Driven by curiosity, humans have continually sought to explore and understand the world around them, leading to the invention of various tools to satiate this inquisitiveness. Despite not having the capacity to process and memorize vast amounts of information in their brains, humans excel in critical thinking, planning, reflection, and harnessing available tools to interact with and interpret the world, enabling them to find answers efficiently. The recent advancements in large language models (LLMs) suggest that machines might also possess the aforementioned human-like capabilities, allowing them to exhibit powerful abilities even with a constrained parameter count. In this paper, we introduce KwaiAgents, a generalized information-seeking agent system based on LLMs. Within KwaiAgents, we propose an agent system that employs LLMs as its cognitive core, which is capable of understanding a user's query, behavior guidelines, and referencing external documents. The agent can also update and retrieve information from its internal memory, plan and execute actions using a time-aware search-browse toolkit, and ultimately provide a comprehensive response. We further investigate the system's performance when powered by LLMs less advanced than GPT-4, and introduce the Meta-Agent Tuning (MAT) framework, designed to ensure even an open-sourced 7B or 13B model performs well among many agent systems. We exploit both benchmark and human evaluations to systematically validate these capabilities. Extensive experiments show the superiority of our agent system compared to other autonomous agents and highlight the enhanced generalized agent-abilities of our fine-tuned LLMs.

Collaborative logistics has been widely recognised as an effective avenue to reduce carbon emissions by enhanced truck utilisation and reduced travel distance. However, stakeholders' participation in collaborations is hindered by information-sharing barriers and the absence of integrated systems. We, thus, in this paper addresses these barriers by investigating an integrated platform that foster collaboration through the integration of agents with digital twins. Specifically, we employ a multi-agent system approach to integrate stakeholders and physical mobile assets in collaborative logistics, representing them as agents. We introduce a loosely-coupled system architecture that facilitates the connection between physical and digital systems, enabling the integration of agents with digital twins. Using this architecture, we implement the platform (or testbed). The resulting testbed, comprising a physical environment and a digital replica, is a digital twin that integrates distributed entities involved in collaborative logistics. The effectiveness of the testbed is demonstrated through a carrier collaboration scenario. This paper is among the earliest few efforts to investigate the integration of agents and digital twin concepts and goes beyond the conceptual discussion of existing studies to the technical implementation of such integration. Transportation is the largest contributor to greenhouse gas (GHG) emissions [1]. Among all transportation modes, trucks are the second-largest source of emissions after cars and taxis. However, they are currently utilised inefficiently, operating at around 60% of their weight capacity, and approximately 30% of the distance they travel carries no freight [2]. Collaborative logistics has been widely recognised as an effective pathway to enhance truck utilisation [3] [4] [5]. This approach involves carriers collaborating through coalition to collectively fulfil delivery requests, achieving reduced total cost and travel distance through economies of scale. Two key barriers, among others [5], contribute to this challenge: 1) Lack of Trusted Platforms: Concerns business secrecy may deter carriers from sharing data with centralised platforms, despite the environmental and economic benefits. These barriers hinder stakeholders' participation in collaboration.

In continual learning (CL), an AI agent (e.g., autonomous vehicles or robotics) learns from non-stationary data streams under dynamic environments. For the practical deployment of such applications, it is important to guarantee robustness to unseen environments while maintaining past experiences. In this paper, a novel CL framework is proposed to achieve robust generalization to dynamic environments while retaining past knowledge. The considered CL agent uses a capacity-limited memory to save previously observed environmental information to mitigate forgetting issues. Then, data points are sampled from the memory to estimate the distribution of risks over environmental change so as to obtain predictors that are robust with unseen changes. The generalization and memorization performance of the proposed framework are theoretically analyzed. This analysis showcases the tradeoff between memorization and generalization with the memory size. Experiments show that the proposed algorithm outperforms memory-based CL baselines across all environments while significantly improving the generalization performance on unseen target environments.

