AI agents have been evaluated in isolation or within small groups, where interactions remain limited in scope and complexity. Large-scale simulations involving many autonomous agents -- reflecting the full spectrum of civilizational processes -- have yet to be explored. Here, we demonstrate how 10 - 1000+ AI agents behave and progress within agent societies. We first introduce the PIANO (Parallel Information Aggregation via Neural Orchestration) architecture, which enables agents to interact with humans and other agents in real-time while maintaining coherence across multiple output streams. We then evaluate agent performance in agent simulations using civilizational benchmarks inspired by human history. These simulations, set within a Minecraft environment, reveal that agents are capable of meaningful progress -- autonomously developing specialized roles, adhering to and changing collective rules, and engaging in cultural and religious transmission. These preliminary results show that agents can achieve significant milestones towards AI civilizations, opening new avenues for large simulations, agentic organizational intelligence, and integrating AI into human civilizations.

Similarity measures are fundamental tools for quantifying the alignment between artificial and biological systems. However, the diversity of similarity measures and their varied naming and implementation conventions makes it challenging to compare across studies. To facilitate comparisons and make explicit the implementation choices underlying a given code package, we have created and are continuing to develop a Python repository that benchmarks and standardizes similarity measures. The goal of creating a consistent naming convention that uniquely and efficiently specifies a similarity measure is not trivial as, for example, even commonly used methods like Centered Kernel Alignment (CKA) have at least 12 different variations, and this number will likely continue to grow as the field evolves. For this reason, we do not advocate for a fixed, definitive naming convention. The landscape of similarity measures and best practices will continue to change and so we see our current repository, which incorporates approximately 100 different similarity measures from 14 packages, as providing a useful tool at this snapshot in time. To accommodate the evolution of the field we present a framework for developing, validating, and refining naming conventions with the goal of uniquely and efficiently specifying similarity measures, ultimately making it easier for the community to make comparisons across studies.

What metrics should guide the development of more realistic models of the brain? One proposal is to quantify the similarity between models and brains using methods such as linear regression, Centered Kernel Alignment (CKA), and angular Procrustes distance. To better understand the limitations of these similarity measures we analyze neural activity recorded in five experiments on nonhuman primates, and optimize synthetic datasets to become more similar to these neural recordings. How similar can these synthetic datasets be to neural activity while failing to encode task relevant variables? We find that some measures like linear regression and CKA, differ from angular Procrustes, and yield high similarity scores even when task relevant variables cannot be linearly decoded from the synthetic datasets. Synthetic datasets optimized to maximize similarity scores initially learn the first principal component of the target dataset, but angular Procrustes captures higher variance dimensions much earlier than methods like linear regression and CKA. We show in both theory and simulations how these scores change when different principal components are perturbed. And finally, we jointly optimize multiple similarity scores to find their allowed ranges, and show that a high angular Procrustes similarity, for example, implies a high CKA score, but not the converse.

Highly autonomous generative agents powered by large language models promise to simulate intricate social behaviors in virtual societies. However, achieving real-time interactions with humans at a low computational cost remains challenging. Here, we introduce Lyfe Agents. They combine low-cost with real-time responsiveness, all while remaining intelligent and goal-oriented. Key innovations include: (1) an option-action framework, reducing the cost of high-level decisions; (2) asynchronous self-monitoring for better self-consistency; and (3) a Summarize-and-Forget memory mechanism, prioritizing critical memory items at a low cost. We evaluate Lyfe Agents' self-motivation and sociability across several multi-agent scenarios in our custom LyfeGame 3D virtual environment platform. When equipped with our brain-inspired techniques, Lyfe Agents can exhibit human-like self-motivated social reasoning. For example, the agents can solve a crime (a murder mystery) through autonomous collaboration and information exchange. Meanwhile, our techniques enabled Lyfe Agents to operate at a computational cost 10-100 times lower than existing alternatives. Our findings underscore the transformative potential of autonomous generative agents to enrich human social experiences in virtual worlds.

Planning is a data efficient decision-making strategy where an agent selects candidate actions by exploring possible future states. To simulate future states when there is a high-dimensional action space, the knowledge of one's decision making strategy must be used to limit the number of actions to be explored. We refer to the model used to simulate one's decisions as the agent's self-model. While self-models are implicitly used widely in conjunction with world models to plan actions, it remains unclear how self-models should be designed. Inspired by current reinforcement learning approaches and neuroscience, we explore the benefits and limitations of using a distilled policy network as the self-model. In such dual-policy agents, a model-free policy and a distilled policy are used for model-free actions and planned actions, respectively. Our results on a ecologically relevant, parametric environment indicate that distilled policy network for self-model stabilizes training, has faster inference than using model-free policy, promotes better exploration, and could learn a comprehensive understanding of its own behaviors, at the cost of distilling a new network apart from the model-free policy.

A vexing problem in artificial intelligence is reasoning about events that occur in complex, changing visual stimuli such as in video analysis or game play. Inspired by a rich tradition of visual reasoning and memory in cognitive psychology and neuroscience, we developed an artificial, configurable visual question and answer dataset (COG) to parallel experiments in humans and animals. COG is much simpler than the general problem of video analysis, yet it addresses many of the problems relating to visual and logical reasoning and memory -- problems that remain challenging for modern deep learning architectures. We additionally propose a deep learning architecture that performs competitively on other diagnostic VQA datasets (i.e. CLEVR) as well as easy settings of the COG dataset. However, several settings of COG result in datasets that are progressively more challenging to learn. After training, the network can zero-shot generalize to many new tasks. Preliminary analyses of the network architectures trained on COG demonstrate that the network accomplishes the task in a manner interpretable to humans.