Through the collaboration of multiple agents possessing diverse expertise and tools, multi-agent systems achieve impressive progress in solving real-world problems. Given the user queries, the meta-agents, serving as the brain within these systems, are required to decompose the queries into multiple sub-tasks that can be allocated to suitable agents capable of solving them, so-called agent-oriented planning. In this study, we identify three critical design principles of agent-oriented planning, including solvability, completeness, and non-redundancy, to ensure that each sub-task is effectively resolved, leading to satisfactory responses to the original queries. These principles further inspire us to propose a novel framework for agent-oriented planning in multi-agent systems, leveraging a fast task decomposition and allocation process followed by an effective and efficient evaluation via a reward model. During the planning process, the meta-agent is also responsible for evaluating the performance of the expert agents, making timely adjustments to the sub-tasks and scheduling as necessary. Besides, we integrate a feedback loop into the proposed framework to further enhance the effectiveness and robustness of such a problem-solving process. Extensive experiments demonstrate the advancement of the proposed framework in solving real-world problems compared to both single-agent systems and existing planning strategies for multi-agent systems.

Vehicle-to-everything (V2X) communication technology is revolutionizing transportation by enabling interactions between vehicles, devices, and infrastructures. This connectivity enhances road safety, transportation efficiency, and driver assistance systems. V2X benefits from Machine Learning, enabling real-time data analysis, better decision-making, and improved traffic predictions, making transportation safer and more efficient. In this paper, we study the problem of joint channel selection, where vehicles with different technologies choose one or more Access Points (APs) to transmit messages in a network. In this problem, vehicles must learn a strategy for channel selection, based on observations that incorporate vehicles' information (position and speed), network and communication data (Signal-to-Interference-plus-Noise Ratio from past communications), and environmental data (road type). We propose an approach based on Federated Deep Reinforcement Learning (FedDRL), which enables each vehicle to benefit from other vehicles' experiences. Specifically, we apply the federated Proximal Policy Optimization (FedPPO) algorithm to this task. We show that this method improves communication reliability while minimizing transmission costs and channel switches. The efficiency of the proposed solution is assessed via realistic simulations, highlighting the potential of FedDRL to advance V2X technology.

SLAM is an important capability for many autonomous systems, and modern LiDAR-based methods offer promising performance. However, for long duration missions, existing works that either operate directly the full pointclouds or on extracted features face key tradeoffs in accuracy and computational efficiency (e.g., memory consumption). To address these issues, this paper presents DFLIOM with several key innovations. Unlike previous methods that rely on handcrafted heuristics and hand-tuned parameters for feature extraction, we propose a learning-based approach that select points relevant to LiDAR SLAM pointcloud registration. Furthermore, we extend our prior work DLIOM with the learned feature extractor and observe our method enables similar or even better localization performance using only about 20\% of the points in the dense point clouds. We demonstrate that DFLIOM performs well on multiple public benchmarks, achieving a 2.4\% decrease in localization error and 57.5\% decrease in memory usage compared to state-of-the-art methods (DLIOM). Although extracting features with the proposed network requires extra time, it is offset by the faster processing time downstream, thus maintaining real-time performance using 20Hz LiDAR on our hardware setup. The effectiveness of our learning-based feature extraction module is further demonstrated through comparison with several handcrafted feature extractors.

Envy-freeness has become the cornerstone of fair division research. In settings where each individual is allocated a disjoint share of collective resources, it is a compelling fairness axiom which demands that no individual strictly prefer the allocation of another individual to their own. Unfortunately, in many real-life collective decision-making problems, the goal is to choose a (common) public outcome that is equally applicable to all individuals, and the notion of envy becomes vacuous. Consequently, this literature has avoided studying fairness criteria that focus on individuals feeling a sense of jealousy or resentment towards other individuals (rather than towards the system), missing out on a key aspect of fairness. In this work, we propose a novel fairness criterion, individual harm ratio, which is inspired by envy-freeness but applies to a broad range of collective decision-making settings. Theoretically, we identify minimal conditions under which this criterion and its groupwise extensions can be guaranteed, and study the computational complexity of related problems. Empirically, we conduct experiments with real data to show that our fairness criterion is powerful enough to differentiate between prominent decision-making algorithms for a range of tasks from voting and fair division to participatory budgeting and peer review.

