Complex tasks are increasingly delegated to ensembles of specialized LLM-based agents that reason, communicate, and coordinate actions-both among themselves and through interactions with external tools, APIs, and databases. While persistent memory has been shown to enhance single-agent performance, most approaches assume a monolithic, single-user context-overlooking the benefits and challenges of knowledge transfer across users under dynamic, asymmetric permissions. We introduce Collaborative Memory, a framework for multi-user, multi-agent environments with asymmetric, time-evolving access controls encoded as bipartite graphs linking users, agents, and resources. Our system maintains two memory tiers: (1) private memory-private fragments visible only to their originating user; and (2) shared memory-selectively shared fragments. Each fragment carries immutable provenance attributes (contributing agents, accessed resources, and timestamps) to support retrospective permission checks. Granular read policies enforce current user-agent-resource constraints and project existing memory fragments into filtered transformed views. Write policies determine fragment retention and sharing, applying context-aware transformations to update the memory. Both policies may be designed conditioned on system, agent, and user-level information. Our framework enables safe, efficient, and interpretable cross-user knowledge sharing, with provable adherence to asymmetric, time-varying policies and full auditability of memory operations.

Traditional interactive environments limit agents' intelligence growth with fixed tasks. Recently, single-agent environments address this by generating new tasks based on agent actions, enhancing task diversity. We consider the decision-making problem in multi-agent settings, where tasks are further influenced by social connections, affecting rewards and information access. However, existing multi-agent environments lack a combination of adaptive physical surroundings and social connections, hindering the learning of intelligent behaviors.To address this, we introduce AdaSociety, a customizable multi-agent environment featuring expanding state and action spaces, alongside explicit and alterable social structures. As agents progress, the environment adaptively generates new tasks with social structures for agents to undertake. In AdaSociety, we develop three mini-games showcasing distinct social structures and tasks.

This paper concerns imitation learning (IL) in cooperative multi-agent systems.The learning problem under consideration poses several challenges, characterized by high-dimensional state and action spaces and intricate inter-agent dependencies. In a single-agent setting, IL was shown to be done efficiently via an inverse soft-Q learning process. However, extending this framework to a multi-agent context introduces the need to simultaneously learn both local value functions to capture local observations and individual actions, and a joint value function for exploiting centralized learning.In this work, we introduce a new multi-agent IL algorithm designed to address these challenges. Our approach enables thecentralized learning by leveraging mixing networks to aggregate decentralized Q functions.We further establish conditions for the mixing networks under which the multi-agent IL objective function exhibits convexity within the Q function space.We present extensive experiments conducted on some challenging multi-agent game environments, including an advanced version of the Star-Craft multi-agent challenge (SMACv2), which demonstrates the effectiveness of our algorithm.

Reinforcement learning (RL) has emerged as a pivotal technique for fine-tuning large language models (LLMs) on specific tasks. However, prevailing RL fine-tuning methods predominantly rely on PPO and its variants. Though these algorithms are effective in general RL settings, they often exhibit suboptimal performance and vulnerability to distribution collapse when applied to the fine-tuning of LLMs. In this paper, we propose CORY, extending the RL fine-tuning of LLMs to a sequential cooperative multi-agent reinforcement learning framework, to leverage the inherent coevolution and emergent capabilities of multi-agent systems. In CORY, the LLM to be fine-tuned is initially duplicated into two autonomous agents: a pioneer and an observer.

We introduce a novel framework, Online Relational Inference (ORI), designed to efficiently identify hidden interaction graphs in evolving multi-agent interacting systems using streaming data. Unlike traditional offline methods that rely on a fixed training set, ORI employs online backpropagation, updating the model with each new data point, thereby allowing it to adapt to changing environments in real-time. A key innovation is the use of an adjacency matrix as a trainable parameter, optimized through a new adaptive learning rate technique called AdaRelation, which adjusts based on the historical sensitivity of the decoder to changes in the interaction graph. Additionally, a data augmentation method named Trajectory Mirror (TM) is introduced to improve generalization by exposing the model to varied trajectory patterns. Experimental results on both synthetic datasets and real-world data (CMU MoCap for human motion) demonstrate that ORI significantly improves the accuracy and adaptability of relational inference in dynamic settings compared to existing methods.

