We study online optimization methods for zero-sum games, a fundamental problem in adversarial learning in machine learning, economics, and many other domains. Traditional methods approximate Nash equilibria (NE) using either regret-based methods (time-average convergence) or contraction-map-based methods (last-iterate convergence). We propose a new method based on Hamiltonian dynamics in physics and prove that it can characterize the set of NE in a finite (linear) number of iterations of alternating gradient descent in the unbounded setting, modulo degeneracy, a first in online optimization. Unlike standard methods for computing NE, our proposed approach can be parallelized and works with arbitrary learning rates, both firsts in algorithmic game theory. Experimentally, we support our results by showing our approach drastically outperforms standard methods.

Large Language Models (LLMs) enable new possibilities for qualitative research at scale, including coding and data annotation. While multi-agent systems (MAS) can emulate human coding workflows, their benefits over single-agent coding remain poorly understood. We conducted an experimental study of how agent persona and temperature shape consensus-building and coding accuracy of dialog segments based on a codebook with 8 codes. Our open-source MAS mirrors deductive human coding through structured agent discussion and consensus arbitration. Using six open-source LLMs (with 3 to 32 billion parameters) and 18 experimental configurations, we analyze over 77,000 coding decisions against a gold-standard dataset of human-annotated transcripts from online math tutoring sessions. Temperature significantly impacted whether and when consensus was reached across all six LLMs. MAS with multiple personas (including neutral, assertive, or empathetic), significantly delayed consensus in four out of six LLMs compared to uniform personas. In three of those LLMs, higher temperatures significantly diminished the effects of multiple personas on consensus. However, neither temperature nor persona pairing lead to robust improvements in coding accuracy. Single agents matched or outperformed MAS consensus in most conditions. Only one model (OpenHermesV2:7B) and code category showed above-chance gains from MAS deliberation when temperature was 0.5 or lower and especially when the agents included at least one assertive persona. Qualitative analysis of MAS collaboration for these configurations suggests that MAS may nonetheless aid in narrowing ambiguous code applications that could improve codebooks and human-AI coding. We contribute new insight into the limits of LLM-based qualitative methods, challenging the notion that diverse MAS personas lead to better outcomes. We open-source our MAS and experimentation code.

Autonomous systems are becoming an integral part of many application domains, like in the mobility sector. However, ensuring their safe and correct behaviour in dynamic and complex environments remains a significant challenge, where systems should autonomously make decisions e.g., about manoeuvring. We propose in this paper a general collaborative approach for increasing the level of trustworthiness in the environment of operation and improve reliability and good decision making in autonomous system. In the presence of conflicting information, aggregation becomes a major issue for trustworthy decision making based on collaborative data sharing. Unlike classical approaches in the literature that rely on consensus or majority as aggregation rule, we exploit the fact that autonomous systems have different quality attributes like perception quality. We use this criteria to determine which autonomous systems are trustworthy and borrow concepts from social epistemology to define aggregation and propagation rules, used for automated decision making. We use Binary Decision Diagrams (BDDs) as formal models for beliefs aggregation and propagation, and formulate reduction rules to reduce the size of the BDDs and allow efficient computation structures for collaborative automated reasoning. Autonomous systems have the ability to interact with their environment and act independently by solving complex tasks without human intervention. The main challenge with designing autonomous systems is to provide them with the ability to operate correctly and safely in dynamic and open contexts. That is, performing tasks at operation time in an environment that is uncertain or was not fully known or defined at design time. When extended to fields such as automated driving, where safety is a critical requirement, assuring high levels of trustworthiness and "good" decision making in complex environments becomes a real challenge. In this paper, we consider collaboration between autonomous systems to increase trustworthiness and improve decision making.