Automated machine learning (AutoML) accelerates AI development by automating tasks in the development pipeline, such as optimal model search and hyperparameter tuning. Existing AutoML systems often require technical expertise to set up complex tools, which is in general time-consuming and requires a large amount of human effort. Therefore, recent works have started exploiting large language models (LLM) to lessen such burden and increase the usability of AutoML frameworks via a natural language interface, allowing non-expert users to build their data-driven solutions. These methods, however, are usually designed only for a particular process in the AI development pipeline and do not efficiently use the inherent capacity of the LLMs. This paper proposes AutoML-Agent, a novel multi-agent framework tailored for full-pipeline AutoML, i.e., from data retrieval to model deployment. AutoML-Agent takes user's task descriptions, facilitates collaboration between specialized LLM agents, and delivers deployment-ready models. Unlike existing work, instead of devising a single plan, we introduce a retrieval-augmented planning strategy to enhance exploration to search for more optimal plans. We also decompose each plan into sub-tasks (e.g., data preprocessing and neural network design) each of which is solved by a specialized agent we build via prompting executing in parallel, making the search process more efficient. Moreover, we propose a multi-stage verification to verify executed results and guide the code generation LLM in implementing successful solutions. Extensive experiments on seven downstream tasks using fourteen datasets show that AutoML-Agent achieves a higher success rate in automating the full AutoML process, yielding systems with good performance throughout the diverse domains.

Diffusion models have recently been successfully applied to a wide range of robotics applications for learning complex multi-modal behaviors from data. However, prior works have mostly been confined to single-robot and small-scale environments due to the high sample complexity of learning multi-robot diffusion models. In this paper, we propose a method for generating collision-free multi-robot trajectories that conform to underlying data distributions while using only single-robot data. Our algorithm, Multi-robot Multi-model planning Diffusion (MMD), does so by combining learned diffusion models with classical search-based techniques--generating data-driven motions under collision constraints. Scaling further, we show how to compose multiple diffusion models to plan in large environments where a single diffusion model fails to generalize well. We demonstrate the effectiveness of our approach in planning for dozens of robots in a variety of simulated scenarios motivated by logistics environments. Multi-robot motion planning (MRMP) is a fundamental challenge in many real-world applications where teams of robots have to work in close proximity to each other to complete their tasks. In automated warehouses, for example, hundreds of mobile robots and robotic manipulators need to coordinate with each other to transport and exchange items while avoiding collisions. Learning motions from demonstrations can oftentimes allow robots to complete tasks they couldn't otherwise, like navigating a region in a pattern frequently followed by human workers; however, it is unclear how to best incorporate demonstrations in MRMP. In fact, MRMP at its simplest form, where robots are only concerned with finding short trajectories between start and goal configurations, is already known to be computationally intractable (Hopcroft & Wilfong, 1986)--significantly harder than single-agent motion planning due to the complexity of mutual interactions between robots. Attempting to simplify the problem, various approximate formulations have been proposed in the literature. For example, a popular approach is to formulate the problem as a multi-agent path finding problem (MAPF) (Stern et al., 2019) by discretizing space and time. While the latest MAPF planners (Li et al., 2021; Okumura, 2024) can compute near-optimal plans and scale to hundreds of agents, they make strong assumptions, such as constant velocities and rectilinear movements that limit their real-world application and reduce their ability to generate complex behaviors learned from demonstrations.

