Effective collaboration in multi-agent systems requires communicating goals and intentions between agents. Current agent frameworks often suffer from dependencies on single-agent execution and lack robust inter-module communication, frequently leading to suboptimal multi-agent reinforcement learning (MARL) policies and inadequate task coordination. To address these challenges, we present a framework for training large language models (LLMs) as collaborative agents to enable coordinated behaviors in cooperative MARL. Each agent maintains a private intention consisting of its current goal and associated sub-tasks. Agents broadcast their intentions periodically, allowing other agents to infer coordination tasks. A propagation network transforms broadcast intentions into teammate-specific communication messages, sharing relevant goals with designated teammates. The architecture of our framework is structured into planning, grounding, and execution modules. During execution, multiple agents interact in a downstream environment and communicate intentions to enable coordinated behaviors. The grounding module dynamically adapts comprehension strategies based on emerging coordination patterns, while feedback from execution agents influnces the planning module, enabling the dynamic re-planning of sub-tasks. Results in collaborative environment simulation demonstrate intention propagation reduces miscoordination errors by aligning sub-task dependencies between agents. Agents learn when to communicate intentions and which teammates require task details, resulting in emergent coordinated behaviors. This demonstrates the efficacy of intention sharing for cooperative multi-agent RL based on LLMs.

The primary objective of Multi-Agent Pathfinding (MAPF) is to plan efficient and conflict-free paths for all agents. Traditional multi-agent path planning algorithms struggle to achieve efficient distributed path planning for multiple agents. In contrast, Multi-Agent Reinforcement Learning (MARL) has been demonstrated as an effective approach to achieve this objective. By modeling the MAPF problem as a MARL problem, agents can achieve efficient path planning and collision avoidance through distributed strategies under partial observation. However, MARL strategies often lack cooperation among agents due to the absence of global information, which subsequently leads to reduced MAPF efficiency. To address this challenge, this letter introduces a unique reward shaping technique based on Independent Q-Learning (IQL). The aim of this method is to evaluate the influence of one agent on its neighbors and integrate such an interaction into the reward function, leading to active cooperation among agents. This reward shaping method facilitates cooperation among agents while operating in a distributed manner. The proposed approach has been evaluated through experiments across various scenarios with different scales and agent counts. The results are compared with those from other state-of-the-art (SOTA) planners. The evidence suggests that the approach proposed in this letter parallels other planners in numerous aspects, and outperforms them in scenarios featuring a large number of agents.

Software agents have emerged as promising tools for addressing complex software engineering tasks. Existing works, on the other hand, frequently oversimplify software development workflows, despite the fact that such workflows are typically more complex in the real world. Thus, we propose AgileCoder, a multi agent system that integrates Agile Methodology (AM) into the framework. This system assigns specific AM roles - such as Product Manager, Developer, and Tester to different agents, who then collaboratively develop software based on user inputs. AgileCoder enhances development efficiency by organizing work into sprints, focusing on incrementally developing software through sprints. Additionally, we introduce Dynamic Code Graph Generator, a module that creates a Code Dependency Graph dynamically as updates are made to the codebase. This allows agents to better comprehend the codebase, leading to more precise code generation and modifications throughout the software development process. AgileCoder surpasses existing benchmarks, like ChatDev and MetaGPT, establishing a new standard and showcasing the capabilities of multi agent systems in advanced software engineering environments.

Multi-Agent Path Finding (MAPF) aims to arrange collision-free goal-reaching paths for a group of agents. Anytime MAPF solvers based on large neighborhood search (LNS) have gained prominence recently due to their flexibility and scalability. Neighborhood selection strategy is crucial to the success of MAPF-LNS and a flurry of methods have been proposed. However, several pitfalls exist and hinder a comprehensive evaluation of these new methods, which mainly include: 1) Lower than actual or incorrect baseline performance; 2) Lack of a unified evaluation setting and criterion; 3) Lack of a codebase or executable model for supervised learning methods. To overcome these challenges, we conduct a fair comparison across prominent methods on the same benchmark and hyperparameter search settings. Additionally, we propose a simple neighborhood selection strategy which marks a clear advancement in terms of runtime efficiency in large maps with large number of agents. Our benchmarking evaluation promotes new challenges for existing learning based methods and presents opportunities for future research when machine learning is integrated with MAPF-LNS.

Despite the recent successes of multi-agent reinforcement learning (MARL) algorithms, efficiently adapting to co-players in mixed-motive environments remains a significant challenge. One feasible approach is to hierarchically model co-players' behavior based on inferring their characteristics. However, these methods often encounter difficulties in efficient reasoning and utilization of inferred information. To address these issues, we propose Hierarchical Opponent modeling and Planning (HOP), a novel multi-agent decision-making algorithm that enables few-shot adaptation to unseen policies in mixed-motive environments. HOP is hierarchically composed of two modules: an opponent modeling module that infers others' goals and learns corresponding goal-conditioned policies, and a planning module that employs Monte Carlo Tree Search (MCTS) to identify the best response. Our approach improves efficiency by updating beliefs about others' goals both across and within episodes and by using information from the opponent modeling module to guide planning. Experimental results demonstrate that in mixed-motive environments, HOP exhibits superior few-shot adaptation capabilities when interacting with various unseen agents, and excels in self-play scenarios. Furthermore, the emergence of social intelligence during our experiments underscores the potential of our approach in complex multi-agent environments.