In the facility location problem, the task is to place one or more facilities so as to minimize the sum of the agent costs for accessing their nearest facility. Heretofore, in the strategic version, agent locations have been assumed to be private, while their cost measures have been public and identical. For the most part, the cost measure has been the distance to the nearest facility. However, in multiple natural settings, such as placing a firehouse or a school, this modeling does not appear to be a good fit. For it seems natural that the agent locations would be known, but their costs might be private information. In addition, for these types of settings, agents may well want the nearest facility to be at the right distance: near, but not too near. This is captured by the doubly-peaked cost introduced by Filos-Ratsikas et al. (AAMAS 2017). In this paper, we re-examine the facility location problem from this perspective: known agent locations and private preferred distances to the nearest facility. We then give lower and upper bounds on achievable approximations, focusing on the problem in 1D, and in 2D with an $L_1$ distance measure.

Large Language Model (LLM) agents represent a promising shift in human-AI interaction, moving beyond passive prompt-response systems to autonomous agents capable of reasoning, planning, and goal-directed action. Despite the widespread application in specialized, high-effort tasks like coding and scientific research, we highlight a critical usability gap in high-demand, mass-market applications. This position paper argues that the limited real-world adoption of LLM agents stems not only from gaps in model capabilities, but also from a fundamental tradeoff between the value an agent can provide and the costs incurred during real-world use. Hence, we call for a shift from solely optimizing model performance to a broader, utility-driven perspective: evaluating agents through the lens of the overall agentic return on investment (Agent ROI). By identifying key factors that determine Agentic ROI--information quality, agent time, and cost--we posit a zigzag development trajectory in optimizing agentic ROI: first scaling up to improve the information quality, then scaling down to minimize the time and cost. We outline the roadmap across different development stages to bridge the current usability gaps, aiming to make LLM agents truly scalable, accessible, and effective in real-world contexts.

Understanding the causal influence of one agent on another agent is crucial for safely deploying artificially intelligent systems such as automated vehicles and mobile robots into human-inhabited environments. Existing models of causal responsibility deal with simplified abstractions of scenarios with discrete actions, thus, limiting real-world use when understanding responsibility in spatial interactions. Based on the assumption that spatially interacting agents are embedded in a scene and must follow an action at each instant, Feasible Action-Space Reduction (FeAR) was proposed as a metric for causal responsibility in a grid-world setting with discrete actions. Since real-world interactions involve continuous action spaces, this paper proposes a formulation of the FeAR metric for measuring causal responsibility in space-continuous interactions. We illustrate the utility of the metric in prototypical space-sharing conflicts, and showcase its applications for analysing backward-looking responsibility and in estimating forward-looking responsibility to guide agent decision making. Our results highlight the potential of the FeAR metric for designing and engineering artificial agents, as well as for assessing the responsibility of agents around humans.

Cooperative multi-agent reinforcement learning faces significant challenges in effectively organizing agent relationships and facilitating information exchange, particularly when agents need to adapt their coordination patterns dynamically. This paper presents a novel framework that integrates dynamic spectral clustering with hypergraph neural networks to enable adaptive group formation and efficient information processing in multi-agent systems. The proposed framework dynamically constructs and updates hypergraph structures through spectral clustering on agents' state histories, enabling higher-order relationships to emerge naturally from agent interactions. The hypergraph structure is enhanced with attention mechanisms for selective information processing, providing an expressive and efficient way to model complex agent relationships. This architecture can be implemented in both value-based and policy-based paradigms through a unified objective combining task performance with structural regularization. Extensive experiments on challenging cooperative tasks demonstrate that our method significantly outperforms state-of-the-art approaches in both sample efficiency and final performance.

This monograph presents a modular cognitive architecture for artificial intelligence grounded in the formal modeling of belief as structured semantic state. Belief states are defined as dynamic ensembles of linguistic expressions embedded within a navigable manifold, where operators enable assimilation, abstraction, nullification, memory, and introspection. Drawing from philosophy, cognitive science, and neuroscience, we develop a layered framework that enables self-regulating epistemic agents capable of reflective, goal-directed thought. At the core of this framework is the epistemic vacuum: a class of semantically inert cognitive states that serves as the conceptual origin of belief space. From this foundation, the Null Tower arises as a generative structure recursively built through internal representational capacities. The theoretical constructs are designed to be implementable in both symbolic and neural systems, including large language models, hybrid agents, and adaptive memory architectures. This work offers a foundational substrate for constructing agents that reason, remember, and regulate their beliefs in structured, interpretable ways.