In this paper we investigate the notion of legibility in sequential decision-making in the context of teams and teamwork. There have been works that extend the notion of legibility to sequential decision making, for deterministic and for stochastic scenarios. However, these works focus on one agent interacting with one human, foregoing the benefits of having legible decision making in teams of agents or in team configurations with humans. In this work we propose an extension of legible decision-making to multi-agent settings that improves the performance of agents working in collaboration. We showcase the performance of legible decision making in team scenarios using our proposed extension in multi-agent benchmark scenarios. We show that a team with a legible agent is able to outperform a team composed solely of agents with standard optimal behaviour.

As large language models (LLMs) advance, there is growing interest in using them to simulate human social behavior through generative agent-based modeling (GABM). However, validating these models remains a key challenge. We present a systematic two-stage validation approach using social dilemma paradigms from psychological literature, first identifying the cognitive components necessary for LLM agents to reproduce known human behaviors in mixed-motive settings from two landmark papers, then using the validated architecture to simulate novel conditions. Our model comparison of different cognitive architectures shows that both persona-based individual differences and theory of mind capabilities are essential for replicating third-party punishment (TPP) as a costly signal of trustworthiness. For the second study on public goods games, this architecture is able to replicate an increase in cooperation from the spread of reputational information through gossip. However, an additional strategic component is necessary to replicate the additional boost in cooperation rates in the condition that allows both ostracism and gossip. We then test novel predictions for each paper with our validated generative agents. We find that TPP rates significantly drop in settings where punishment is anonymous, yet a substantial amount of TPP persists, suggesting that both reputational and intrinsic moral motivations play a role in this behavior. For the second paper, we introduce a novel intervention and see that open discussion periods before rounds of the public goods game further increase contributions, allowing groups to develop social norms for cooperation. This work provides a framework for validating generative agent models while demonstrating their potential to generate novel and testable insights into human social behavior.

Abstract--Large language models (LLMs) have proven effective in artificial intelligence, where the multi-agent system (MAS) holds considerable promise for healthcare development by achieving the collaboration of LLMs. However, the absence of a systematic pipeline for agent construction and the rigidity of static collaboration patterns render current MAS-based models vulnerable to collaboration failures, resulting in substantial performance degradation in medical decision-making scenarios. T o this end, we propose a novel Masked Agent Collaboration (MAC) framework that harnesses Pareto-optimal agent construction and cross-consistency maximization mechanisms to achieve adaptive progressive propagation of collaborative information, boosting the medical decision-making capacity. Specifically, we first conduct a Pareto-frontier factors analysis towards the LLMs pool to consider their key factors, including the model size, inference time, diversity score, and throughput ratio, where we calculate the similarity between pairwise outputs within an LLM to derive its diversity score. Beyond this analysis, we enable the identification of Pareto-optimal models that balance efficiency and capability, which are subsequently selected as collaborative agents to consider the fundamental trade-offs inherent in practical LLM deployment. Afterward, we measure the pairwise similarity between the outputs from collaborative agents to determine their cross-consistency values, subsequently masking out the agent with the lowest cross-consistency value to eliminate the output that is likely semantically inconsistent. Finally, we conduct collaboration of agents by achieving adaptive progressive propagation, where each agent aggregates the outputs of unmasked agents from the previous layer as its input to generate the corresponding output via prompt engineering. Evaluations across three datasets confirm the effectiveness of our MAC, notably outperforming the multi-agent collaboration model (composed of 70B-141B open-access LLMs) by 16.55% and GPT -4 by 9.35% in Obstetrics and Gynecology on NEJMQA.

