We evaluate the framework with a deterministic coding-agent protocol using verifier-defined success, total cost, and process metrics such as macro adoption, failure recovery, route match, and transition correctness. Results show that fixed macro execution is efficient when applicable but brittle under mismatch, while runtime routing and explicit macro-to-micro recovery improve robustness and recover controlled macro failures that fixed-granularity execution leaves unresolved. Our findings suggest that skill libraries for coding agents should be treated not only as retrievable resources, but also as controllable, verifiable, and recoverable execution abstractions.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Granularity, Modular design, Macro, Coding (social sciences), Distributed computing

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange