Context engineering that sticks: drop the reranker, add memory, one architecture from rag search to robot action

Location: Venue 5 - 358

We demonstrate how a custom RAG system without rerankers achieves strong internal MRR (Mean Reciprocal Rank) and powers our agents. Then we transform the same context-engineering approach into robot memory: short-term buffers, episodic logs, and long-term knowledge graphs. This unified architecture bridges information retrieval and robotic action planning, showing how memory-augmented systems can maintain contextual understanding across diverse AI applications. We explore the technical implementation, performance comparisons, and practical benefits of memory-centric approaches over traditional reranking methods.