Nearly all human work is collaborative; thus, the evaluation of real-world NLP applications often requires multiple dimensions that align with diverse human perspectives. As real human evaluator resources are often scarce and costly, the emerging "LLM-as-a-judge" paradigm sheds light on a promising approach to leverage LLM agents to believably simulate human evaluators. Yet, to date, existing LLM-as-a-judge approaches face two limitations: persona descriptions of agents are often arbitrarily designed, and the frameworks are not generalizable to other tasks. To address these challenges, we propose MAJ-EVAL, a Multi-Agent-as-Judge evaluation framework that can automatically construct multiple evaluator personas with distinct dimensions from relevant text documents (e.g., research papers), instantiate LLM agents with the personas, and engage in-group debates with multi-agents to Generate multi-dimensional feedback. Our evaluation experiments in both the educational and medical domains demonstrate that MAJ-EVAL can generate evaluation results that better align with human experts' ratings compared with conventional automated evaluation metrics and existing LLM-as-a-judge methods.

Many real-world systems, such as transportation systems, ecological systems, and Internet systems, are complex systems. As an important tool for studying complex systems, computational experiments can map them into artificial society models that are computable and reproducible within computers, thereby providing digital and computational methods for quantitative analysis. In current research, the construction of individual agent models often ignores the long-term accumulative effect of memory mechanisms in the development process of agents, which to some extent causes the constructed models to deviate from the real characteristics of real-world systems. To address this challenge, this paper proposes an individual agent model based on a memory-learning collaboration mechanism, which implements hierarchical modeling of the memory mechanism and a multi-indicator evaluation mechanism. Through hierarchical modeling of the individual memory repository, the group memory repository, and the memory buffer pool, memory can be effectively managed, and knowledge sharing and dissemination between individuals and groups can be promoted. At the same time, the multi-indicator evaluation mechanism enables dynamic evaluation of memory information, allowing dynamic updates of information in the memory set and promoting collaborative decision-making between memory and learning. Experimental results show that, compared with existing memory modeling methods, the agents constructed by the proposed model demonstrate better decision-making quality and adaptability within the system. This verifies the effectiveness of the individual agent model based on the memory-learning collaboration mechanism proposed in this paper in improving the quality of individual-level modeling in artificial society modeling and achieving anthropomorphic characteristics.

Despite substantial progress in applying neural networks (NN) to multi-agent reinforcement learning (MARL) areas, they still largely suffer from a lack of transparency and interoperability. However, its implicit cooperative mechanism is not yet fully understood due to black-box networks. In this work, we study an interpretable value decomposition framework via concept bottleneck models, which promote trustworthiness by conditioning credit assignment on an intermediate level of human-like cooperation concepts. To address this problem, we propose a novel value-based method, named Concepts learning for Multi-agent Q-learning (CMQ), that goes beyond the current performance-vs-interpretability trade-off by learning interpretable cooperation concepts. CMQ represents each cooperation concept as a supervised vector, as opposed to existing models where the information flowing through their end-to-end mechanism is concept-agnostic. Intuitively, using individual action value conditioning on global state embeddings to represent each concept allows for extra cooperation representation capacity. Empirical evaluations on the StarCraft II micromanagement challenge and level-based foraging (LBF) show that CMQ achieves superior performance compared with the state-of-the-art counterparts. The results also demonstrate that CMQ provides more cooperation concept representation capturing meaningful cooperation modes, and supports test-time concept interventions for detecting potential biases of cooperation mode and identifying spurious artifacts that impact cooperation.

Software development is a complex, multi-phase process traditionally requiring collaboration among individuals with diverse expertise. We propose AgentMesh, a Python-based framework that uses multiple cooperating LLM-powered agents to automate software development tasks. In AgentMesh, specialized agents - a Planner, Coder, Debugger, and Reviewer - work in concert to transform a high-level requirement into fully realized code. The Planner agent first decomposes user requests into concrete subtasks; the Coder agent implements each subtask in code; the Debugger agent tests and fixes the code; and the Reviewer agent validates the final output for correctness and quality. We describe the architecture and design of these agents and their communication, and provide implementation details including prompt strategies and workflow orchestration. A case study illustrates AgentMesh handling a non-trivial development request via sequential task planning, code generation, iterative debugging, and final code review. We discuss how dividing responsibilities among cooperative agents leverages the strengths of large language models while mitigating single-agent limitations. Finally, we examine current limitations - such as error propagation and context scaling - and outline future work toward more robust, scalable multi-agent AI systems for software engineering automation.

