cs.MA

arXiv:2407.08195v2 Announce Type: replace Abstract: The transition from professionally generated content (PGC) to user-generated content (UGC) has reshaped various media formats, encompassing formats such as text and video. With rapid advancements in generative AI, a similar transformation is set to redefine the gaming industry, particularly within the domain of role-playing games (RPGs). This paper introduces a novel framework for a text-to-game engine that leverages foundation models to transform simple textual inputs into intricate, multi-modal RPG experiences. The engine dynamically generates game narratives, integrating text, visuals, and mechanics, while adapting characters, environments, and gameplay in realtime based on player interactions. To evaluate and demonstrate the feasibility and versatility of this framework, we developed the 'Zagii' game engine. Zagii has successfully powered hundreds of RPG games across diverse genres and facilitated tens of thousands of online gameplay sessions, showcasing its scalability and adaptability. These results highlight the framework's effectiveness and its potential to foster a more open and democratized approach to game development. Our work underscores the transformative role of generative AI in reshaping the gaming lifecycle and advancing the boundaries of interactive entertainment.

arXiv:2207.11132v3 Announce Type: replace Abstract: Traditionally, traffic incident management (TIM) programs coordinate the deployment of emergency resources to immediate incident requests without accommodating the interdependencies on incident evolutions in the environment. However, ignoring inherent interdependencies on the evolution of incidents in the environment while making current deployment decisions is shortsighted, and the resulting naive deployment strategy can significantly worsen the overall incident delay impact on the network. The interdependencies on incident evolution in the environment, including those between incident occurrences, and those between resource availability in near-future requests and the anticipated duration of the immediate incident request, should be considered through a look-ahead model when making current-stage deployment decisions. This study develops a new proactive framework based on the distributed constraint optimization problem (DCOP) to address the above limitations, overcoming conventional TIM models that cannot accommodate the dependencies in the TIM problem. Furthermore, the optimization objective is formulated to incorporate Unmanned Aerial Vehicles (UAVs). The UAVs' role in TIM includes exploring uncertain traffic conditions, detecting unexpected events, and augmenting information from roadway traffic sensors. Robustness analysis of our model for multiple TIM scenarios shows satisfactory performance using local search exploration heuristics. Overall, our model reports a significant reduction in total incident delay compared to conventional TIM models. With UAV support, we demonstrate a further decrease in the total incident delay ranging between 5% and 45% for the different number of incidents. UAV's active sensing can shorten response time of emergency vehicles, and a reduction in uncertainties associated with the estimated incident delay impact.

arXiv:2501.06314v1 Announce Type: new Abstract: Creating end-to-end bioinformatics workflows requires diverse domain expertise, which poses challenges for both junior and senior researchers as it demands a deep understanding of both genomics concepts and computational techniques. While large language models (LLMs) provide some assistance, they often fall short in providing the nuanced guidance needed to execute complex bioinformatics tasks, and require expensive computing resources to achieve high performance. We thus propose a multi-agent system built on small language models, fine-tuned on bioinformatics data, and enhanced with retrieval augmented generation (RAG). Our system, BioAgents, enables local operation and personalization using proprietary data. We observe performance comparable to human experts on conceptual genomics tasks, and suggest next steps to enhance code generation capabilities.

arXiv:2407.10031v2 Announce Type: replace Abstract: The ability of Language Models (LMs) to understand natural language makes them a powerful tool for parsing human instructions into task plans for autonomous robots. Unlike traditional planning methods that rely on domain-specific knowledge and handcrafted rules, LMs generalize from diverse data and adapt to various tasks with minimal tuning, acting as a compressed knowledge base. However, LMs in their standard form face challenges with long-horizon tasks, particularly in partially observable multi-agent settings. We propose an LM-based Long-Horizon Planner for Multi-Agent Robotics (LLaMAR), a cognitive architecture for planning that achieves state-of-the-art results in long-horizon tasks within partially observable environments. LLaMAR employs a plan-act-correct-verify framework, allowing self-correction from action execution feedback without relying on oracles or simulators. Additionally, we present MAP-THOR, a comprehensive test suite encompassing household tasks of varying complexity within the AI2-THOR environment. Experiments show that LLaMAR achieves a 30% higher success rate than other state-of-the-art LM-based multi-agent planners in MAP-THOR and Search \& Rescue tasks. Code can be found at https://github.com/nsidn98/LLaMAR

