Related papers: Evaluating Long-Term Memory in 3D Mazes
Research on large language model (LLM) security is shifting from "will the model leak training data" to a more consequential question: can an agent with persistent, long-term memory be continuously shaped, cross-session poisoned, accessed…
Resource constraints can fundamentally change both learning and decision-making. We explore how memory constraints influence an agent's performance when navigating unknown environments using standard reinforcement learning algorithms.…
A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains…
Traditional approaches to training agents have generally involved a single, deterministic environment of minimal complexity to solve various tasks such as robot locomotion or computer vision. However, agents trained in static environments…
Augmented Reality (AR) systems are increasingly integrating foundation models, such as Multimodal Large Language Models (MLLMs), to provide more context-aware and adaptive user experiences. This integration has led to the development of AR…
Most current AI models have little ability to store and later retrieve a record or representation of what they do. In human cognition, episodic memories play an important role in both recall of the past as well as planning for the future.…
Reinforcement learning (RL) has demonstrated strong potential in training large language models (LLMs) capable of complex reasoning for real-world problem solving. More recently, RL has been leveraged to create sophisticated LLM-based…
This study compares the modularity performance of two artificial neural network architectures: a Long Short-Term Memory (LSTM) recurrent network, and Morphognosis, a neural network based on a hierarchy of spatial and temporal contexts.…
Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal…
Game environments provide rich, controllable settings that stimulate many aspects of real-world complexity. As such, game agents offer a valuable testbed for exploring capabilities relevant to Artificial General Intelligence. Recently, the…
Large language models (LLMs) have advanced the field of artificial intelligence (AI) and are a powerful enabler for interactive systems. However, they still face challenges in long-term interactions that require adaptation towards the user…
Humans excel at remembering concrete experiences along spatiotemporal contexts and performing reasoning across those events, i.e., the capacity for episodic memory. In contrast, memory in language agents remains mainly semantic, and current…
The Game Theory & Multi-Agent team at DeepMind studies several aspects of multi-agent learning ranging from computing approximations to fundamental concepts in game theory to simulating social dilemmas in rich spatial environments and…
We propose a planning and perception mechanism for a robot (agent), that can only observe the underlying environment partially, in order to solve an image classification problem. A three-layer architecture is suggested that consists of a…
In continual learning (CL), an AI agent (e.g., autonomous vehicles or robotics) learns from non-stationary data streams under dynamic environments. For the practical deployment of such applications, it is important to guarantee robustness…
There has been a recent explosion in the capabilities of game-playing artificial intelligence. Many classes of tasks, from video games to motor control to board games, are now solvable by fairly generic algorithms, based on deep learning…
Agent memory shapes how Large Language Model (LLM)-powered agents, akin to the human brain, progressively refine themselves through environment interactions. Existing paradigms remain constrained: parametric memory forcibly adjusts model…
In neuroscience, attention has been shown to bidirectionally interact with reinforcement learning (RL) processes. This interaction is thought to support dimensionality reduction of task representations, restricting computations to relevant…
Long-horizon multimodal agents depend on external memory; however, similarity-based retrieval often surfaces stale, low-credibility, or conflicting items, which can trigger overconfident errors. We propose Multimodal Memory Agent (MMA),…
For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting--inspired by human cognitive processes (hippocampal indexing/consolidation theory and…