--Decentralized trading of real-world alternative assets (e.g., gold) requires bridging physical asset custody with blockchain systems while meeting strict requirements for compliance, liquidity, and risk management. We present a research-oriented architecture, GoldMine OS, that employs multiple specialized AI agents to automate and secure the tokenization and exchange of physical gold into a blockchain-based stablecoin ("OZ"). We detail the design of four cooperative agents (for Compliance, T oken Issuance, Market-Making, and Risk Control) and a coordinating core, and we evaluate the system through both simulation and a controlled pilot deployment. In experiments, the prototype achieves on-demand token issuance in under 1.2 s, a speed-up of over 100 compared to traditional manual workflows. The integrated Market-Making agent provides tight liquidity (spreads often <0.5%) even under volatile market conditions. Through fault injection tests, we demonstrate the system's resilience: an oracle price spoofing attack is detected and mitigated within 10 s, and a simulated vault mis-reporting triggers an immediate halt of issuances with minimal impact on users. Our results indicate that an AI-agent-based decentralized exchange for alternative assets can meet rigorous performance and safety requirements. We discuss the broader implications for democratizing access to traditionally illiquid assets and outline how our governance model (multi-signature agent updates and on-chain community voting on risk parameters) ensures ongoing transparency, adaptability, and formal assurance of system integrity. Tokenizing real-world assets (RW As) like precious metals on blockchains promises to democratize access to alternative investments, but it raises significant challenges in trust, compliance, and market stability [1] [2]. For instance, gold-backed cryptocurrencies such as P AX Gold (P AXG) and Tether Gold (XAUT) peg digital tokens to physical gold reserves, yet they rely heavily on centralized processes for custody and compliance [2]. Achieving a truly decentralized yet regulatorily compliant trading platform for assets like gold remains an open problem. Key hurdles include ensuring that on-chain token supply always mirrors off-chain reserves (requiring robust proof-of-reserve mechanisms), automating complex compliance checks (KYC/AML) in a user-friendly manner, providing continuous liquidity in thinly-traded assets, and guarding against failures of external data sources (the well-known oracle problem [3]). In this paper, we address these challenges by designing and evaluating GoldMine OS, an AI-driven multi-agent architecture for decentralized trading of gold-backed tokens.

In multiple unmanned ground vehicle confrontations, autonomously evolving multi-agent tactical decisions from situational awareness remain a significant challenge. Traditional handcraft rule-based methods become vulnerable in the complicated and transient battlefield environment, and current reinforcement learning methods mainly focus on action manipulation instead of strategic decisions due to lack of interpretability. Here, we propose a vision-language model-based commander to address the issue of intelligent perception-to-decision reasoning in autonomous confrontations. Our method integrates a vision language model for scene understanding and a lightweight large language model for strategic reasoning, achieving unified perception and decision within a shared semantic space, with strong adaptability and interpretability. Unlike rule-based search and reinforcement learning methods, the combination of the two modules establishes a full-chain process, reflecting the cognitive process of human commanders. Simulation and ablation experiments validate that the proposed approach achieves a win rate of over 80% compared with baseline models.

Reward functions, learned or manually specified, are rarely perfect. Instead of accurately expressing human goals, these reward functions are often distorted by human beliefs about how best to achieve those goals. Specifically, these reward functions often express a combination of the human's terminal goals -- those which are ends in themselves -- and the human's instrumental goals -- those which are means to an end. We formulate a simple example in which even slight conflation of instrumental and terminal goals results in severe misalignment: optimizing the misspecified reward function results in poor performance when measured by the true reward function. This example distills the essential properties of environments that make reinforcement learning highly sensitive to conflation of instrumental and terminal goals. We discuss how this issue can arise with a common approach to reward learning and how it can manifest in real environments.

This paper presents a multi-agent reinforcement learning (MARL) framework for cooperative collision avoidance of UA V swarms leveraging domain knowledge-driven reward. The reward is derived from knowledge in the domain of image processing, approximating contours on a two-dimensional field. By modeling obstacles as maxima on the field, collisions are inherently avoided as contours never go through peaks or intersect. Additionally, counters are smooth and energy-efficient. Our framework enables training with large swarm sizes as the agent interaction is minimized and the need for complex credit assignment schemes or observation sharing mechanisms in state-of-the-art MARL approaches are eliminated. Moreover, UA Vs obtain the ability to adapt to complex environments where contours may be nonviable or non-existent through intensive training. Extensive experiments are conducted to evaluate the performances of our framework against state-of-the-art MARL algorithms.