This paper studies the problem of multi-agent trajectory prediction in crowded unknown environments. A novel energy function optimization-based framework is proposed to generate prediction trajectories. Firstly, a new energy function is designed for easier optimization. Secondly, an online optimization pipeline for calculating parameters and agents' velocities is developed. In this pipeline, we first design an efficient group division method based on Frechet distance to classify agents online. Then the strategy on decoupling the optimization of velocities and critical parameters in the energy function is developed, where the the slap swarm algorithm and gradient descent algorithms are integrated to solve the optimization problems more efficiently. Thirdly, we propose a similarity-based resample evaluation algorithm to predict agents' optimal goals, defined as the target-moving headings of agents, which effectively extracts hidden information in observed states and avoids learning agents' destinations via the training dataset in advance. Experiments and comparison studies verify the advantages of the proposed method in terms of prediction accuracy and speed.

The rise of powerful large language models (LLMs) has spurred a new trend in building LLM-based autonomous agents for solving complex tasks, especially multi-agent systems. Despite the remarkable progress, we notice that existing works are heavily dependent on human-designed frameworks, which greatly limits the functional scope and scalability of agent systems. How to automatically extend the specialized agent to multi-agent systems to improve task-solving capability still remains a significant challenge. In this paper, we introduce EvoAgent, a generic method to automatically extend expert agents to multi-agent systems via the evolutionary algorithm, thereby improving the effectiveness of LLM-based agents in solving tasks. Specifically, we consider the existing agent frameworks as the initial individual and then apply a series of evolutionary operators (e.g., mutation, crossover, selection, etc.) to generate multiple agents with diverse agent settings. EvoAgent can be generalized to any LLM-based agent framework, and can automatically extend the existing agent framework to multi-agent systems without any extra human designs. Experimental results across various tasks have shown that EvoAgent can automatically generate multiple expert agents and significantly enhance the task-solving capabilities of LLM-based agents.

Decentralized planning is a key element of cooperative multi-agent systems for information gathering tasks. However, despite the high frequency of agent failures in realistic large deployment scenarios, current approaches perform poorly in the presence of failures, by not converging at all, and/or by making very inefficient use of resources (e.g. energy). In this work, we propose Attritable MCTS (A-MCTS), a decentralized MCTS algorithm capable of timely and efficient adaptation to changes in the set of active agents. It is based on the use of a global reward function for the estimation of each agent's local contribution, and regret matching for coordination. We evaluate its effectiveness in realistic data-harvesting problems under different scenarios. We show both theoretically and experimentally that A-MCTS enables efficient adaptation even under high failure rates. Results suggest that, in the presence of frequent failures, our solution improves substantially over the best existing approaches in terms of global utility and scalability.

In multi-agent reinforcement learning (MARL), the Centralized Training with Decentralized Execution (CTDE) framework is pivotal but struggles due to a gap: global state guidance in training versus reliance on local observations in execution, lacking global signals. Inspired by human societal consensus mechanisms, we introduce the Hierarchical Consensus-based Multi-Agent Reinforcement Learning (HC-MARL) framework to address this limitation. HC-MARL employs contrastive learning to foster a global consensus among agents, enabling cooperative behavior without direct communication. This approach enables agents to form a global consensus from local observations, using it as an additional piece of information to guide collaborative actions during execution. To cater to the dynamic requirements of various tasks, consensus is divided into multiple layers, encompassing both short-term and long-term considerations. Short-term observations prompt the creation of an immediate, low-layer consensus, while long-term observations contribute to the formation of a strategic, high-layer consensus. This process is further refined through an adaptive attention mechanism that dynamically adjusts the influence of each consensus layer. This mechanism optimizes the balance between immediate reactions and strategic planning, tailoring it to the specific demands of the task at hand. Extensive experiments and real-world applications in multi-robot systems showcase our framework's superior performance, marking significant advancements over baselines.

In this work, we introduce the Resilient Projected Push-Pull (RP3) algorithm designed for distributed optimization in multi-agent cyber-physical systems with directed communication graphs and the presence of malicious agents. Our algorithm leverages stochastic inter-agent trust values and gradient tracking to achieve geometric convergence rates in expectation even in adversarial environments. We introduce growing constraint sets to limit the impact of the malicious agents without compromising the geometric convergence rate of the algorithm. We prove that RP3 converges to the nominal optimal solution almost surely and in the $r$-th mean for any $r\geq 1$, provided the step sizes are sufficiently small and the constraint sets are appropriately chosen. We validate our approach with numerical studies on average consensus and multi-robot target tracking problems, demonstrating that RP3 effectively mitigates the impact of malicious agents and achieves the desired geometric convergence.