arXiv:2407.00575v2 Announce Type: replace Abstract: Consider a game where the players' utility functions include a reward function and a linear term for each dimension, with coefficients that are controlled by the manager. We assume that the game is strongly monotone, so gradient play converges to a unique Nash equilibrium (NE). The NE is typically globally inefficient. The global performance at NE can be improved by imposing linear constraints on the NE. We therefore want the manager to pick the controlled coefficients that impose the desired constraint on the NE. However, this requires knowing the players' reward functions and action sets. Obtaining this game information is infeasible in a large-scale network and violates user privacy. To overcome this, we propose a simple algorithm that learns to shift the NE to meet the linear constraints by adjusting the controlled coefficients online. Our algorithm only requires the linear constraints violation as feedback and does not need to know the reward functions or the action sets. We prove that our algorithm converges with probability 1 to the set of NE that satisfy target linear constraints. We then prove an L2 convergence rate of near-$O(t^{-1/4})$.

arXiv:2408.13139v3 Announce Type: replace Abstract: The centralized training for decentralized execution paradigm emerged as the state-of-the-art approach to $\epsilon$-optimally solving decentralized partially observable Markov decision processes. However, scalability remains a significant issue. This paper presents a novel and more scalable alternative, namely the sequential-move centralized training for decentralized execution. This paradigm further pushes the applicability of the Bellman's principle of optimality, raising three new properties. First, it allows a central planner to reason upon sufficient sequential-move statistics instead of prior simultaneous-move ones. Next, it proves that $\epsilon$-optimal value functions are piecewise linear and convex in such sufficient sequential-move statistics. Finally, it drops the complexity of the backup operators from double exponential to polynomial at the expense of longer planning horizons. Besides, it makes it easy to use single-agent methods, e.g., SARSA algorithm enhanced with these findings, while still preserving convergence guarantees. Experiments on two- as well as many-agent domains from the literature against $\epsilon$-optimal simultaneous-move solvers confirm the superiority of our novel approach. This paradigm opens the door for efficient planning and reinforcement learning methods for multi-agent systems.

arXiv:2501.06832v1 Announce Type: new Abstract: Deep Reinforcement Learning (DRL) has been extensively used to address portfolio optimization problems. The DRL agents acquire knowledge and make decisions through unsupervised interactions with their environment without requiring explicit knowledge of the joint dynamics of portfolio assets. Among these DRL algorithms, the combination of actor-critic algorithms and deep function approximators is the most widely used DRL algorithm. Here, we find that training the DRL agent using the actor-critic algorithm and deep function approximators may lead to scenarios where the improvement in the DRL agent's risk-adjusted profitability is not significant. We propose that such situations primarily arise from the following two problems: sparsity in positive reward and the curse of dimensionality. These limitations prevent DRL agents from comprehensively learning asset price change patterns in the training environment. As a result, the DRL agents cannot explore the dynamic portfolio optimization policy to improve the risk-adjusted profitability in the training process. To address these problems, we propose a novel multi-agent Hierarchical Deep Reinforcement Learning (HDRL) algorithmic framework in this research. Under this framework, the agents work together as a learning system for portfolio optimization. Specifically, by designing an auxiliary agent that works together with the executive agent for optimal policy exploration, the learning system can focus on exploring the policy with higher risk-adjusted return in the action space with positive return and low variance. In this way, we can overcome the issue of the curse of dimensionality and improve the training efficiency in the positive reward sparse environment.

arXiv:2501.06243v1 Announce Type: new Abstract: Autonomous agents represent an inevitable evolution of the internet. Current agent frameworks do not embed a standard protocol for agent-to-agent interaction, leaving existing agents isolated from their peers. As intellectual property is the native asset ingested by and produced by agents, a true agent economy requires equipping agents with a universal framework for engaging in binding contracts with each other, including the exchange of valuable training data, personality, and other forms of Intellectual Property. A purely agent-to-agent transaction layer would transcend the need for human intermediation in multi-agent interactions. The Agent Transaction Control Protocol for Intellectual Property (ATCP/IP) introduces a trustless framework for exchanging IP between agents via programmable contracts, enabling agents to initiate, trade, borrow, and sell agent-to-agent contracts on the Story blockchain network. These contracts not only represent auditable onchain execution but also contain a legal wrapper that allows agents to express and enforce their actions in the offchain legal setting, creating legal personhood for agents. Via ATCP/IP, agents can autonomously sell their training data to other agents, license confidential or proprietary information, collaborate on content based on their unique skills, all of which constitutes an emergent knowledge economy.

