Tag
Liquid AI demonstrates using LFM2.5-ColBERT-350M as a filter to select only the five most relevant tools from 151 options, reducing latency and improving tool selection accuracy.
LFM2.5-ColBERT-350M is a model that reliably selects the most relevant tools from a set of 151, saving tokens and improving accuracy, ideal for agentic edge models.
This paper investigates over-privileged tool selection in LLM agents, introducing ToolPrivBench to evaluate and mitigate unnecessary use of high-privilege tools. It finds that safety alignment does not ensure least-privilege choices, and proposes a post-training defense that reduces excessive privilege use without sacrificing performance.
The author shares their experience switching from semantic embeddings to BM25 for tool selection in agents, finding that BM25 achieves 81% top-1 accuracy vs. 64% for embeddings on a corpus of 200 query-tool pairs, because tool descriptions are short and keyword-driven rather than semantically rich like documents.
A Japanese developer demonstrates how using Claude Code's "find skills" feature enables optimal tool selection for coding tasks.