paper-with-me

Papers

Skill Retrieval Augmentation for Agentic AI

2026-04-27 · Weihang Su, Jianming Long, Qingyao Ai, Qiaozhi He, Yichen Tang, Changyue Wang, Yiteng Tu, Yingbo Wang, Yiqun Liu arxiv

As large language models (LLMs) evolve into agentic problem solvers, they increasingly rely on external, reusable skills to handle tasks beyond their native parametric capabilities. In existing agent systems, the dominant strategy for incorporating skills is to explicitly enumerate available skills within the context window. However, this strategy fails to scale: as skill corpora expand, context budgets are consumed rapidly, and the agent becomes markedly less accurate in identifying the right skill. To this end, this paper formulates Skill Retrieval Augmentation (SRA), a new paradigm in which agents dynamically retrieve, incorporate, and apply relevant skills from large external skill corpora on demand. To make this problem measurable, we construct a large-scale skill corpus and introduce SRA-Bench, the first benchmark for decomposed evaluation of the full SRA pipeline, covering skill retrieval, skill incorporation, and end-task execution. SRA-Bench contains 5,400 capability-intensive test instances and 636 manually constructed gold skills, which are mixed with web-collected distractor skills to form a large-scale corpus of 26,262 skills. Extensive experiments show that retrieval-based skill augmentation can substantially improve agent performance, validating the promise of the paradigm. At the same time, we uncover a fundamental gap in skill incorporation: current LLM agents tend to load skills at similar rates, regardless of whether a gold skill is retrieved or whether the task actually requires external capabilities. This shows that the bottleneck in skill augmentation lies not only in retrieval but also in the base model's ability to determine which skill to load and when external loading is actually needed. These findings position SRA as a distinct research problem and establish a foundation for the scalable augmentation of capabilities in future agent systems.

📄 PDF Abstract BibTeX arXiv:2604.24594

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

2026-04-02 · Zhengxi Lu, Zhiyuan Yao, Jinyang Wu, Chengcheng Han 외 arxiv

Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a reliable mechanism for augmenting LLM agents. Yet inference-time skill augm…

Reinforcement Learning

Dynamic Dual-Granularity Skill Bank for Agentic RL

2026-03-30 · Songjun Tu, Chengdong Xu, Qichao Zhang, Yaocheng Zhang 외 arxiv

Agentic RL can benefit substantially from reusable experience, yet existing skill-based methods mainly extract trajectory-level guidance and often lack principled mechanisms for maintaining an evolving skill memory. We p…

UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation

2026-06-28 · Songjun Tu, Chengdong Xu, Qichao Zhang, Yiwen Ma 외 arxiv

Skill memories can improve agentic reinforcement learning by reusing past experience as textual guidance, but retrieved skills are not oracular: they may help in one state while misleading the same policy in another. Thi…

Reinforcement Learning

From Correctness to Preference: A Framework for Personalized Agentic Reinforcement Learning

2026-05-22 · Ranxu zhang, zeyang li, Jiacheng Huang, Rui Zhang 외 arxiv

Agentic reinforcement learning (Agentic RL) has achieved strong progress in tasks with clear success signals. However, many real-world agent applications require user-conditioned behavior: the same query may call for dif…

Reinforcement Learning

RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution

2026-08-27 · Junjie Zhang, Hui Liu, Kecheng Chen, Xianbo Mo 외 arxiv

LLM-based agents are increasingly deployed in product-level execution harnesses, where jailbreaks can trigger harmful tool use and persistent state changes, creating greater risks than unsafe text generation alone. Exist…

Text Generation