#retrieval
Every summary, chronological. Filter by category, tag, or source from the rail.
Multiscale Indexing: Solving the Fixed Chunk Size Trap
Fixed chunk sizes are a form of lossy compression that creates a 20-40% recall gap. Instead of tuning chunk sizes, index data at multiple scales and use Reciprocal Rank Fusion (RRF) to merge results for significantly higher accuracy.
AI EngineerWhy BM25 is the Secret Weapon for Agentic Search
BM25 is seeing a resurgence in agentic workflows because LLMs act as 'super-users' who can write complex, multi-step queries that exploit the precision of lexical matching, which is often more effective and explainable than dense embeddings.
Scaling Agentic Search with Dynamic Workspace Expansion
DR-DCI improves agentic search by combining retriever-based scalability with local terminal-style operations, allowing agents to dynamically pull documents into a workspace for precise analysis.
Harness-1: Offloading Bookkeeping to Improve Search Agent Performance
Harness-1 improves retrieval performance by separating search policy from state management, using a stateful harness to handle bookkeeping and memory, allowing the 20B model to focus on semantic decisions.
Showing 4 of 4