Language is a powerful communicative and cognitive tool. It enables humans to express thoughts, share intentions, and reason about complex phenomena. Despite our fluency in using and understanding language, the question of how it arises and evolves over time remains unsolved. A leading hypothesis in linguistics and anthropology posits that language evolved to meet the ecological and social demands of early human cooperation. Language did not arise in isolation, but through shared survival goals. Inspired by this view, we investigate the emergence of language in multi-agent Foraging Games. These environments are designed to reflect the cognitive and ecological constraints believed to have influenced the evolution of communication. Agents operate in a shared grid world with only partial knowledge about other agents and the environment, and must coordinate to complete games like picking up high-value targets or executing temporally ordered actions. Using end-to-end deep reinforcement learning, agents learn both actions and communication strategies from scratch. We find that agents develop communication protocols with hallmark features of natural language: arbitrariness, interchangeability, displacement, cultural transmission, and compositionality. We quantify each property and analyze how different factors, such as population size, social dynamics, and temporal dependencies, shape specific aspects of the emergent language. Our framework serves as a platform for studying how language can evolve from partial observability, temporal reasoning, and cooperative goals in embodied multi-agent settings. We will release all data, code, and models publicly.

Much discussion about large language models and language-and-vision models has focused on whether these models are intelligent agents. We present an alternative perspective. We argue that these artificial intelligence models are cultural technologies that enhance cultural transmission in the modern world, and are efficient imitation engines. We explore what AI models can tell us about imitation and innovation by evaluating their capacity to design new tools and discover novel causal structures, and contrast their responses with those of human children. Our work serves as a first step in determining which particular representations and competences, as well as which kinds of knowledge or skill, can be derived from particular learning techniques and data. Critically, our findings suggest that machines may need more than large scale language and images to achieve what a child can do.

DeepMind's researchers are working round the clock to push the frontiers of AI. The lab has published 34 research papers in the last four months. Let's look at the key papers the Alphabet subsidiary has published in 2022. The paper found the model size and the training dataset size should be scaled in equal measure for compute-optimal training. The researchers tested the theory by training a compute-optimal model, Chinchilla, using the same compute budget as Gopher but with 70B parameters and 4x more data.

One of the fundamental questions of cultural evolutionary research is how individual-level processes scale up to generate population-level patterns. Previous studies in music have revealed that frequency-based bias (e.g. conformity and novelty) drives large-scale cultural diversity in different ways across domains and levels of analysis. Music sampling is an ideal research model for this process because samples are known to be culturally transmitted between collaborating artists, and sampling events are reliably documented in online databases. The aim of the current study was to determine whether frequency-based bias has played a role in the cultural transmission of music sampling traditions, using a longitudinal dataset of sampling events across three decades. Firstly, we assessed whether turn-over rates of popular samples differ from those expected under neutral evolution. Next, we used agent-based simulations in an approximate Bayesian computation framework to infer what level of frequency-based bias likely generated the observed data. Despite anecdotal evidence of novelty bias, we found that sampling patterns at the population-level are most consistent with conformity bias.

Consider a collaborative task that requires communication. Two agents are placed in an environment and must create a language from scratch in order to coordinate. Recent work has been interested in what kinds of languages emerge when deep reinforcement learning agents are put in such a situation, and in particular in the factors that cause language to be compositional-i.e. meaning is expressed by combining words which themselves have meaning. Evolutionary linguists have also studied the emergence of compositional language for decades, and they find that in addition to structural priors like those already studied in deep learning, the dynamics of transmitting language from generation to generation contribute significantly to the emergence of compositionality. In this paper, we introduce these cultural evolutionary dynamics into language emergence by periodically replacing agents in a population to create a knowledge gap, implicitly inducing cultural transmission of language. We show that this implicit cultural transmission encourages the resulting languages to exhibit better compositional generalization and suggest how elements of cultural dynamics can be further integrated into populations of deep agents.

Web services are basic functions of a software system to support the concept of service-oriented architecture. They are often composed together to provide added values, known as web service composition. Researchers often employ Evolutionary Computation techniques to efficiently construct composite services with near-optimized functional quality (i.e., Quality of Semantic Matchmaking) or non-functional quality (i.e., Quality of Service) or both due to the complexity of this problem. With a significant increase in service composition requests, many composition requests have similar input and output requirements but may vary due to different preferences from different user segments. This problem is often treated as a multi-objective service composition so as to cope with different preferences from different user segments simultaneously. Without taking a multi-objective approach that gives rise to a solution selection challenge, we perceive multiple similar service composition requests as jointly forming an evolutionary multi-tasking problem in this work. We propose an effective permutation-based evolutionary multi-tasking approach that can simultaneously generate a set of solutions, with one for each service request. We also introduce a neighborhood structure over multiple tasks to allow newly evolved solutions to be evaluated on related tasks. Our proposed method can perform better at the cost of only a fraction of time, compared to one state-of-art single-tasking EC-based method. We also found that the use of the proper neighborhood structure can enhance the effectiveness of our approach.

The science-fiction writer Robert Heinlein once wrote, "Each generation thinks it invented sex." He was presumably referring to the pride each generation takes in defining its own sexual practices and ethics. But his comment hit the mark in another sense: Every generation has to reinvent sex because the previous generation did a lousy job of teaching it. In the United States, the conversations we have with our children about sex are often awkward, limited, and brimming with euphemism. At school, if kids are lucky enough to live in a state that allows it, they'll get something like 10 total hours of sex education.1

The science-fiction writer Robert Heinlein once wrote, "Each generation thinks it invented sex." He was presumably referring to the pride each generation takes in defining its own sexual practices and ethics. But his comment hit the mark in another sense: Every generation has to reinvent sex because the previous generation did a lousy job of teaching it. In the United States, the conversations we have with our children about sex are often awkward, limited, and brimming with euphemism. At school, if kids are lucky enough to live in a state that allows it, they'll get something like 10 total hours of sex education.1

Research has found that bumblebees are capable of learning how to pull strings in exchange of a reward -- specifically food -- and also pass on the ability to do so to other bees. This reportedly marks the first instance where this experiment to test intelligence has proved successful with an insect. The study, by researchers from the Queen Mary University of London, was published Tuesday in the journal PLOS Biology and showed that certain "innovator bees" were able to pull a string to reach sugar water by themselves and in turn, train their "naïve" counterparts to do the same. "We found that when the appropriate social and ecological conditions are present, culture can be mediated by the use of a combination of simple forms of learning," lead author Sylvain Alem said in a press release. "Thus, cultural transmission does not require the high cognitive sophistication specific to humans, nor is it a distinctive feature of humans."