While search-augmented large language models (LLMs) exhibit impressive capabilities, their reliability in complex multi-hop reasoning remains limited. This limitation arises from three fundamental challenges: decomposition errors, where tasks are incorrectly broken down; retrieval missing, where key evidence fails to be retrieved; and reasoning errors, where flawed logic propagates through the reasoning chain. A single failure in any of these stages can derail the final answer. We propose Erasable Reinforcement Learning (ERL), a novel framework that transforms fragile reasoning into a robust process. ERL explicitly identifies faulty steps, erases them, and regenerates reasoning in place, preventing defective logic from propagating through the reasoning chain. This targeted correction mechanism turns brittle reasoning into a more resilient process. Models trained with ERL, termed ESearch, achieve substantial improvements on HotpotQA, MuSiQue, 2Wiki, and Bamboogle, with the 3B model achieving +8.48% EM and +11.56% F1, and the 7B model achieving +5.38% EM and +7.22% F1 over previous state-of-the-art(SOTA) results. These findings suggest that erasable reinforcement learning provides a powerful paradigm shift for robust multi-step reasoning in LLMs.

These authors contributed equally to this work. Abstract The relationship between energy demand and variables such as economic activity and weather is well established. However, this paper aims to explore the connection between energy demand and other social aspects, which receive little attention. Through the use of natural language processing on a large news corpus, we shed light on this important link. This study was carried out in five regions of the UK and Ireland and considers multiple horizons from 1 to 30 days. It also considers economic variables such as GDP, unemployment and inflation. We found that: 1) News about military conflicts, transportation, the global pandemic, regional economics, and the international energy market are related to electricity demand. Electricity demand modelling is a fundamental process in power system planning, operation, and energy trading [1]. In order to avoid additional carbon emissions from excess electricity generation and the high costs of electricity storage, electricity demand and supply should be matched over time [2]. Demand forecasting has become a means of enabling power dispatch, planning generation schedules, and integrating renewable energy sources [3]. Electricity demand forecasting is linked to various factors, including weather, economic activity, and major events.

A study to test people's reactions to driverless cars has used a "ghost driver" to record their responses. The work, by the University of Nottingham, found that, in the absence of someone in the driving seat, pedestrians trust certain visual prompts more than others when deciding whether to cross the road. As part of the study, a car was driven around the university's campus over several days with its driver - research fellow David R. Large - concealed in the driver's seat. Mr Large, senior research fellow with the Human Factors Research Group at the university, said: "We wanted to explore how pedestrians would interact with a driverless car and developed this unique methodology to explore their reactions." Follow BBC East Midlands on Facebook, on Twitter, or on Instagram.

A hidden 17th Century garden that emerged during a heatwave has been shown in new drone footage. The European-style formal garden at the Chatsworth Estate in Derbyshire was designed in 1699 for the 1st Duke of Devonshire. It was grassed over 30 years later but substantial remains lie buried under just a thin layer of soil and grass, which has since been parched by the recent dry weather. While the historic design will not be fully restored any time soon, Steve Porter - head of gardens and landscape at Chatsworth - said he hoped the old garden, known as the Great Parterre, could be recreated with gravel once the grass had recovered. "Every time you look you almost see more of the detail, more of the scrolls of the beds and more of the paths and it sort of brings it all back to life and you realise just how intricate and just how amazing it would have been," he added. Follow BBC East Midlands on Facebook, Twitter, or Instagram.