This study examines whether collective reasoning among generative agents can facilitate novel and coherent thinking that leads to innovation. To achieve this, it proposes GAI, a new LLM-empowered framework designed for reflection and interaction among multiple generative agents to replicate the process of innovation. The core of the GAI framework lies in an architecture that dynamically processes the internal states of agents and a dialogue scheme specifically tailored to facilitate analogy-driven innovation. The framework's functionality is evaluated using Dyson's invention of the bladeless fan as a case study, assessing the extent to which the core ideas of the innovation can be replicated through a set of fictional technical documents. The experimental results demonstrate that models with internal states significantly outperformed those without, achieving higher average scores and lower variance. Notably, the model with five heterogeneous agents equipped with internal states successfully replicated the key ideas underlying the Dyson's invention. This indicates that the internal state enables agents to refine their ideas, resulting in the construction and sharing of more coherent and comprehensive concepts.

Understanding individual travel behaviors is critical for developing efficient and sustainable transportation systems. Travel behavioral analysis aims to capture the decision-making process of individual travel execution, including travel route choice, travel mode choice, departure time choice, and trip purpose. Among these choices, modeling route choice not only helps analyze and understand travelers' behaviors, but also constitutes the essential part of traffic assignment methods [1]. Specifically, it enables the evaluation of travelers' perceptions of route characteristics, the forecasting of behavior in hypothetical scenarios, the prediction of future traffic dynamics on transportation networks, and the understanding of travelers' responses to travel information. Real-world route choice is complex because of the inherent difficulties in accurately representing human behavior, travelers' limited knowledge of network composition, uncertainties in perceptions of route characteristics, and the lack of precise information about travelers' preferences [1]. To overcome these limitations, DTD traffic dynamics have attracted significant attention since they focus on drivers' dynamic shifts in route choices and the evolution of traffic flow over time, rather than merely static equilibrium states. DTD models are flexible to incorporate diverse behavioral rules such as forecasting [2, 3], bounded rationality [4, 5], decision-making based on prospects [6, 7], marginal utility effects [8, 9], and social interactions [10]. Despite these advantages identified in [11] and [12], DTD models still struggle to accurately reflect the observed fluctuations in traffic dynamics, particularly the persistent deviations around User Equilibrium (UE) noted in empirical studies [13, 14, 15]. To better understand traffic dynamics, Agent-Based Modeling (ABM) offers a promising alternative.

Multi-Agent Reinforcement Learning (MARL) approaches have emerged as popular solutions to address the general challenges of cooperation in multi-agent environments, where the success of achieving shared or individual goals critically depends on the coordination and collaboration between agents. However, existing cooperative MARL methods face several challenges intrinsic to multi-agent systems, such as the curse of dimensionality, non-stationarity, and the need for a global exploration strategy. Moreover, the presence of agents with constraints (e.g., limited battery life, restricted mobility) or distinct roles further exacerbates these challenges. This document provides an overview of recent advances in Multi-Agent Reinforcement Learning (MARL) conducted at the Persistent Autonomy and Robot Learning (PeARL) lab at the University of Massachusetts Lowell. We briefly discuss various research directions and present a selection of approaches proposed in our most recent publications. For each proposed approach, we also highlight potential future directions to further advance the field.

Language agents [1-4] are AI agents [5] that integrate LLMs [6-8] as core components. LLMs excel at zero-shot generalization [9, 10], providing a notable advantage over traditional AI agents, such as those based on handcrafted rules or reinforcement learning, which often struggle to generalize to new environments [11]. While LLMs can exhibit flawed reasoning and logic when used in isolation [12-14], constructing a language agent by grounding LLMs in an environment with observational feedback can mitigate these issues. Early work on language agents used LLMs to directly output actions in the external environment [15-17], while more recently, language agents have been augmented with internal reasoning [18, 19] and planning [20, 21] procedures, as well as long-term memory storage [22, 23]. An emergent research challenge is to pose a theoretical description of the learning problem solved by language agents [4, 24] and to develop efficient methods to optimize the components of a language agent [24-26]. Here, we define common language agent tasks as language decision processes (LDPs) and frame language agents as stochastic computation graphs [27] that may be trained to solve LDPs. We show that pre-existing agents [18, 19, 21] can be implemented within our stochastic computation graph framework and introduce a simple and extensible software package named LDP that enables modular interchange of environments, agents, and optimizers, simplifying experimentation across a variety of settings. These authors jointly supervise technical work at FutureHouse.

Diversity is a critical aspect of multi-agent communication. In this paper, we focus on controlling and exploring diversity in the context of open-domain multi-agent conversations, particularly for world simulation applications. We propose Adaptive Prompt Pruning (APP), a novel method that dynamically adjusts the content of the utterance generation prompt to control diversity using a single parameter, lambda. Through extensive experiments, we show that APP effectively controls the output diversity across models and datasets, with pruning more information leading to more diverse output. We comprehensively analyze the relationship between prompt content and conversational diversity. Our findings reveal that information from all components of the prompt generally constrains the diversity of the output, with the Memory block exerting the most significant influence. APP is compatible with established techniques like temperature sampling and top-p sampling, providing a versatile tool for diversity management. To address the trade-offs of increased diversity, such as inconsistencies with omitted information, we incorporate a post-generation correction step, which effectively balances diversity enhancement with output consistency. Additionally, we examine how prompt structure, including component order and length, impacts diversity. This study addresses key questions surrounding diversity in multi-agent world simulation, offering insights into its control, influencing factors, and associated trade-offs. Our contributions lay the foundation for systematically engineering diversity in LLM-based multi-agent collaborations, advancing their effectiveness in real-world applications.