In this paper, we assess the state of the art in pedestrian trajectory prediction within the context of generating single trajectories, a critical aspect aligning with the requirements in autonomous systems. The evaluation is conducted on the widely-used ETH/UCY dataset where the Average Displacement Error (ADE) and the Final Displacement Error (FDE) are reported. Alongside this, we perform an ablation study to investigate the impact of the observed motion history on prediction performance. To evaluate the scalability of each approach when confronted with varying amounts of agents, the inference time of each model is measured. Following a quantitative analysis, the resulting predictions are compared in a qualitative manner, giving insight into the strengths and weaknesses of current approaches. The results demonstrate that although a constant velocity model (CVM) provides a good approximation of the overall dynamics in the majority of cases, additional features need to be incorporated to reflect common pedestrian behavior observed. Therefore, this study presents a data-driven analysis with the intent to guide the future development of pedestrian trajectory prediction algorithms.

Decision making and planning have long relied heavily on AI-driven forecasts. The government and the general public are working to minimize the risks while maximizing benefits in the face of potential future public health uncertainties. This study used an improved method of forecasting utilizing the Random Descending Velocity Inertia Weight (RDV IW) technique to improve the convergence of Particle Swarm Optimization (PSO) and the accuracy of Artificial Neural Network (ANN). The IW technique, inspired by the motions of a golf ball, modified the particles' velocities as they approached the solution point to a parabolically descending structure. Simulation results revealed that the proposed forecasting model with [0.4, 0.9] combination of alpha and alpha_dump exhibits a 6.36% improvement in position error and 11.75% improvement in computational time compared to the old model, thus, improving its convergence. It reached the optimum level at minimal steps with 12.50% improvement as against the old model since it provides better velocity averages when speed stabilization occurs at the 24th iteration. Meanwhile, the computed p-values for NRMSE (0.04889174), MAE (0.02829063), MAPE (0.02226053), WAPE (0.01701545), and R2 (0.00000021) of the proposed algorithm are less than the set 0.05 level of significance, thus the values indicated a significant result in terms of accuracy performance. Applying the modified ANN-PSO using RDV IW technique greatly improved the new HIV/AIDS forecasting model compared with the two models.

This paper develops a graph reinforcement learning approach to online planning of the schedule and destinations of electric aircraft that comprise an urban air mobility (UAM) fleet operating across multiple vertiports. This fleet scheduling problem is formulated to consider time-varying demand, constraints related to vertiport capacity, aircraft capacity and airspace safety guidelines, uncertainties related to take-off delay, weather-induced route closures, and unanticipated aircraft downtime. Collectively, such a formulation presents greater complexity, and potentially increased realism, than in existing UAM fleet planning implementations. To address these complexities, a new policy architecture is constructed, primary components of which include: graph capsule conv-nets for encoding vertiport and aircraft-fleet states both abstracted as graphs; transformer layers encoding time series information on demand and passenger fare; and a Multi-head Attention-based decoder that uses the encoded information to compute the probability of selecting each available destination for an aircraft. Trained with Proximal Policy Optimization, this policy architecture shows significantly better performance in terms of daily averaged profits on unseen test scenarios involving 8 vertiports and 40 aircraft, when compared to a random baseline and genetic algorithm-derived optimal solutions, while being nearly 1000 times faster in execution than the latter.

