Using Large Language Models (LLMs) to produce robot programs from natural language has allowed for robot systems that can complete a higher diversity of tasks. However, LLM-generated programs may be faulty, either due to ambiguity in instructions, misinterpretation of the desired task, or missing information about the world state. As these programs run, the state of the world changes and they gather new information. When a failure occurs, it is important that they recover from the current world state and avoid repeating steps that they they previously completed successfully. We propose RoboRepair, a system which traces the execution of a program up until error, and then runs an LLM-produced recovery program that minimizes repeated actions. To evaluate the efficacy of our system, we create a benchmark consisting of eleven tasks with various error conditions that require the generation of a recovery program. We compare the efficiency of the recovery program to a plan built with an oracle that has foreknowledge of future errors.

ChatGPT is getting all the attention as of late, but modern AI technologies have a range of use cases beyond finally making Bing useful. One emerging trend is putting AI to work to aid with the frustrating and laborious task of filing and auditing corporate expense reports. Today, Microsoft and American Express announced a deal that aims to do just that. The companies agreed to expand their decades-long partnership to build solutions that leverage Microsoft Cloud and AI technologies, starting with expense report management. According to Amex, the initial solution will leverage machine learning and AI to automate expense reporting and approvals.

Managing expenses isn't a task that many people particularly love to work on, yet it's a vital one and can have enormous ramifications for a business if not handled properly. If you'd like to find a way to spend less time sorting out this area of your organizational finances and reduce problems simultaneously, it's worth turning to technology. Thanks to artificial intelligence (AI), expense management is becoming easier and more effective than ever. In many organizations, a lack of space or too much paperwork to store leads to a lot of stress and time spent attempting to locate files. If this is a pain point in your venture, AI can help at least limit expense-based paperwork, among other things.

In development for more than a year, Auto-Itemization from TripActions Liquid is a solution that automatically splits transactions and attributes each line item to specific expense policies. The technology allows a user to upload a receipt for automatic itemisation; using AI, foreign language translation and fuzzy matching, each line item is categorised and assigned to a specific policy with 90 per cent accuracy. The use of machine learning also ensures that accuracy will increase over time. Single transactions often consist of multiple parts or line items -- like variable daily service charges for a hotel stay -- that need to be reported independently for accounting and tax purposes. The cost of the room needs to align with a company's hotel policy, while the room service that employee orders can align to a per diem for meal costs.

All businesses need a system to accurately track their expenses. Without it, they would not be able to keep reliable records and would likely soon find themselves in financial trouble. To track expenses, most businesses rely on some form of expense management software. However, not all expense management software options are created equal. One such example is expense management software that's powered by AI.

The pandemic has brought about significant changes in employee spend and expense behavior. As workers transitioned from the office to working from home, uncertainty about what was an allowable expense led to accidental policy violations for many companies. In fact, we see in SAP Concur data that the proportion of expenses categorized as "Other" increased by 58% from 2019 to 2020. The pandemic has undoubtedly heightened the business need around enhanced audit capability. The SAP Concur organization has a rich history of developing technologies that address the needs of the biggest companies in the world, all the way down to very small businesses. Verify, a new SAP Concur offering, discovers potential spend issues for customers of all sizes.

Airbus SE is using artificial intelligence to squeeze cost out of its finance function, an experiment launched in the aircraft maker's Americas division that could save the corporation millions of dollars annually if rolled out in other regions. It's one of the latest examples of how companies across sectors are digitizing operations to increase efficiency, reduce human error and free up employees for tasks that require more human judgment, such as strategic planning, analysis and audits. "Companies can now automate highly repetitive activity at a lower cost with a higher degree of accuracy," said David Axson, head of the CFO consulting practice at Accenture Strategy, a unit of consulting firm Accenture PLC. "This especially applies to high-volume-use cases like accounts payable." Less than half of companies' accounts-payable activity worldwide is currently automated, Accenture Strategy says.

Appen is a Business Reporter client. There are varying differences behind each CFO's strategic plan. In my experience, short-term CFOs focus on cost-cutting to save money and manage the bottom line. However, forward-looking CFOs manage not only the bottom line but also the top line. They care about growing market share, revenue and the long-term financial health of the business, as well as competitive positioning.

These are among the expenses employees bill to their companies, according to AppZen, a provider of financial software. You've got to hand it to them, employees are certainly creative in their perceptions of what constitutes business expenses. Businesses process an average of 100,000 expense reports and 700,000 invoices a year, and that means suspect expenses are falling through the cracks, according to AppZen's The State of Business Spend report for Q4 2019. The problem is that most modern invoice automation systems can look out for two invoices with the same invoice number, or the same amount, and stop a payment that appears to be a duplicate, according to AppZen. But they don't find typos in invoice numbers, duplicates across expense and AP systems – or, ahem, interesting items employees bill to their employers.

With the wealth of cloud-based finance and accounting tools available, it's tempting to think that the digital transformation of the finance department is nearly complete. But many of today's tools simply digitize cumbersome processes and workflows -- take expense management solutions as a prime example, which rely on the old paper-based expense report metaphor. Systems like these still require a huge amount of manual processing and data input, particularly from controllers and accounting teams. Because today's tools don't address the underlying issues perpetuated by traditional workflows, finance teams spend far too much time chasing down missing information, aggregating data, and correcting errors instead of focusing on more strategic and impactful activities, as reported in a recent study on operational challenges for finance teams. The next wave of technology, powered by advanced automation and AI, will completely transform the complete expense process, streamlining workflows and integrating real-time data so that finance teams only need to focus on the issues that matter most.