The evolution of large language models (LLMs) has enhanced the planning capabilities of language agents in diverse real-world scenarios. Despite these advancements, the potential of LLM-powered agents to comprehend ambiguous user instructions for reasoning and decision-making is still under exploration. In this work, we introduce a new task, Proactive Agent Planning, which requires language agents to predict clarification needs based on user-agent conversation and agent-environment interaction, invoke external tools to collect valid information, and generate a plan to fulfill the user's demands. To study this practical problem, we establish a new benchmark dataset, Ask-before-Plan. To tackle the deficiency of LLMs in proactive planning, we propose a novel multi-agent framework, Clarification-Execution-Planning (\texttt{CEP}), which consists of three agents specialized in clarification, execution, and planning. We introduce the trajectory tuning scheme for the clarification agent and static execution agent, as well as the memory recollection mechanism for the dynamic execution agent. Extensive evaluations and comprehensive analyses conducted on the Ask-before-Plan dataset validate the effectiveness of our proposed framework.

Pretrained large language models (LLMs) are surprisingly effective at performing zero-shot tasks, including time-series forecasting. However, understanding the mechanisms behind such capabilities remains highly challenging due to the complexity of the models. In this paper, we study LLMs' ability to extrapolate the behavior of dynamical systems whose evolution is governed by principles of physical interest. Our results show that LLaMA 2, a language model trained primarily on texts, achieves accurate predictions of dynamical system time series without fine-tuning or prompt engineering. Moreover, the accuracy of the learned physical rules increases with the length of the input context window, revealing an in-context version of neural scaling law. Along the way, we present a flexible and efficient algorithm for extracting probability density functions of multi-digit numbers directly from LLMs.

This work focuses on reducing neural network size, which is a major driver of neural network execution time, power consumption, bandwidth, and memory footprint. A key challenge is to reduce size in a manner that can be exploited readily for efficient training and inference without the need for specialized hardware. We propose Self-Compression: a simple, general method that simultaneously achieves two goals: (1) removing redundant weights, and (2) reducing the number of bits required to represent the remaining weights. This is achieved using a generalized loss function to minimize overall network size. In our experiments we demonstrate floating point accuracy with as few as 3% of the bits and 18% of the weights remaining in the network.

Ancient Greek historians have now an artificial intelligence (AI) tool to help decipher texts. Being a scholar in ancient Greek is difficult. The primary texts, on stone that may have been chipped and weathered through time, are frequently damaged beyond repair and hard to decipher, but a recent tool by Google's DeepMind hopes to solve that using artificial intelligence. The application is rather unusual because it uses AI, in a useful way outside of the technology world. DeepMind's Ithaca, a machine learning model, makes surprisingly accurate guesses at missing words and the location and dates of ancient Greek texts.

Just like how we learn from our environment and our actions determine whether we are rewarded or punished, so do reinforcement learning agents whose ultimate aim is to maximise the rewards. This article brings the top 8 reinforcement learning innovations that shaped AI across several industries in 2022. Alphabet's DeepMind collaborated with the University of Venice, the University of Oxford and the Athens University of Economics and Business to build a deep neural network called'Ithaca', which can restore missing text from ancient texts. In a paper published in Nature, DeepMind stated that Ithaca was trained using natural language processing (NLP) to not only recover lost ancient text that has been damaged over time but also identify the original location of the text and establish the date when it was made. With DeepMind's latest release AlphaTensor, an AI system (based on a 3D board game), researchers shed light on a 50-year-old fundamental mathematics question of finding the fastest way to multiply two matrices.

Artificial intelligence (AI) is usually associated with getting us to the future faster, but it can also be a powerful tool in uncovering the past. Here are 6 ways the technology is being used around the world to help us understand the past and prepare for the future. An inscription showing Algorithm helping historians restore Greek inscriptions. An AI algorithm called Ithaca is helping historians restore ancient Greek inscriptions. Researchers at British AI firm DeepMind trained the algorithm on around 60,000 ancient Greek texts from across the Mediterranean that were written between 700 BC and AD 500.

In March 2022 DeepMind, an artificial intelligence company, announced it had developed Ithaca, a deep neural network trained to restore and attribute ancient Greek inscriptions. It uses artificial neural networks that are modeled on the way neurons in the human brain communicate, with multiple layers of processing that are used to extract progressively higher-level features from the data. By recognizing patterns in elements such as language choice and style, across such an extensive database, the theory is that Ithaca will be able to fill in the blanks of damaged inscriptions based on probability. In other words, the highest accuracy rate was achieved when historians' expertise and contextual knowledge were combined with Ithaca's ability to detect statistical patterns across tens of thousands of inscriptions. Whatever Ithaca has to offer epigraphic restoration, the emphasis on assisting rather than replacing historians with AI is entirely prudent because of the way humans and machines can complement each other's strengths and mitigate each other's weaknesses.

In March 2022 DeepMind, an artificial intelligence company, announced it had developed Ithaca, a deep neural network trained to restore and attribute ancient Greek inscriptions. Ancient Greek inscriptions have shaped our understanding of the Mediterranean world from 800BC to late antiquity. Inscriptions refer to text written on durable materials such as stone and pottery. Unfortunately, these materials are typically not durable enough to remain perfectly preserved for two millennia. Therefore, the epigraphic evidence of this period is often damaged by the time it is uncovered and the inscribed texts are incomplete as a result.

The earliest form of writing originated nearly 5000 years ago in Mesopotamia (present-day Iraq), representing the Sumerian language. However, these early manuscripts, inscriptions, manuals have suffered the wrath of time. Historians have long worried about the missing texts that could give an insight into the life and culture of ancient civilisation, Artificial Intelligence has now come to their aid. Named after the Greek island in Homer's Odyssey, Ithaca, the first deep neural network will help in not only restoring the missing text of damaged inscriptions, but also identifying their original location, and establishing the date they were written. Designed to assist and expand the historian's workflow, this AI has achieved 62 per cent accuracy when restoring damaged texts and improved the accuracy of historians from 25 per cent to 72 per cent.

AI is helping historians rewrite history, literally. A new study published in the journal Nature reports that AI can fill in gaps in ancient Greek inscriptions and indicate where and when they were made. The article notes that "over the centuries, many inscriptions have been damaged to the point of illegibility, moved far from their original place, and the date of their writing is in a state of uncertainty." According to TRTWorld, the researchers claim that the new artificial intelligence system they have developed can not only accurately read ancient Greek inscriptions, but also fill in gaps in the text caused by damage, and even determine their chronological and geographical location. Dr. Thea Sommerschild is a co-author of a study conducted by Ca' Foscari University of Venice, Harvard University, and artificial intelligence company DeepMind. Explaining the importance of the inscriptions for historians, she said that they are evidence of the thought, language, society and history of ancient civilizations, as they were written directly by the people of those times, reports the Guardian.