An agent trained within a closed system can master any desired capability, as long as the following three conditions hold: (a) it receives sufficiently informative and aligned feedback, (b) its coverage of experience/data is broad enough, and (c) it has sufficient capacity and resource. In this position paper, we justify these conditions, and consider what limitations arise from (a) and (b) in closed systems, when assuming that (c) is not a bottleneck. Considering the special case of agents with matching input and output spaces (namely, language), we argue that such pure recursive self-improvement, dubbed "Socratic learning", can boost performance vastly beyond what is present in its initial data or knowledge, and is only limited by time, as well as gradual misalignment concerns. Furthermore, we propose a constructive framework to implement it, based on the notion of language games.

In this paper, we present a novel trajectory prediction model for autonomous driving, combining a Characterized Diffusion Module and a Spatial-Temporal Interaction Network to address the challenges posed by dynamic and heterogeneous traffic environments. Our model enhances the accuracy and reliability of trajectory predictions by incorporating uncertainty estimation and complex agent interactions. Through extensive experimentation on public datasets such as NGSIM, HighD, and MoCAD, our model significantly outperforms existing state-of-the-art methods. We demonstrate its ability to capture the underlying spatial-temporal dynamics of traffic scenarios and improve prediction precision, especially in complex environments. The proposed model showcases strong potential for application in real-world autonomous driving systems.

With the growing popularity of generative AI for images, video, and music, we witnessed models rapidly improve in quality and performance. However, not much attention is paid towards enabling AI's ability to "be creative". In this study, we implemented and simulated the systems model of creativity (proposed by Csikszentmihalyi) using virtual agents utilizing large language models (LLMs) and text prompts. For comparison, the simulations were conducted with the "virtual artists" being: 1)isolated and 2)placed in a multi-agent system. Both scenarios were compared by analyzing the variations and overall "creativity" in the generated artifacts (measured via a user study and LLM). Our results suggest that the generative agents may perform better in the framework of the systems model of creativity.

In the realm of emerging real-time networked applications like cyber-physical systems (CPS), the Age of Information (AoI) has merged as a pivotal metric for evaluating the timeliness. To meet the high computational demands, such as those in intelligent manufacturing within CPS, mobile edge computing (MEC) presents a promising solution for optimizing computing and reducing AoI. In this work, we study the timeliness of computational-intensive updates and explores jointly optimize the task updating and offloading policies to minimize AoI. Specifically, we consider edge load dynamics and formulate a task scheduling problem to minimize the expected time-average AoI. The fractional objective introduced by AoI and the semi-Markov game nature of the problem render this challenge particularly difficult, with existing approaches not directly applicable. To this end, we present a comprehensive framework to fractional reinforcement learning (RL). We first introduce a fractional single-agent RL framework and prove its linear convergence. We then extend this to a fractional multi-agent RL framework with a convergence analysis. To tackle the challenge of asynchronous control in semi-Markov game, we further design an asynchronous model-free fractional multi-agent RL algorithm, where each device makes scheduling decisions with the hybrid action space without knowing the system dynamics and decisions of other devices. Experimental results show that our proposed algorithms reduce the average AoI by up to 52.6% compared with the best baseline algorithm in our experiments.

Abstract--Large Language Models (LLMs) still face challenges when dealing with complex reasoning tasks, often resulting in hallucinations, which limit the practical application of LLMs. To alleviate this issue, this paper proposes a new method that integrates different LLMs to expand the knowledge boundary, reduce dependence on a single model, and promote in-depth debate among agents. The main contributions include: 1) Introducing third-party LLMs to adjust the attention weights of agents through uncertainty estimation and confidence analysis, optimizing consensus formation in multi-agent systems; 2) Experiments on arithmetic datasets have validated the effectiveness of the method, surpassing traditional multi-agent baselines. This research provides a new perspective for large models to alleviate hallucination phenomena when dealing with complex tasks. In these systems, multiple agents articulate their arguments, while a neutral moderator oversees the debate process to facilitate the attainment of a final resolution Therefore, this paper raises a question: Can a third-party [2].By employing multiple instances of language models and model be introduced to complete tasks through the collaboration engaging in several rounds of proposal and debate regarding of multiple Large Language Models?

This paper studies the multi-robot reliable navigation problem in uncertain topological networks, which aims at maximizing the robot team's on-time arrival probabilities in the face of road network uncertainties. The uncertainty in these networks stems from the unknown edge traversability, which is only revealed to the robot upon its arrival at the edge's starting node. Existing approaches often struggle to adapt to real-time network topology changes, making them unsuitable for varying topological environments. To address the challenge, we reformulate the problem into a Partially Observable Markov Decision Process (POMDP) framework and introduce the Dynamic Adaptive Graph Embedding method to capture the evolving nature of the navigation task. We further enhance each robot's policy learning process by integrating deep reinforcement learning with Graph Attention Networks (GATs), leveraging self-attention to focus on critical graph features. The proposed approach, namely Multi-Agent Routing in Variable Environments with Learning (MARVEL) employs the generalized policy gradient algorithm to optimize the robots' real-time decision-making process iteratively. We compare the performance of MARVEL with state-of-the-art reliable navigation algorithms as well as Canadian traveller problem solutions in a range of canonical transportation networks, demonstrating improved adaptability and performance in uncertain topological networks. Additionally, real-world experiments with two robots navigating within a self-constructed indoor environment with uncertain topological structures demonstrate MARVEL's practicality.

