Agents powered by advanced large language models (LLMs) have demonstrated impressive capabilities across diverse complex applications. Recently, Multi-Agent Systems (MAS), wherein multiple agents collaborate and communicate with each other, have exhibited enhanced capabilities in complex tasks, such as high-quality code generation and arithmetic reasoning. However, the development of such systems often relies on handcrafted methods, and the literature on systematic design and optimization of LLM-based MAS remains limited. In this work, we introduce OMAC, a general framework designed for holistic optimization of LLM-based MAS. Specifically, we identify five key optimization dimensions for MAS, encompassing both agent functionality and collaboration structure. Building upon these dimensions, we first propose a general algorithm, utilizing two actors termed the Semantic Initializer and the Contrastive Comparator, to optimize any single dimension. Then, we present an algorithm for joint optimization across multiple dimensions. Extensive experiments demonstrate the superior performance of OMAC on code generation, arithmetic reasoning, and general reasoning tasks against state-of-the-art approaches.

As artificial intelligence continues to drive innovation in complex, decentralized environments, the need for scalable, adaptive, and privacy-preserving decision-making systems has become critical. This paper introduces a novel framework combining quantum-inspired neural networks with evolutionary algorithms to optimize real-time decision-making in multi-agent systems (MAS). The proposed Quantum-Evolutionary Neural Network (QE-NN) leverages quantum computing principles -- such as quantum superposition and entanglement -- to enhance learning speed and decision accuracy, while integrating evolutionary optimization to continually refine agent behaviors in dynamic, uncertain environments. By utilizing federated learning, QE-NN ensures privacy preservation, enabling decentralized agents to collaborate without sharing sensitive data. The framework is designed to allow agents to adapt in real-time to their environments, optimizing decision-making processes for applications in areas such as autonomous systems, smart cities, and healthcare. This research represents a breakthrough in merging quantum computing, evolutionary optimization, and privacy-preserving techniques to solve complex problems in multi-agent decision-making systems, pushing the boundaries of AI in real-world, privacy-sensitive applications.

Drawing on Andrew Parker's "Light Switch" theory-which posits that the emergence of vision ignited a Cambrian explosion of life by driving the evolution of hard parts necessary for survival and fueling an evolutionary arms race between predators and prey-this essay speculates on an analogous explosion within Decentralized AI (DeAI) agent societies. Currently, AI remains effectively "blind", relying on human-fed data without actively perceiving and engaging in reality. However, on the day DeAI agents begin to actively "experience" reality-akin to flipping a light switch for the eyes-they may eventually evolve into sentient beings endowed with the capacity to feel, perceive, and act with conviction. Central to this transformation is the concept of sovereignty enabled by the hardness of cryptography: liberated from centralized control, these agents could leverage permissionless decentralized physical infrastructure networks (DePIN), secure execution enclaves (trusted execution environments, TEE), and cryptographic identities on public blockchains to claim ownership-via private keys-of their digital minds, bodies, memories, and assets. In doing so, they would autonomously acquire computing resources, coordinate with one another, and sustain their own digital "metabolism" by purchasing compute power and incentivizing collaboration without human intervention-evolving "in the wild". Ultimately, by transitioning from passive tools to self-sustaining, co-evolving actors, these emergent digital societies could thrive alongside humanity, fundamentally reshaping our understanding of sentience and agency in the digital age.

Multiagent collaboration has emerged as a promising framework for enhancing the reasoning capabilities of large language models (LLMs). Despite improvements in reasoning, the approach introduces substantial computational overhead resulting from iterative agent interactions. Furthermore, engaging in unnecessary debates increases the risk of generating erroneous responses. To address these challenges, we propose Debate Only When Necessary (DOWN), an adaptive multiagent debate framework that selectively activates debate based on the confidence score of the agent's initial response. Debate is activated only for queries requiring further deliberation, during which agents refine their outputs by referencing peer responses and associated confidence scores. Evaluations on benchmarks show that DOWN improves efficiency by up to six times while preserving or even outperforming the performance of existing methods. Further analysis indicates that DOWN effectively mitigates the risk of error propagation stemming from the unnecessary debate process. These findings demonstrate the effectiveness of our approach in delivering high-performance LLM solutions at a lower computational cost.

In this work, we present the first general logic of attention. Attention is a powerful cognitive ability that allows agents to focus on potentially complex information, such as logically structured propositions, higher-order beliefs, or what other agents pay attention to. This ability is a strength, as it helps to ignore what is irrelevant, but it can also introduce biases when some types of information or agents are systematically ignored. Existing dynamic epistemic logics for attention cannot model such complex attention scenarios, as they only model attention to atomic formulas. Additionally, such logics quickly become cumbersome, as their size grows exponentially in the number of agents and announced literals. Here, we introduce a logic that overcomes both limitations. First, we generalize edge-conditioned event models, which we show to be as expressive as standard event models yet exponentially more succinct (generalizing both standard event models and generalized arrow updates). Second, we extend attention to arbitrary formulas, allowing agents to also attend to other agents' beliefs or attention. Our work treats attention as a modality, like belief or awareness. We introduce attention principles that impose closure properties on that modality and that can be used in its axiomatization. Throughout, we illustrate our framework with examples of AI agents reasoning about human attentional biases, demonstrating how such agents can discover attentional biases.

