Search papers, labs, and topics across Lattice.
This paper introduces Skill Retrieval Augmentation (SRA), a paradigm where agents dynamically retrieve and apply relevant skills from a large external corpus, addressing the context window limitations of explicitly enumerating skills. They construct SRA-Bench, a benchmark with 5,400 test instances and a large-scale skill corpus, to evaluate skill retrieval, incorporation, and execution. Experiments demonstrate that SRA improves agent performance, but also reveals a bottleneck in skill incorporation, as LLMs struggle to determine when and which skill to load.
Explicitly enumerating skills in-context doesn't scale for agentic LLMs, but retrieving skills on demand can substantially improve performance – if the LLM can figure out when and which skill to load.
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.
Tsinghua AI