Contemporary embodied agents, such as Voyager in Minecraft, have demonstrated promising capabilities in open-ended individual learning. However, when powered with open large language models (LLMs), these agents often struggle with rudimentary tasks, even when fine-tuned on domain-specific knowledge. These advancements enable agents to reason about their and others' mental states, empirically addressing two prevalent failure modes: false beliefs and faulty task executions. The development of generally capable agents marks a significant shift in advancing artificial intelligence, transitioning from assimilating data to generating novel knowledge through embodied interactions with open-ended environments (Kolve et al., 2017; Savva et al., 2019; Puig et al., 2018; Shridhar et al., 2020). Classical approaches leveraging reinforcement learning (Schulman et al., 2017; Hafner et al., 2023) and imitation learning (Zare et al., 2024) often struggle with generalization and exploration, as agents tend to converge on repetitive behaviors in static environments (Cobbe et al., 2019). To address these limitations, researchers have sought to emulate human-like lifelong learning capabilities, developing systems that can continuously acquire, update, and transfer knowledge over extended periods (Parisi et al., 2019; Wang et al., 2023b).The advent of large language models (LLMs) has accelerated this pursuit, enabling the development of agents such as Voyager (Wang et al., 2023a) that can apply internet-scale knowledge to continuously explore, plan, and acquire new skills in partially observable, open-ended environments such as Minecraft. Despite their promise, we argue that state-of-the-art lifelong learning agents like Voyager face a crucial limitation: they learn in isolation, neglecting a fundamental aspect of human intelligence--the social context. So central is the social context to our existence, that the Social Intelligence Hypothesis posits that our cognitive capabilities evolved primarily to navigate the complexities of social life (Humphrey, 1976; Dunbar, 1998). This isolated learning becomes particularly problematic when coupled with these agents' reliance on closed LLM) like GPT-4. Wang et al. (2023a) note that "VOYAGER requires Hey! I need help with Sure!

Efficient traffic control (TSC) is essential for urban mobility, but traditional systems struggle to handle the complexity of real-world traffic. Multi-agent Reinforcement Learning (MARL) offers adaptive solutions, but online MARL requires extensive interactions with the environment, making it costly and impractical. Offline MARL mitigates these challenges by using historical traffic data for training but faces significant difficulties with heterogeneous behavior policies in real-world datasets, where mixed-quality data complicates learning. We introduce OffLight, a novel offline MARL framework designed to handle heterogeneous behavior policies in TSC datasets. To improve learning efficiency, OffLight incorporates Importance Sampling (IS) to correct for distributional shifts and Return-Based Prioritized Sampling (RBPS) to focus on high-quality experiences. OffLight utilizes a Gaussian Mixture Variational Graph Autoencoder (GMM-VGAE) to capture the diverse distribution of behavior policies from local observations. Extensive experiments across real-world urban traffic scenarios show that OffLight outperforms existing offline RL methods, achieving up to a 7.8% reduction in average travel time and 11.2% decrease in queue length. Ablation studies confirm the effectiveness of OffLight's components in handling heterogeneous data and improving policy performance. These results highlight OffLight's scalability and potential to improve urban traffic management without the risks of online learning.

Multi-Agent Reinforcement Learning (MARL) methods have shown promise in enabling agents to learn a shared communication protocol from scratch and accomplish challenging team tasks. However, the learned language is usually not interpretable to humans or other agents not co-trained together, limiting its applicability in ad-hoc teamwork scenarios. In this work, we propose a novel computational pipeline that aligns the communication space between MARL agents with an embedding space of human natural language by grounding agent communications on synthetic data generated by embodied Large Language Models (LLMs) in interactive teamwork scenarios. Our results demonstrate that introducing language grounding not only maintains task performance but also accelerates the emergence of communication. Furthermore, the learned communication protocols exhibit zero-shot generalization capabilities in ad-hoc teamwork scenarios with unseen teammates and novel task states. This work presents a significant step toward enabling effective communication and collaboration between artificial agents and humans in real-world teamwork settings.

In this paper, we address the shape formation problem for massive robot swarms in environments where external localization systems are unavailable. Achieving this task effectively with solely onboard measurements is still scarcely explored and faces some practical challenges. To solve this challenging problem, we propose the following novel results. Firstly, to estimate the relative positions among neighboring robots, a concurrent-learning based estimator is proposed. It relaxes the persistent excitation condition required in the classical ones such as least-square estimator. Secondly, we introduce a finite-time agreement protocol to determine the shape location. This is achieved by estimating the relative position between each robot and a randomly assigned seed robot. The initial position of the seed one marks the shape location. Thirdly, based on the theoretical results of the relative localization, a novel behavior-based control strategy is devised. This strategy not only enables adaptive shape formation of large group of robots but also enhances the observability of inter-robot relative localization. Numerical simulation results are provided to verify the performance of our proposed strategy compared to the state-of-the-art ones. Additionally, outdoor experiments on real robots further demonstrate the practical effectiveness and robustness of our methods.