We present EPIC, an AI-driven platform designed to augment operational data analytics. EPIC employs a hierarchical multi-agent architecture where a top-level large language model provides query processing, reasoning and synthesis capabilities. These capabilities orchestrate three specialized low-level agents for information retrieval, descriptive analytics, and predictive analytics. This architecture enables EPIC to perform HPC operational analytics on multi-modal data, including text, images, and tabular formats, dynamically and iteratively. EPIC addresses the limitations of existing HPC operational analytics approaches, which rely on static methods that struggle to adapt to evolving analytics tasks and stakeholder demands. Through extensive evaluations on the Frontier HPC system, we demonstrate that EPIC effectively handles complex queries. Using descriptive analytics as a use case, fine-tuned smaller models outperform large state-of-the-art foundation models, achieving up to 26% higher accuracy. Additionally, we achieved 19x savings in LLM operational costs compared to proprietary solutions by employing a hybrid approach that combines large foundational models with fine-tuned local open-weight models.

Using Counter-Strike: Global Offensive (CS:GO) as a testbed, our framework accurately simulates gameplay using only movement decisions as tactical positioning--without explicitly modeling low-level mechanics such as aiming and shooting. Central to our approach is a waypoint system that simplifies and discretizes continuous states and actions, paired with neural predictive and generative models trained on real CS:GO tournament data to reconstruct event outcomes. Extensive evaluations show that replays generated from human data in DECOY closely match those observed in the original game. Our publicly available simulation environment provides a valuable tool for advancing research in strategic multi-agent planning and behavior generation. 1 INTRODUCTION Team-based multiplayer strategy games have emerged as grand challenge domains for multi-agent learning and long-horizon planning. Breakthroughs in complex games such as StarCraft II and Dota 2--where AI agents have achieved human-expert or even superhuman performance through large-scale self-play training (Baker et al. 2019; Vinyals et al. 2019; Berner et al. 2019; Open Ended Learning Team et al. 2021)--demonstrate that, given sufficient simulation and training, sophisticated strategies can be discovered even in environments characterized by long time horizons, imperfect information, and high-dimensional state-action spaces. However, these successes come at the expense of enormous computational costs, and a prevailing trend in the field is to scale performance by increasing model size and training on larger datasets with more simulation steps (Neumann and Gros 2022; Obando-Ceron et al. 2024; Kaplan et al. 2020).

The rise of Multi-Agent Systems (MAS) in Artificial Intelligence (AI), especially integrated with Large Language Models (LLMs), has greatly facilitated the resolution of complex tasks. However, current systems are still facing challenges of inter-agent communication, coordination, and interaction with heterogeneous tools and resources. Most recently, the Model Context Protocol (MCP) by Anthropic and Agent-to-Agent (A2A) communication protocol by Google have been introduced, and to the best of our knowledge, very few applications exist where both protocols are employed within a single MAS framework. We present a pilot study of AgentMaster, a novel modular multi-protocol MAS framework with self-implemented A2A and MCP, enabling dynamic coordination, flexible communication, and rapid development with faster iteration. Through a unified conversational interface, the system supports natural language interaction without prior technical expertise and responds to multimodal queries for tasks including information retrieval, question answering, and image analysis. The experiments are validated through both human evaluation and quantitative metrics, including BERTScore F1 (96.3%) and LLM-as-a-Judge G-Eval (87.1%). These results demonstrate robust automated inter-agent coordination, query decomposition, task allocation, dynamic routing, and domain-specific relevant responses. Overall, our proposed framework contributes to the potential capabilities of domain-specific, cooperative, and scalable conversational AI powered by MAS.

Decentralized combinatorial optimization in evolving multi-agent systems poses significant challenges, requiring agents to balance long-term decision-making, short-term optimized collective outcomes, while preserving autonomy of interactive agents under unanticipated changes. Reinforcement learning offers a way to model sequential decision-making through dynamic programming to anticipate future environmental changes. However, applying multi-agent reinforcement learning (MARL) to decentralized combinatorial optimization problems remains an open challenge due to the exponential growth of the joint state-action space, high communication overhead, and privacy concerns in centralized training. To address these limitations, this paper proposes Hierarchical Reinforcement and Collective Learning (HRCL), a novel approach that leverages both MARL and decentralized collective learning based on a hierarchical framework. Agents take high-level strategies using MARL to group possible plans for action space reduction and constrain the agent behavior for Pareto optimality. Meanwhile, the low-level collective learning layer ensures efficient and decentralized coordinated decisions among agents with minimal communication. Extensive experiments in a synthetic scenario and real-world smart city application models, including energy self-management and drone swarm sensing, demonstrate that HRCL significantly improves performance, scalability, and adaptability compared to the standalone MARL and collective learning approaches, achieving a win-win synthesis solution.

Intelligent systems have traditionally been designed as tools rather than collaborators, often lacking critical characteristics that collaboration partnerships require. Recent advances in large language model (LLM) agents open new opportunities for human-LLM-agent collaboration by enabling natural communication and various social and cognitive behaviors. Yet it remains unclear whether principles of computer-mediated collaboration established in HCI and CSCW persist, change, or fail when humans collaborate with LLM agents. To support systematic investigations of these questions, we introduce an open and configurable research platform for HCI researchers. The platform's modular design allows seamless adaptation of classic CSCW experiments and manipulation of theory-grounded interaction controls. We demonstrate the platform's effectiveness and usability through two case studies: (1) re-implementing the classic human-human-collaboration task Shape Factory as a between-subject human-agent-collaboration experiment with 16 participants, and (2) a participatory cognitive walkthrough with five HCI researchers to refine workflows and interfaces for experiment setup and analysis.

