https://traize.ai/en/research/feed.xml Traize research perspectives Our researchers explain recent advances in generative AI and what they mean for companies using it. 2026-09-14T00:00:00.000Z https://traize.ai/en/research/perspectives/contextual-document-embeddings/ Better search starts with the context of your documents 2026-09-14T00:00:00.000Z 2026-09-14T00:00:00.000Z Lukas Bierling A passage becomes easier to find when the search system understands where it belongs. Research on contextual embeddings explores how to preserve that information efficiently. https://traize.ai/en/research/perspectives/embedders-dilemma/ Similar retrieval scores, very different costs 2026-09-14T00:00:00.000Z 2026-09-14T00:00:00.000Z Lukas Bierling A new benchmark compares ten LLMs with 26 embedding models across 37 tasks. The results show why companies should decide carefully which work a language model does. https://traize.ai/en/research/perspectives/small-language-models-agents/ Why business agents make a strong case for small language models 2026-09-14T00:00:00.000Z 2026-09-14T00:00:00.000Z Lukas Bierling Business workflows contain many recurring, well-defined tasks. Specialised models could make these steps cheaper to run and easier to control. https://traize.ai/en/research/perspectives/small-model-reranking/ Teaching small models to find the evidence that matters 2026-09-14T00:00:00.000Z 2026-09-14T00:00:00.000Z Lukas Bierling Finding a related document is only the beginning. Research on specialised rerankers shows how compact models can learn to judge whether a passage actually helps answer a question.