Intelligent embodied agents need to quickly adapt to new scenarios by integrating long histories of experience into decision-making. For instance, a robot in an unfamiliar house initially wouldn't know the locations of objects needed for tasks and might perform inefficiently. However, as it gathers more experience, it should learn the layout of its environment and remember where objects are, allowing it to complete new tasks more efficiently. To enable such rapid adaptation to new tasks, we present ReLIC, a new approach for in-context reinforcement learning (RL) for embodied agents. With ReLIC, agents are capable of adapting to new environments using 64,000 steps of in-context experience with full attention while being trained through self-generated experience via RL. We achieve this by proposing a novel policy update scheme for on-policy RL called "partial updates" as well as a Sink-KV mechanism that enables effective utilization of a long observation history for embodied agents. Our method outperforms a variety of meta-RL baselines in adapting to unseen houses in an embodied multi-object navigation task. In addition, we find that ReLIC is capable of few-shot imitation learning despite never being trained with expert demonstrations. We also provide a comprehensive analysis of ReLIC, highlighting that the combination of large-scale RL training, the proposed partial updates scheme, and the Sink-KV are essential for effective in-context learning. The code for ReLIC and all our experiments is at github.com/aielawady/relic. A desired capability of intelligent embodied agents is to rapidly adapt to new scenarios through experience. An essential requirement for this capability is integrating a long history of experience into decision-making to enable an agent to accumulate knowledge about the new scenario that it is encountering. For example, a robot placed in an unseen house initially has no knowledge of the home layout and where to find objects. The robot should leverage its history of experiences of completing tasks in this new home to learn the home layout details, where to find objects, and how to act to complete tasks successfully. To achieve adaptation of decision-making to new tasks, prior work has leveraged a technique called in-context reinforcement learning (RL) where an agent is trained with RL to utilize past experience in an environment (Wang et al., 2016; Team et al., 2023; Duan et al., 2016; Grigsby et al., 2023; Melo, 2022). By using sequence models over a history of interactions in an environment, these methods adapt to new scenarios by conditioning policy actions on this context of interaction history without updating the policy parameters.

Recent progress in generative models has stimulated significant innovations in many fields, such as image generation and chatbots. Despite their success, these models often produce sketchy and misleading solutions for complex multi-agent decision-making problems because they miss the trial-and-error experience and reasoning as humans. To address this limitation, we explore a paradigm that integrates a language-guided simulator into the multi-agent reinforcement learning pipeline to enhance the generated answer. The simulator is a world model that separately learns dynamics and reward, where the dynamics model comprises an image tokenizer as well as a causal transformer to generate interaction transitions autoregressively, and the reward model is a bidirectional transformer learned by maximizing the likelihood of trajectories in the expert demonstrations under language guidance. Given an image of the current state and the task description, we use the world model to train the joint policy and produce the image sequence as the answer by running the converged policy on the dynamics model. The empirical results demonstrate that this framework can improve the answers for multi-agent decision-making problems by showing superior performance on the training and unseen tasks of the StarCraft Multi-Agent Challenge benchmark. In particular, it can generate consistent interaction sequences and explainable reward functions at interaction states, opening the path for training generative models of the future.

Writing compelling fiction is a multifaceted process combining elements such as crafting a plot, developing interesting characters, and using evocative language. While large language models (LLMs) show promise for story writing, they currently rely heavily on intricate prompting, which limits their use. We propose Agents' Room, a generation framework inspired by narrative theory, that decomposes narrative writing into subtasks tackled by specialized agents. To illustrate our method, we introduce Tell Me A Story, a high-quality dataset of complex writing prompts and human-written stories, and a novel evaluation framework designed specifically for assessing long narratives. We show that Agents' Room generates stories that are preferred by expert evaluators over those produced by baseline systems by leveraging collaboration and specialization to decompose the complex story writing task into tractable components. We provide extensive analysis with automated and human-based metrics of the generated output.

As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs are susceptible to societal biases due to their exposure to human-generated data. Given that LLMs are being used to gain insights into various societal aspects, it is essential to mitigate these biases. To that end, our study investigates the presence of implicit gender biases in multi-agent LLM interactions and proposes two strategies to mitigate these biases. We begin by creating a dataset of scenarios where implicit gender biases might arise, and subsequently develop a metric to assess the presence of biases. Our empirical analysis reveals that LLMs generate outputs characterized by strong implicit bias associations (>= 50\% of the time). Furthermore, these biases tend to escalate following multi-agent interactions. To mitigate them, we propose two strategies: self-reflection with in-context examples (ICE); and supervised fine-tuning. Our research demonstrates that both methods effectively mitigate implicit biases, with the ensemble of fine-tuning and self-reflection proving to be the most successful.