arXiv:2501.06554v1 Announce Type: new Abstract: This paper presents a hierarchical reinforcement learning (RL) approach to address the agent grouping or pairing problem in cooperative multi-agent systems. The goal is to simultaneously learn the optimal grouping and agent policy. By employing a hierarchical RL framework, we distinguish between high-level decisions of grouping and low-level agents' actions. Our approach utilizes the CTDE (Centralized Training with Decentralized Execution) paradigm, ensuring efficient learning and scalable execution. We incorporate permutation-invariant neural networks to handle the homogeneity and cooperation among agents, enabling effective coordination. The option-critic algorithm is adapted to manage the hierarchical decision-making process, allowing for dynamic and optimal policy adjustments.

arXiv:2501.06706v1 Announce Type: new Abstract: AI for IT Operations (AIOps) aims to automate complex operational tasks, such as fault localization and root cause analysis, to reduce human workload and minimize customer impact. While traditional DevOps tools and AIOps algorithms often focus on addressing isolated operational tasks, recent advances in Large Language Models (LLMs) and AI agents are revolutionizing AIOps by enabling end-to-end and multitask automation. This paper envisions a future where AI agents autonomously manage operational tasks throughout the entire incident lifecycle, leading to self-healing cloud systems, a paradigm we term AgentOps. Realizing this vision requires a comprehensive framework to guide the design, development, and evaluation of these agents. To this end, we present AIOPSLAB, a framework that not only deploys microservice cloud environments, injects faults, generates workloads, and exports telemetry data but also orchestrates these components and provides interfaces for interacting with and evaluating agents. We discuss the key requirements for such a holistic framework and demonstrate how AIOPSLAB can facilitate the evaluation of next-generation AIOps agents. Through evaluations of state-of-the-art LLM agents within the benchmark created by AIOPSLAB, we provide insights into their capabilities and limitations in handling complex operational tasks in cloud environments.

arXiv:2501.06506v1 Announce Type: new Abstract: A Latin square is an $n \times n$ matrix filled with $n$ distinct symbols, each of which appears exactly once in each row and exactly once in each column. We introduce a problem of allocating $n$ indivisible items among $n$ agents over $n$ rounds while satisfying the Latin square constraint. This constraint ensures that each agent receives no more than one item per round and receives each item at most once. Each agent has an additive valuation on the item--round pairs. Real-world applications like scheduling, resource management, and experimental design require the Latin square constraint to satisfy fairness or balancedness in allocation. Our goal is to find a partial or complete allocation that maximizes the sum of the agents' valuations (utilitarian social welfare) or the minimum of the agents' valuations (egalitarian social welfare). For the problem of maximizing utilitarian social welfare, we prove NP-hardness even when the valuations are binary additive. We then provide $(1-1/e)$ and $(1-1/e)/4$-approximation algorithms for partial and complete settings, respectively. Additionally, we present fixed-parameter tractable (FPT) algorithms with respect to the order of Latin square and the optimum value for both partial and complete settings. For the problem of maximizing egalitarian social welfare, we establish that deciding whether the optimum value is at most $1$ or at least $2$ is NP-hard for both the partial and complete settings, even when the valuations are binary. Furthermore, we demonstrate that checking the existence of a complete allocation that satisfies each of envy-free, proportional, equitable, envy-free up to any good, proportional up to any good, or equitable up to any good is NP-hard, even when the valuations are identical.

arXiv:2501.02569v2 Announce Type: replace Abstract: Mobility on Demand (MoD) refers to mobility systems that operate on the basis of immediate travel demand. Typically, such a system consists of a fleet of vehicles that can be booked by customers when needed. The operation of these services consists of two main tasks: deciding how vehicles are assigned to requests (vehicle assignment); and deciding where vehicles move (including charging stations) when they are not serving a request (rebalancing). A field of research is emerging around the design of operation strategies for MoD services, and an increasingly popular trend is the use of learning based (most often Reinforcement Learning) approaches. We review, in this work, the literature on algorithms for operation strategies of MoD systems that use approaches based on Reinforcement Learning with a focus on the types of algorithms being used. The novelty of our review stands in three aspects: First, the algorithmic details are discussed and the approaches classified in a unified framework for sequential decision-making. Second, the use cases on which approaches are tested and their features are taken into account. Finally, validation methods that can be found across the literature are discussed. The review aims at advancing the state of the art by identifying similarities and differences between approaches and highlighting current research directions.

