Models & Labs
Google Unveils Agentic RAG for Complex Queries
Google Research Bloghigh confidence
Why it matters
- →The agentic RAG framework significantly improves the accuracy of complex query responses by 34%.
- →It introduces a multi-agent system that ensures all necessary context is gathered before generating an answer.
- →This advancement transforms enterprise query management by providing more reliable and comprehensive information.
Google has introduced a new agentic RAG framework designed to enhance the accuracy of responses to complex enterprise queries. This system, developed in collaboration with Google Cloud, employs a multi-agent workflow that iteratively searches for context across various data sources. Unlike traditional RAG systems, the agentic RAG framework includes a Sufficient Context Agent that identifies missing information and prompts further searches, resulting in a 34% improvement in accuracy on factuality datasets. This innovation allows for more dependable and comprehensive answers to intricate business questions.
Read originalMore from Google Research Blog
More in Models & Labs
Models & Labsmodels
llama.cpp b10955 release addresses heap corruption
The latest release of llama.cpp, b10955, tackles a critical issue of heap corruption by disabling the ggml-cpu precompiled header and fixing CACHE_LINE_SIZE ambiguity. This update ensures consistent CACHE_LINE_SIZE values across C++ kernels and C work-buffer sizing code, preventing heap-buffer-overflow and subsequent crashes. By restoring the natural include order and removing the std::hardware_destructive_interference_size branch, the update makes the value deterministic and include-order independent. This release is a technical fix that stabilizes the runtime environment for developers using llama.cpp.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10956 release enhances SYCL backend
The latest llama.cpp release, b10956, introduces significant improvements to the SYCL backend, particularly for handling large k values in TOP_K operations. By implementing a radix select method, the update allows for efficient GPU-resident processing, avoiding previous limitations that forced operations to fall back to the CPU. This change enhances performance, especially in scenarios requiring large k values, such as qwen4exp's sparse-attention indexer. The update ensures that operations are more efficient and scalable, providing a notable boost in processing speed without regressing any measured shapes.