Related papers: Asynchronous Agents with Perfect Recall: Model Red…
Multi-Agent Systems (MAS) are notoriously complex and hard to verify. In fact, it is not trivial to model a MAS, and even when a model is built, it is not always possible to verify, in a formal way, that it is actually behaving as we…
In this work, we propose and evaluate a new reinforcement learning method, COMPact Experience Replay (COMPER), which uses temporal difference learning with predicted target values based on recurrence over sets of similar transitions, and a…
Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors: a single faulty step can propagate across agents and disrupt the trajectory. In this paper, we present MASC,…
We examine sequential equilibrium in the context of computational games, where agents are charged for computation. In such games, an agent can rationally choose to forget, so issues of imperfect recall arise. In this setting, we consider…
Constructing a consistent shared spatial memory is a critical challenge in multi-agent systems, where partial observability and limited bandwidth often lead to catastrophic failures in coordination. We introduce a multi-agent predictive…
This article provides an analytical framework for how to simulate human-like thought processes within a computer. It describes how attention and memory should be structured, updated, and utilized to search for associative additions to the…
Existing evaluations of agents with memory typically assess memorization and action in isolation. One class of benchmarks evaluates memorization by testing recall of past conversations or text but fails to capture how memory is used to…
Learning by experience in Multi-Agent Systems (MAS) is a difficult and exciting task, due to the lack of stationarity of the environment, whose dynamics evolves as the population learns. In order to design scalable algorithms for systems…
Model checking of strategic abilities is a notoriously hard problem, even more so in the realistic case of agents with imperfect information, acting in a stochastic environment. Assume-guarantee reasoning can be of great help here,…
The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and complex reasoning. Benefiting from the strong capabilities of LLMs, recent research focus has…
We propose a new method to study the internal memory used by reinforcement learning policies. We estimate the amount of relevant past information by estimating mutual information between behavior histories and the current action of an…
Agent-based modelling constitutes a versatile approach to representing and simulating complex systems. Studying large-scale systems is challenging because of the computational time required for the simulation runs: scaling is at least…
This paper proposes Memory-Augmented State Machine Prompting (MASMP), a novel framework for LLM agents in real-time strategy games. Addressing key challenges like hallucinations and fragmented decision-making in existing approaches, MASMP…
Consider a typical organization whose worker agents seek to collectively cooperate for its general betterment. However, each individual agent simultaneously seeks to act to secure a larger chunk than its co-workers of the annual increment…
Existing Multi-Agent Systems (MAS) typically rely on homogeneous model configurations, failing to exploit the diverse expertise inherent in different post-trained architectures. We propose Team-of-Thoughts, a heterogeneous MAS framework…
Due to the complex interactions between agents, learning multi-agent control policy often requires a prohibited amount of data. This paper aims to enable multi-agent systems to effectively utilize past memories to adapt to novel…
Large language model (LLM)-powered multi-agent systems (MAS) demonstrate remarkable collective intelligence, wherein multi-agent memory serves as a pivotal mechanism for continual adaptation. However, existing multi-agent memory designs…
Multi-agent reinforcement learning (MARL) algorithms have made promising progress in recent years by leveraging the centralized training and decentralized execution (CTDE) paradigm. However, existing MARL algorithms still suffer from the…
Reinforcement learning agents in complex game environments often suffer from sparse rewards, training instability, and poor sample efficiency. This paper presents a hybrid training approach that combines offline imitation learning with…
A lifelong learning agent is able to continually learn from potentially infinite streams of pattern sensory data. One major historic difficulty in building agents that adapt in this way is that neural systems struggle to retain…