Topic: schema

Adaption Labs has launched Invent a Dataset, a tool that creates training data based on task descriptions without needing a seed corpus or manual labeling, aiming to streamline the training process for machine learning models. This innovation could significantly reduce the time and effort required in preparing datasets, making model development more accessible and efficient.

marktechpost.com↗

The ggml/llama.cpp project released a fix for generating grammar in GBNF format for empty object schemas, addressing an issue that affects how the software handles certain JSON structures. This update is important as it enhances the robustness of schema processing, ensuring more accurate and comprehensive generation of grammars, which is crucial for the project's functionality and user experience.

Nexus introduces a depth-adaptive key-value cache and retrieval-decoupled tool routing to improve the efficiency of agentic large language models operating on the Model Context Protocol, addressing the issue of prefill time dominating due to growing tool registries. This innovation aims to reduce time-to-first-token (TTFT) by re-encoding fewer tool schemas each turn.

arxiv.org↗