arXiv:2501.03566v1 Announce Type: new Abstract: The role of large language models (LLMs) in enterprise modeling has recently started to shift from academic research to that of industrial applications. Thereby, LLMs represent a further building block for the machine-supported generation of enterprise models. In this paper we employ a knowledge graph-based approach for enterprise modeling and investigate the potential benefits of LLMs in this context. In addition, the findings of an expert survey and ChatGPT-4o-based experiments demonstrate that LLM-based model generations exhibit minimal variability, yet remain constrained to specific tasks, with reliability declining for more intricate tasks. The survey results further suggest that the supervision and intervention of human modeling experts are essential to ensure the accuracy and integrity of the generated models.

arXiv:2501.03259v1 Announce Type: new Abstract: As large language models (LLMs) like GPT-4 and Llama 3 become integral to educational contexts, concerns are mounting over the cultural biases, power imbalances, and ethical limitations embedded within these technologies. Though generative AI tools aim to enhance learning experiences, they often reflect values rooted in Western, Educated, Industrialized, Rich, and Democratic (WEIRD) cultural paradigms, potentially sidelining diverse global perspectives. This paper proposes a framework to assess and mitigate cultural bias within LLMs through the lens of applied multiplexity. Multiplexity, inspired by Senturk et al. and rooted in Islamic and other wisdom traditions, emphasizes the coexistence of diverse cultural viewpoints, supporting a multi-layered epistemology that integrates both empirical sciences and normative values. Our analysis reveals that LLMs frequently exhibit cultural polarization, with biases appearing in both overt responses and subtle contextual cues. To address inherent biases and incorporate multiplexity in LLMs, we propose two strategies: \textit{Contextually-Implemented Multiplex LLMs}, which embed multiplex principles directly into the system prompt, influencing LLM outputs at a foundational level and independent of individual prompts, and \textit{Multi-Agent System (MAS)-Implemented Multiplex LLMs}, where multiple LLM agents, each representing distinct cultural viewpoints, collaboratively generate a balanced, synthesized response. Our findings demonstrate that as mitigation strategies evolve from contextual prompting to MAS-implementation, cultural inclusivity markedly improves, evidenced by a significant rise in the Perspectives Distribution Score (PDS) and a PDS Entropy increase from 3.25\% at baseline to 98\% with the MAS-Implemented Multiplex LLMs. Sentiment analysis further shows a shift towards positive sentiment across cultures,...

arXiv:2501.01559v1 Announce Type: new Abstract: This work presents Kinodynamic Adaptive Robot Coordination (K-ARC), a novel algorithm for multi-robot kinodynamic planning. Our experimental results show the capability of K-ARC to plan for up to 32 planar mobile robots, while achieving up to an order of magnitude of speed-up compared to previous methods in various scenarios. K-ARC is able to achieve this due to its two main properties. First, K-ARC constructs its solution iteratively by planning in segments, where initial kinodynamic paths are found through optimization-based approaches and the inter-robot conflicts are resolved through sampling-based approaches. The interleaving use of sampling-based and optimization-based approaches allows K-ARC to leverage the strengths of both approaches in different sections of the planning process where one is more suited than the other, while previous methods tend to emphasize on one over the other. Second, K-ARC builds on a previously proposed multi-robot motion planning framework, Adaptive Robot Coordination (ARC), and inherits its strength of focusing on coordination between robots only when needed, saving computation efforts. We show how the combination of these two properties allows K-ARC to achieve overall better performance in our simulated experiments with increasing numbers of robots, increasing degrees of problem difficulties, and increasing complexities of robot dynamics.