Multi-Agent Reinforcement Learning involves agents that learn together in a shared environment, leading to emergent dynamics sensitive to initial conditions and parameter variations. A Dynamical Systems approach, which studies the evolution of multi-component systems over time, has uncovered some of the underlying dynamics by constructing deterministic approximation models of stochastic algorithms. In this work, we demonstrate that even in the simplest case of independent Q-learning with a Boltzmann exploration policy, significant discrepancies arise between the actual algorithm and previous approximations. We elaborate why these models actually approximate interesting variants rather than the original incremental algorithm. To explain the discrepancies, we introduce a new discrete-time approximation model that explicitly accounts for agents' update frequencies within the learning process and show that its dynamics fundamentally differ from the simplified dynamics of prior models. We illustrate the usefulness of our approach by applying it to the question of spontaneous cooperation in social dilemmas, specifically the Prisoner's Dilemma as the simplest case study. We identify conditions under which the learning behaviour appears as long-term stable cooperation from an external perspective. However, our model shows that this behaviour is merely a metastable transient phase and not a true equilibrium, making it exploitable. We further exemplify how specific parameter settings can significantly exacerbate the moving target problem in independent learning. Through a systematic analysis of our model, we show that increasing the discount factor induces oscillations, preventing convergence to a joint policy. These oscillations arise from a supercritical Neimark-Sacker bifurcation, which transforms the unique stable fixed point into an unstable focus surrounded by a stable limit cycle.

Artificial intelligence (AI) has enabled agents to master complex video games, from first-person shooters like Counter-Strike to real-time strategy games such as StarCraft II and racing games like Gran Turismo. While these achievements are notable, applying these AI methods in commercial video game production remains challenging due to computational constraints. In commercial scenarios, the majority of computational resources are allocated to 3D rendering, leaving limited capacity for AI methods, which often demand high computational power, particularly those relying on pixel-based sensors. Moreover, the gaming industry prioritizes creating human-like behavior in AI agents to enhance player experience, unlike academic models that focus on maximizing game performance. This paper introduces a novel methodology for training neural networks via imitation learning to play a complex, commercial-standard, VALORANT-like 2v2 tactical shooter game, requiring only modest CPU hardware during inference. Our approach leverages an innovative, pixel-free perception architecture using a small set of ray-cast sensors, which capture essential spatial information efficiently. These sensors allow AI to perform competently without the computational overhead of traditional methods. Models are trained to mimic human behavior using supervised learning on human trajectory data, resulting in realistic and engaging AI agents. Human evaluation tests confirm that our AI agents provide human-like gameplay experiences while operating efficiently under computational constraints. This offers a significant advancement in AI model development for tactical shooter games and possibly other genres.

In a decision-making scenario, a principal could use conditional predictions from an expert agent to inform their choice. However, this approach would introduce a fundamental conflict of interest. An agent optimizing for predictive accuracy is incentivized to manipulate their principal towards more predictable actions, which prevents that principal from being able to deterministically select their true preference. We demonstrate that this impossibility result can be overcome through the joint evaluation of multiple agents. When agents are made to engage in zero-sum competition, their incentive to influence the action taken is eliminated, and the principal can identify and take the action they most prefer. We further prove that this zero-sum setup is unique, efficiently implementable, and applicable under stochastic choice. Experiments in a toy environment demonstrate that training on a zero-sum objective significantly enhances both predictive accuracy and principal utility, and can eliminate previously learned manipulative behavior.

Most multi-agent reinforcement learning (MARL) methods are limited in the scale of problems they can handle. With increasing numbers of agents, the number of training iterations required to find the optimal behaviors increases exponentially due to the exponentially growing joint state and action spaces. This paper tackles this limitation by introducing a scalable MARL method called Distributed multi-Agent Reinforcement Learning with One-hop Neighbors (DARL1N). DARL1N is an off-policy actor-critic method that addresses the curse of dimensionality by restricting information exchanges among the agents to one-hop neighbors when representing value and policy functions. Each agent optimizes its value and policy functions over a one-hop neighborhood, significantly reducing the learning complexity, yet maintaining expressiveness by training with varying neighbor numbers and states. This structure allows us to formulate a distributed learning framework to further speed up the training procedure. Distributed computing systems, however, contain straggler compute nodes, which are slow or unresponsive due to communication bottlenecks, software or hardware problems. To mitigate the detrimental straggler effect, we introduce a novel coded distributed learning architecture, which leverages coding theory to improve the resilience of the learning system to stragglers. Comprehensive experiments show that DARL1N significantly reduces training time without sacrificing policy quality and is scalable as the number of agents increases. Moreover, the coded distributed learning architecture improves training efficiency in the presence of stragglers.

In Reinforcement Learning (RL) theory, we impose restrictive assumptions to design an algorithm with provably sublinear regret. Common assumptions, like linear or RKHS models, and Gaussian or log-concave posteriors over the models, do not explain practical success of RL across a wider range of distributions and models. Thus, we study how to design RL algorithms with sublinear regret for isoperimetric distributions, specifically the ones satisfying the Log-Sobolev Inequality (LSI). LSI distributions include the standard setups of RL and others, such as many non-log-concave and perturbed distributions. First, we show that the Posterior Sampling-based RL (PSRL) yields sublinear regret if the data distributions satisfy LSI under some mild additional assumptions. Also, when we cannot compute or sample from an exact posterior, we propose a Langevin sampling-based algorithm design: LaPSRL. We show that LaPSRL achieves order optimal regret and subquadratic complexity per episode. Finally, we deploy LaPSRL with a Langevin sampler -- SARAH-LD, and test it for different bandit and MDP environments. Experimental results validate the generality of LaPSRL across environments and its competitive performance with respect to the baselines.