NTILC: Neural Tool Invocation via Learned Compression 事件

NTILC: Neural Tool Invocation via Learned Compression arXiv:2606.06566v1 Announce Type: cross Abstract: Agentic tool-calling language models depend on large registries of callable APIs, functions, and local actions. Placing full tool specifications directly in the prompt incurs a cost that scales linearly with the size of the tool registry, rapidly consuming the context budget. As the registry grows, this leads to higher latency and degrades selection accuracy, particularly due to interference