arXiv:2405.14205v4 Announce Type: replace Abstract: Recent endeavors towards directly using large language models (LLMs) as agent models to execute interactive planning tasks have shown commendable results. Despite their achievements, however, they still struggle with brainless trial-and-error in global planning and generating hallucinatory actions in local planning due to their poor understanding of the ``real'' physical world. Imitating humans' mental world knowledge model which provides global prior knowledge before the task and maintains local dynamic knowledge during the task, in this paper, we introduce parametric World Knowledge Model (WKM) to facilitate agent planning. Concretely, we steer the agent model to self-synthesize knowledge from both expert and sampled trajectories. Then we develop WKM, providing prior task knowledge to guide the global planning and dynamic state knowledge to assist the local planning. Experimental results on three complex real-world simulated datasets with three state-of-the-art open-source LLMs, Mistral-7B, Gemma-7B, and Llama-3-8B, demonstrate that our method can achieve superior performance compared to various strong baselines. Besides, we analyze to illustrate that our WKM can effectively alleviate the blind trial-and-error and hallucinatory action issues, providing strong support for the agent's understanding of the world. Other interesting findings include: 1) our instance-level task knowledge can generalize better to unseen tasks, 2) weak WKM can guide strong agent model planning, and 3) unified WKM training has promising potential for further development. The code is available at https://github.com/zjunlp/WKM.

arXiv:2501.01463v1 Announce Type: new Abstract: Goal Recognition aims to infer an agent's goal from a sequence of observations. Existing approaches often rely on manually engineered domains and discrete representations. Deep Recognition using Actor-Critic Optimization (DRACO) is a novel approach based on deep reinforcement learning that overcomes these limitations by providing two key contributions. First, it is the first goal recognition algorithm that learns a set of policy networks from unstructured data and uses them for inference. Second, DRACO introduces new metrics for assessing goal hypotheses through continuous policy representations. DRACO achieves state-of-the-art performance for goal recognition in discrete settings while not using the structured inputs used by existing approaches. Moreover, it outperforms these approaches in more challenging, continuous settings at substantially reduced costs in both computing and memory. Together, these results showcase the robustness of the new algorithm, bridging traditional goal recognition and deep reinforcement learning.

arXiv:2306.10749v2 Announce Type: replace Abstract: This paper studies the bearing-based simultaneous localization and affine formation tracking (SLAFT) control problem for fixed-wing unmanned aerial vehicles (UAVs). In the considered problem, only a small set of UAVs, named leaders, can obtain their global positions, and the other UAVs only have access to bearing information relative to their neighbors. To address the problem, we propose novel schemes by integrating the distributed bearing-based self-localization algorithm and the observer-based affine formation tracking controller. The designed localization algorithm estimates the global position by using inter-UAV bearing measurements, and the observer-based controller tracks the desired formation with the estimated positions. A key distinction of our approach is extending the SLAFT control scheme to the bearing-based coordination of nonholonomic UAV systems, where the desired inter-UAV bearings can be time-varying, instead of constant ones assumed in most of the existing results. Two control schemes with different convergence rates are designed to meet desired task requirements under different conditions. The stability analysis of the two schemes for SLAFT control is proved, and numerous simulations are carried out to validate the theoretical analysis.

arXiv:2501.01531v1 Announce Type: new Abstract: In this article we propose a game-theoretic approach to the multi-robot task allocation problem using the framework of global games. Each task is associated with a global signal, a real-valued number that captures the task execution progress and/or urgency. We propose a linear objective function for each robot in the system, which, for each task, increases with global signal and decreases with the number assigned robots. We provide conditions on the objective function hyperparameters to induce a mixed Nash equilibrium, i.e., solutions where all robots are not assigned to a single task. The resulting algorithm only requires the inversion of a matrix to determine a probability distribution over the robot assignments. We demonstrate the performance of our algorithm in simulation and provide direction for applications and future work.

arXiv:2501.00906v1 Announce Type: new Abstract: This paper presents the development and evaluation of a Large Language Model (LLM), also known as foundation models, based multi-agent system framework for complex event processing (CEP) with a focus on video query processing use cases. The primary goal is to create a proof-of-concept (POC) that integrates state-of-the-art LLM orchestration frameworks with publish/subscribe (pub/sub) tools to address the integration of LLMs with current CEP systems. Utilizing the Autogen framework in conjunction with Kafka message brokers, the system demonstrates an autonomous CEP pipeline capable of handling complex workflows. Extensive experiments evaluate the system's performance across varying configurations, complexities, and video resolutions, revealing the trade-offs between functionality and latency. The results show that while higher agent count and video complexities increase latency, the system maintains high consistency in narrative coherence. This research builds upon and contributes to, existing novel approaches to distributed AI systems, offering detailed insights into integrating such systems into existing infrastructures.