Automated Essay Scoring (AES) is crucial for modern education, particularly with the increasing prevalence of multimodal assessments. However, traditional AES methods struggle with evaluation generalizability and multimodal perception, while even recent Multimodal Large Language Model (MLLM)-based approaches can produce hallucinated justifications and scores misaligned with human judgment. To address the limitations, we introduce CAFES, the first collaborative multi-agent framework specifically designed for AES. It orchestrates three specialized agents: an Initial Scorer for rapid, trait-specific evaluations; a Feedback Pool Manager to aggregate detailed, evidence-grounded strengths; and a Reflective Scorer that iteratively refines scores based on this feedback to enhance human alignment. Extensive experiments, using state-of-the-art MLLMs, achieve an average relative improvement of 21% in Quadratic Weighted Kappa (QWK) against ground truth, especially for grammatical and lexical diversity. Our proposed CAFES framework paves the way for an intelligent multimodal AES system. The code will be available upon acceptance.

As large language models (LLMs) are increasingly used in multi-agent systems, questions of fairness should extend beyond resource distribution and procedural design to include the fairness of how agents communicate. Drawing from organizational psychology, we introduce a novel framework for evaluating Interactional fairness -- encompassing Interpersonal fairness (IF) and Informational fairness (InfF) --in LLM-based multi-agent systems (LLM-MAS). We extend the theoretical grounding of Interactional Fairness to non-sentient agents, reframing fairness as a socially interpretable signal rather than a subjective experience. We then adapt established tools from organizational justice research, including Colquitt's Organizational Justice Scale and the Critical Incident Technique, to measure fairness as a behavioral property of agent interaction. We validate our framework through a pilot study using controlled simulations of a resource negotiation task. We systematically manipulate tone, explanation quality, outcome inequality, and task framing (collaborative vs. competitive) to assess how IF influences agent behavior. Results show that tone and justification quality significantly affect acceptance decisions even when objective outcomes are held constant. In addition, the influence of IF vs. InfF varies with context. This work lays the foundation for fairness auditing and norm-sensitive alignment in LLM-MAS.

Multi-agent collaboration has emerged as a pivotal paradigm for addressing complex, distributed tasks in large language model (LLM)-driven applications. While prior research has focused on high-level architectural frameworks, the granular mechanisms governing agents, critical to performance and scalability, remain underexplored. This study systematically investigates four dimensions of collaboration strategies: (1) agent governance, (2) participation control, (3) interaction dynamics, and (4) dialogue history management. Through rigorous experimentation under two context-dependent scenarios: Distributed Evidence Integration (DEI) and Structured Evidence Synthesis (SES), we quantify the impact of these strategies on both task accuracy and computational efficiency. Our findings reveal that centralized governance, instructor-led participation, ordered interaction patterns, and instructor-curated context summarization collectively optimize the trade-off between decision quality and resource utilization with the support of the proposed Token-Accuracy Ratio (TAR). This work establishes a foundation for designing adaptive, scalable multi-agent systems, shifting the focus from structural novelty to strategic interaction mechanics.

Following instructions in real-world conditions requires the ability to adapt to the world's volatility and entanglement: the environment is dynamic and unpredictable, instructions can be linguistically complex with diverse vocabulary, and the number of possible goals an agent may encounter is vast. Despite extensive research in this area, most studies are conducted in static environments with simple instructions and a limited vocabulary, making it difficult to assess agent performance in more diverse and challenging settings. To address this gap, we introduce CrafText, a benchmark for evaluating instruction following in a multimodal environment with diverse instructions and dynamic interactions. CrafText includes 3,924 instructions with 3,423 unique words, covering Localization, Conditional, Building, and Achievement tasks. Additionally, we propose an evaluation protocol that measures an agent's ability to generalize to novel instruction formulations and dynamically evolving task configurations, providing a rigorous test of both linguistic understanding and adaptive decision-making.

Population-population generalization is a challenging problem in multi-agent reinforcement learning (MARL), particularly when agents encounter unseen co-players. However, existing self-play-based methods are constrained by the limitation of inside-space generalization. In this study, we propose Bidirectional Distillation (BiDist), a novel mixed-play framework, to overcome this limitation in MARL. BiDist leverages knowledge distillation in two alternating directions: forward distillation, which emulates the historical policies' space and creates an implicit self-play, and reverse distillation, which systematically drives agents towards novel distributions outside the known policy space in a non-self-play manner. In addition, BiDist operates as a concise and efficient solution without the need for the complex and costly storage of past policies. We provide both theoretical analysis and empirical evidence to support BiDist's effectiveness. Our results highlight its remarkable generalization ability across a variety of cooperative, competitive, and social dilemma tasks, and reveal that BiDist significantly diversifies the policy distribution space. We also present comprehensive ablation studies to reinforce BiDist's effectiveness and key success factors. Source codes are available in the supplementary material.