We present a novel framework for open-set Simultaneous Localization and Mapping (SLAM) in unstructured environments that uses segmentation to create a map of objects and geometric relationships between objects for localization. Our system consists of 1) a front-end mapping pipeline using a zero-shot segmentation model to extract object masks from images and track them across frames to generate an object-based map and 2) a frame alignment pipeline that uses the geometric consistency of objects to efficiently localize within maps taken in a variety of conditions. This approach is shown to be more robust to changes in lighting and appearance than traditional feature-based SLAM systems or global descriptor methods. This is established by evaluating SOS-SLAM on the Batvik seasonal dataset which includes drone flights collected over a coastal plot of southern Finland during different seasons and lighting conditions. Across flights during varying environmental conditions, our approach achieves higher recall than benchmark methods with precision of 1.0. SOS-SLAM localizes within a reference map up to 14x faster than other feature based approaches and has a map size less than 0.4% the size of the most compact other maps. When considering localization performance from varying viewpoints, our approach outperforms all benchmarks from the same viewpoint and most benchmarks from different viewpoints. SOS-SLAM is a promising new approach for SLAM in unstructured environments that is robust to changes in lighting and appearance and is more computationally efficient than other approaches. We release our code and datasets: https://acl.mit.edu/SOS-SLAM/.

Multi-agent multi-target tracking has a wide range of applications, including wildlife patrolling, security surveillance or environment monitoring. Such algorithms often make restrictive assumptions: the number of targets and/or their initial locations may be assumed known, or agents may be pre-assigned to monitor disjoint partitions of the environment, reducing the burden of exploration. This also limits applicability when there are fewer agents than targets, since agents are unable to continuously follow the targets in their fields of view. Multi-agent tracking algorithms additionally assume inter-agent synchronization of observations, or the presence of a central controller to coordinate joint actions. Instead, we focus on the setting of decentralized multi-agent, multi-target, simultaneous active search-and-tracking with asynchronous inter-agent communication. Our proposed algorithm DecSTER uses a sequential monte carlo implementation of the probability hypothesis density filter for posterior inference combined with Thompson sampling for decentralized multi-agent decision making. We compare different action selection policies, focusing on scenarios where targets outnumber agents. In simulation, we demonstrate that DecSTER is robust to unreliable inter-agent communication and outperforms information-greedy baselines in terms of the Optimal Sub-Pattern Assignment (OSPA) metric for different numbers of targets and varying teamsizes.

The conservation of hydrological resources involves continuously monitoring their contamination. A multi-agent system composed of autonomous surface vehicles is proposed in this paper to efficiently monitor the water quality. To achieve a safe control of the fleet, the fleet policy should be able to act based on measurements and to the the fleet state. It is proposed to use Local Gaussian Processes and Deep Reinforcement Learning to jointly obtain effective monitoring policies. Local Gaussian processes, unlike classical global Gaussian processes, can accurately model the information in a dissimilar spatial correlation which captures more accurately the water quality information. A Deep convolutional policy is proposed, that bases the decisions on the observation on the mean and variance of this model, by means of an information gain reward. Using a Double Deep Q-Learning algorithm, agents are trained to minimize the estimation error in a safe manner thanks to a Consensus-based heuristic. Simulation results indicate an improvement of up to 24% in terms of the mean absolute error with the proposed models. Also, training results with 1-3 agents indicate that our proposed approach returns 20% and 24% smaller average estimation errors for, respectively, monitoring water quality variables and monitoring algae blooms, as compared to state-of-the-art approaches

Companies, organizations, and governments increasingly exploit Language Models' (LM) remarkable capability to display agent-like behavior. As LMs are adopted to perform tasks with growing autonomy, there exists an urgent need for reliable and scalable evaluation benchmarks. Current, predominantly static LM benchmarks are ill-suited to evaluate such dynamic applications. Thus, we propose jointly evaluating LM performance and alignment through the lenses of negotiation games. We argue that this common task better reflects real-world deployment conditions while offering insights into LMs' decision-making processes. Crucially, negotiation games allow us to study multi-turn, and cross-model interactions, modulate complexity, and side-step accidental data leakage in evaluation. We report results for six publicly accessible LMs from several major providers on a variety of negotiation games, evaluating both self-play and cross-play performance. Noteworthy findings include: (i) open-source models are currently unable to complete these tasks; (ii) cooperative bargaining games prove challenging; and (iii) the most powerful models do not always "win".