Therapy recommendation for chronic patients with multimorbidity is challenging due to risks of treatment conflicts. Existing decision support systems face scalability limitations. Inspired by the way in which general practitioners (GP) manage multimorbidity patients, occasionally convening multidisciplinary team (MDT) collaboration, this study investigated the feasibility and value of using a Large Language Model (LLM)-based multi-agent system (MAS) for safer therapy recommendations. We designed a single agent and a MAS framework simulating MDT decision-making by enabling discussion among LLM agents to resolve medical conflicts. The systems were evaluated on therapy planning tasks for multimorbidity patients using benchmark cases. We compared MAS performance with single-agent approaches and real-world benchmarks. An important contribution of our study is the definition of evaluation metrics that go beyond the technical precision and recall and allow the inspection of clinical goals met and medication burden of the proposed advices to a gold standard benchmark. Our results show that with current LLMs, a single agent GP performs as well as MDTs. The best-scoring models provide correct recommendations that address all clinical goals, yet the advices are incomplete. Some models also present unnecessary medications, resulting in unnecessary conflicts between medication and conditions or drug-drug interactions.

Protecting cyberspace requires not only advanced tools but also a shift in how we reason about threats, trust, and autonomy. Traditional cybersecurity methods rely on manual responses and brittle heuristics. To build proactive and intelligent defense systems, we need integrated theoretical frameworks and software tools. Game theory provides a rigorous foundation for modeling adversarial behavior, designing strategic defenses, and enabling trust in autonomous systems. Meanwhile, software tools process cyber data, visualize attack surfaces, verify compliance, and suggest mitigations. Yet a disconnect remains between theory and practical implementation. The rise of Large Language Models (LLMs) and agentic AI offers a new path to bridge this gap. LLM-powered agents can operationalize abstract strategies into real-world decisions. Conversely, game theory can inform the reasoning and coordination of these agents across complex workflows. LLMs also challenge classical game-theoretic assumptions, such as perfect rationality or static payoffs, prompting new models aligned with cognitive and computational realities. This co-evolution promises richer theoretical foundations and novel solution concepts. Agentic AI also reshapes software design: systems must now be modular, adaptive, and trust-aware from the outset. This chapter explores the intersection of game theory, agentic AI, and cybersecurity. We review key game-theoretic frameworks (e.g., static, dynamic, Bayesian, and signaling games) and solution concepts. We then examine how LLM agents can enhance cyber defense and introduce LLM-driven games that embed reasoning into AI agents. Finally, we explore multi-agent workflows and coordination games, outlining how this convergence fosters secure, intelligent, and adaptive cyber systems.

In Decentralized Multi-Agent Reinforcement Learning (MARL), the development of Emergent Communication has long been constrained by the ``Joint Exploration Dilemma'', leading agents to fall into a ``Communication Vacuum Equilibrium'' . Traditional methods address this by introducing inductive biases to facilitate communication emergence . This study fundamentally questions whether such artificial inductive biases are, in fact, over-engineering. Through experiments with the ``AI Mother Tongue'' (AIM) framework, based on a Vector Quantized Variational Autoencoder (VQ-VAE), we demonstrate that when agents possess an endogenous symbol system, their neural representations naturally exhibit spontaneous semantic compression and Nash equilibrium-driven semantic convergence, achieving effective symbolic communication without external inductive biases. This aligns with recent neuroscience findings suggesting that the human brain does not directly use human language for internal thought , and resonates with research on ``soft thinking'' capabilities in Large Language Models (LLMs) . Compared to traditional explicit communication methods, AIM demonstrates stronger generality and efficiency. The interpretable analysis toolkit developed in this study confirms that symbol usage exhibits a significant power-law distribution, leading to three major theoretical insights: the ``Neural Communication Hypothesis'', the ``Tool-First Principle'', and the ``Semantic Interpretability Paradigm''. Future research will explore the integration of Hierarchical Quantized Variational Autoencoders (HQ-VAE) to enhance AIM's complex expressive capabilities and investigate the potential for ``Reinforcement Learning (RL) Low-Level Pre-training''. This discovery offers new avenues for bridging symbolism and connectionism.