Large Language Models (LLMs) generalize well across language tasks, but suffer from hallucinations and uninterpretability, making it difficult to assess their accuracy without ground-truth. Retrieval-Augmented Generation (RAG) models have been proposed to reduce hallucinations and provide provenance for how an answer was generated. Applying such models to the scientific literature may enable large-scale, systematic processing of scientific knowledge. We present PaperQA, a RAG agent for answering questions over the scientific literature. PaperQA is an agent that performs information retrieval across full-text scientific articles, assesses the relevance of sources and passages, and uses RAG to provide answers. Viewing this agent as a question answering model, we find it exceeds performance of existing LLMs and LLM agents on current science QA benchmarks. To push the field closer to how humans perform research on scientific literature, we also introduce LitQA, a more complex benchmark that requires retrieval and synthesis of information from full-text scientific papers across the literature. Finally, we demonstrate PaperQA's matches expert human researchers on LitQA.

HMRC's use of AI and big data to gather evidence in tax investigations has led to a 30% drop in property raids, according to law firm Pinsent Masons. The firm explained that HMRC has leveraged sophisticated algorithms and big data sources to gather evidence with greater ease and efficiency than costly and time-consuming property raids. Steven Porter, Partner at Pinsent Masons, said: "HMRC's big brother-style data collection on taxpayers is giving it the material it needs to ramp up its tax investigations and at the same time, is reducing the need for it to actually raid properties." The figure has dropped from 669 property raids in 2016/17 to 471 last year. In particular, tax inspectors have been using the state-of-the-art Connect database, an analytical system worth £80m and designed by BAE Systems, to carry out preliminary investigative work within seconds.

In this scenario, neighbours have been complaining that something smelly is coming from a nearby house. You've been called to the scene. This is what you'd hear if you were on one of the eight military and civilian bomb squad teams competing in the Robot Rodeo last week, an annual event hosted by Sandia National Laboratories in New Mexico.