In this work, we consider learning over multitask graphs, where each agent aims to estimate its own parameter vector. Although agents seek distinct objectives, collaboration among them can be beneficial in scenarios where relationships between tasks exist. Among the various approaches to promoting relationships between tasks and, consequently, enhancing collaboration between agents, one notable method is regularization. While previous multitask learning studies have focused on smooth regularization to enforce graph smoothness, this work explores non-smooth regularization techniques that promote sparsity, making them particularly effective in encouraging piecewise constant transitions on the graph. We begin by formulating a global regularized optimization problem, which involves minimizing the aggregate sum of individual costs, regularized by a general non-smooth term designed to promote piecewise-constant relationships between the tasks of neighboring agents. Based on the forward-backward splitting strategy, we propose a decentralized learning approach that enables efficient solutions to the regularized optimization problem. Then, under convexity assumptions on the cost functions and co-regularization, we establish that the proposed approach converges in the mean-square-error sense within $O(μ)$ of the optimal solution of the globally regularized cost. For broader applicability and improved computational efficiency, we also derive closed-form expressions for commonly used non-smooth (and, possibly, non-convex) regularizers, such as the weighted sum of the $\ell_0$-norm, $\ell_1$-norm, and elastic net regularization. Finally, we illustrate both the theoretical findings and the effectiveness of the approach through simulations.

The evolution of morality presents a puzzle: natural selection should favor self-interest, yet humans developed moral systems promoting altruism. We address this question by introducing a novel Large Language Model (LLM)-based agent simulation framework modeling prehistoric hunter-gatherer societies. This platform is designed to probe diverse questions in social evolution, from survival advantages to inter-group dynamics. To investigate moral evolution, we designed agents with varying moral dispositions based on the Expanding Circle Theory \citep{singer1981expanding}. We evaluated their evolutionary success across a series of simulations and analyzed their decision-making in specially designed moral dilemmas. These experiments reveal how an agent's moral framework, in combination with its cognitive constraints, directly shapes its behavior and determines its evolutionary outcome. Crucially, the emergent patterns echo seminal theories from related domains of social science, providing external validation for the simulations. This work establishes LLM-based simulation as a powerful new paradigm to complement traditional research in evolutionary biology and anthropology, opening new avenues for investigating the complexities of moral and social evolution.

In this paper, we present the first systematic comparison of Data Assimilation (DA) and Likelihood-Based Inference (LBI) in the context of Agent-Based Models (ABMs). These models generate observable time series driven by evolving, partially-latent microstates. Latent states need to be estimated to align simulations with real-world data -- a task traditionally addressed by DA, especially in continuous and equation-based models such as those used in weather forecasting. However, the nature of ABMs poses challenges for standard DA methods. Solving such issues requires adaptation of previous DA techniques, or ad-hoc alternatives such as LBI. DA approximates the likelihood in a model-agnostic way, making it broadly applicable but potentially less precise. In contrast, LBI provides more accurate state estimation by directly leveraging the model's likelihood, but at the cost of requiring a hand-crafted, model-specific likelihood function, which may be complex or infeasible to derive. We compare the two methods on the Bounded-Confidence Model, a well-known opinion dynamics ABM, where agents are affected only by others holding sufficiently similar opinions. We find that LBI better recovers latent agent-level opinions, even under model mis-specification, leading to improved individual-level forecasts. At the aggregate level, however, both methods perform comparably, and DA remains competitive across levels of aggregation under certain parameter settings. Our findings suggest that DA is well-suited for aggregate predictions, while LBI is preferable for agent-level inference.

Large language models (LLMs) have advanced code generation from single-function tasks to competitive-programming problems, but existing multi-agent solutions either rely on costly large-scale ($>$ 30B) models or collapse when downsized to small open-source models. We present MapCoder-Lite, which upgrades a single 7B model into four role-specialised agents-retriever, planner, coder, and debugger-using only rank-32, role-specific LoRA adapters ($<3\%$ extra parameters). Three lightweight techniques make this possible: (i) trajectory distillation from strong LLMs fixes format fragility in retrieval and debugging, (ii) supervisor-guided correction strengthens planning and coding agents, and (iii) agent-wise LoRA fine-tuning delivers memory-efficient specialisation. Comprehensive evaluation on xCodeEval, APPS, and CodeContests shows that MapCoder-Lite more than doubles xCodeEval accuracy (from $13.2\%$ to $28.3\%$), eliminates all format failures, and closes to within six points of a 32B baseline while cutting GPU memory and token-generation time by $4\times$. These results demonstrate that careful agent-wise fine-tuning unleashes high-quality multi-agent coding on a small language model.

The increasing autonomy of LLM agents in handling sensitive communications, accelerated by Model Context Protocol (MCP) and Agent-to-Agent (A2A) frameworks, creates urgent privacy challenges. While recent work reveals significant gaps between LLMs' privacy Q&A performance and their agent behavior, existing benchmarks remain limited to static, simplified scenarios. We present PrivacyChecker, a model-agnostic, contextual integrity based mitigation approach that effectively reduces privacy leakage from 36.08% to 7.30% on DeepSeek-R1 and from 33.06% to 8.32% on GPT-4o, all while preserving task helpfulness. We also introduce PrivacyLens-Live, transforming static benchmarks into dynamic MCP and A2A environments that reveal substantially higher privacy risks in practical. Our modular mitigation approach integrates seamlessly into agent protocols through three deployment strategies, providing practical privacy protection for the emerging agentic ecosystem. Our data and code will be made available at https://aka.ms/privacy_in_action.