Related papers: Meta-Diversity Search in Complex Systems, A Recipe…
We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inefficient. To tackle…
This Research through Design paper explores how object detection may be applied to a large digital art museum collection to facilitate new ways of encountering and experiencing art. We present the design and evaluation of an interactive…
The automation of scientific discovery represents a critical milestone in Artificial Intelligence (AI) research. However, existing agentic systems for science suffer from two fundamental limitations: rigid, pre-programmed workflows that…
We consider enhancing large language models (LLMs) for complex planning tasks. While existing methods allow LLMs to explore intermediate steps to make plans, they either depend on unreliable self-verification or external verifiers to…
Current Neural Architecture Search techniques can suffer from a few shortcomings, including high computational cost, excessive bias from the search space, conceptual complexity or uncertain empirical benefits over random search. In this…
Recommender systems use data on past user preferences to predict possible future likes and interests. A key challenge is that while the most useful individual recommendations are to be found among diverse niche objects, the most reliably…
We introduce a new artificial intelligence (AI) approach called, the 'Digital Synaptic Neural Substrate' (DSNS). It uses selected attributes from objects in various domains (e.g. chess problems, classical music, renowned artworks) and…
The emerging field of Diverse Intelligence seeks to identify, formalize, and understand commonalities in behavioral competencies across a wide range of implementations. Especially interesting are simple systems that provide unexpected…
Self-driving labs are transforming drug discovery by enabling automated, AI-guided experimentation, but they face challenges in orchestrating complex workflows, integrating diverse instruments and AI models, and managing data efficiently.…
Children learn continually by asking questions about the concepts they are most curious about. With robots becoming an integral part of our society, they must also learn unknown concepts continually by asking humans questions. The paper…
Monte-Carlo Tree Search (MCTS) is a fundamental sampling-based search algorithm widely used for online planning in sequential decision-making domains. Despite its success in driving recent advances in artificial intelligence, understanding…
Leveraging large language models (LLMs), autonomous agents have significantly improved, gaining the ability to handle a variety of tasks. In open-ended settings, optimizing collaboration for efficiency and effectiveness demands flexible…
As autonomous agents increasingly operate in real-world digital ecosystems, understanding how they coordinate, form institutions, and accumulate shared culture becomes both a scientific and practical priority. This paper introduces…
Open-ended evolution requires unbounded possibilities that evolving entities can explore. The cardinality of a set of those possibilities thus has a significant implication for the open-endedness of evolution. We propose that facilitating…
Much current research in AI and games is being devoted to Monte Carlo search (MCS) algorithms. While the quest for a single unified MCS algorithm that would perform well on all problems is of major interest for AI, practitioners often know…
We present MineNPC-Task, a user-authored benchmark and evaluation harness for testing memory-aware, mixed-initiative LLM agents in open-world Minecraft. Rather than relying on synthetic prompts, tasks are elicited through formative and…
Artificial intelligence has undergone immense growth and maturation in recent years, though autonomous systems have traditionally struggled when fielded in diverse and previously unknown environments. DARPA is seeking to change that with…
Collaborative tasks are ubiquitous activities where a form of communication is required in order to reach a joint goal. Collaborative building is one of such tasks. We wish to develop an intelligent builder agent in a simulated building…
Large Language Models (LLMs) have the capacity of performing complex scheduling in a multi-agent system and can coordinate these agents into completing sophisticated tasks that require extensive collaboration. However, despite the…
The goal of coordinated multi-robot exploration tasks is to employ a team of autonomous robots to explore an unknown environment as quickly as possible. Compared with human-designed methods, which began with heuristic and rule-based…