From sugar shortages to military contracts, World War II helped make M&Ms and Hershey's bars into symbols of American abundance. A 1940s Milky Way ad shows candy keeping pilots smiling through the war. Breakthroughs, discoveries, and DIY tips sent every weekday. Every year, Hershey manufactures 373 million of its signature milk chocolate bars . While the company doesn't release exact stats on Halloween sales, you can bet a lot of those end up in plastic Jack O'Lantern-shaped pails.

The advantages of pre-trained large language models (LLMs) are apparent in a variety of language processing tasks. But can a language model's knowledge be further harnessed to effectively disambiguate objects and navigate decision-making challenges within the realm of robotics? Our study reveals the LLM's aptitude for solving complex decision making challenges that are often previously modeled by Partially Observable Markov Decision Processes (POMDPs). A pivotal focus of our research is the object disambiguation capability of LLMs. We detail the integration of an LLM into a tabletop environment disambiguation task, a decision making problem where the robot's task is to discern and retrieve a user's desired object from an arbitrarily large and complex cluster of objects. Despite multiple query attempts with zero-shot prompt engineering (details can be found in the Appendix), the LLM struggled to inquire about features not explicitly provided in the scene description. In response, we have developed a few-shot prompt engineering system to improve the LLM's ability to pose disambiguating queries. The result is a model capable of both using given features when they are available and inferring new relevant features when necessary, to successfully generate and navigate down a precise decision tree to the correct object--even when faced with identical options.

Large Language Models (LLMs) have limited performance when solving arithmetic reasoning tasks and often provide incorrect answers. Unlike natural language understanding, math problems typically have a single correct answer, making the task of generating accurate solutions more challenging for LLMs. To the best of our knowledge, we are not aware of any LLMs that indicate their level of confidence in their responses which fuels a trust deficit in these models impeding their adoption. To address this deficiency, we propose `MathPrompter', a technique that improves performance of LLMs on arithmetic problems along with increased reliance in the predictions. MathPrompter uses the Zero-shot chain-of-thought prompting technique to generate multiple Algebraic expressions or Python functions to solve the same math problem in different ways and thereby raise the confidence level in the output results. This is in contrast to other prompt based CoT methods, where there is no check on the validity of the intermediate steps followed. Our technique improves over state-of-the-art on the MultiArith dataset ($78.7\%\rightarrow92.5\%$) evaluated using 175B parameter GPT-based LLM.

Collaborative robots (cobots) have begun to make their mark on manufacturing floors, and now they have entered the retail domain. In a world-first, robotic retail technology pioneer Niska has brought to the Australian market an interactive retail experience that incorporates cutting edge robotics and artificial intelligence technology. The store opened in Melbourne today (17 September). The project, three years in the making, saw Niska collaborate with robotics companies ABB, KUKA and Soft Bank Robotics; engineering company Special Patterns; UNSW; and Phosphor. Consulting on the robotics technology was Greg Sale, director of consulting firm Manufacturing, Technology & Marketing.