Classical game-theoretic models typically assume rational agents, complete information, and common knowledge of payoffs - assumptions that are often violated in real-world MAS characterized by uncertainty, misaligned perceptions, and nested beliefs. To overcome these limitations, researchers have proposed extensions that incorporate models of cognitive constraints, subjective beliefs, and heterogeneous reasoning. Among these, hypergame theory extends the classical paradigm by explicitly modeling agents' subjective perceptions of the strategic scenario, known as perceptual games, in which agents may hold divergent beliefs about the structure, payoffs, or available actions. We present a systematic review of agent-compatible applications of hypergame theory, examining how its descriptive capabilities have been adapted to dynamic and interactive MAS contexts. We analyze 44 selected studies from cybersecurity, robotics, social simulation, communications, and general game-theoretic modeling. Building on a formal introduction to hypergame theory and its two major extensions - hierarchical hypergames and HNF - we develop agent-compatibility criteria and an agent-based classification framework to assess integration patterns and practical applicability. Our analysis reveals prevailing tendencies, including the prevalence of hierarchical and graph-based models in deceptive reasoning and the simplification of extensive theoretical frameworks in practical applications. We identify structural gaps, including the limited adoption of HNF-based models, the lack of formal hypergame languages, and unexplored opportunities for modeling human-agent and agent-agent misalignment. By synthesizing trends, challenges, and open research directions, this review provides a new roadmap for applying hypergame theory to enhance the realism and effectiveness of strategic modeling in dynamic multi-agent environments.

This position paper examines the use of Large Language Models (LLMs) in social simulation, analyzing both their potential and their limitations from a computational social science perspective. The first part reviews recent findings on the ability of LLMs to replicate key aspects of human cognition, including Theory of Mind reasoning and social inference, while also highlighting significant limitations such as cognitive biases, lack of true understanding, and inconsistencies in behavior. The second part surveys emerging applications of LLMs in multi-agent simulation frameworks, focusing on system architectures, scale, and validation strategies. Notable projects such as Generative Agents (Smallville) and AgentSociety are discussed in terms of their design choices, empirical grounding, and methodological innovations. Particular attention is given to the challenges of behavioral fidelity, calibration, and reproducibility in large-scale LLM-driven simulations. The final section distinguishes between contexts where LLMs, like other black-box systems, offer direct value-such as interactive simulations and serious games-and those where their use is more problematic, notably in explanatory or predictive modeling. The paper concludes by advocating for hybrid approaches that integrate LLMs into traditional agent-based modeling platforms (GAMA, Netlogo, etc), enabling modelers to combine the expressive flexibility of language-based reasoning with the transparency and analytical rigor of classical rule-based systems.

Feed-forward neural networks (FFNNs) are vulnerable to input noise, reducing prediction performance. Existing regularization methods like dropout often alter network architecture or overlook neuron interactions. This study aims to enhance FFNN noise robustness by modifying backpropagation, interpreted as a multi-agent game, and exploring controlled target variable noising. Our "gradient dropout" selectively nullifies hidden layer neuron gradients with probability 1 - p during backpropagation, while keeping forward passes active. This is framed within compositional game theory. Additionally, target variables were perturbed with white noise or stable distributions. Experiments on ten diverse tabular datasets show varying impacts: improvement or diminishing of robustness and accuracy, depending on dataset and hyperparameters. Notably, on regression tasks, gradient dropout (p = 0.9) combined with stable distribution target noising significantly increased input noise robustness, evidenced by flatter MSE curves and more stable SMAPE values. These results highlight the method's potential, underscore the critical role of adaptive parameter tuning, and open new avenues for analyzing neural networks as complex adaptive systems exhibiting emergent behavior within a game-theoretic framework.