Artificial Intelligence (cs.AI)

Abstract: While LLMs have shown great success in understanding and generating text in traditional conversational settings, their potential for performing ill-defined complex tasks is largely under-studied. Indeed, we are yet to conduct comprehensive benchmarking studies with multiple LLMs that are exclusively focused on a complex task. However, conducting such benchmarking studies is challenging because of the large variations in LLMs' performance when different prompt types/styles are used and different degrees of detail are provided in the prompts. To address this issue, the paper proposes a general taxonomy that can be used to design prompts with specific properties in order to perform a wide range of complex tasks. This taxonomy will allow future benchmarking studies to report the specific categories of prompts used as part of the study, enabling meaningful comparisons across different studies. Also, by establishing a common standard through this taxonomy, researchers will be able to draw more accurate conclusions about LLMs' performance on a specific complex task.

Abstract: This paper show a work on better use of LLMs with SelfzCoT a self-prompt zero-shot CoT. Specifically, on the zero-shot arithmetic reasoning tasks, the accuracy of the proposed SelfzCoT is improved with GSM8K from 40.50% to 82.34%, with MultiArith from 79.3% to 94.7%, with ADDSUB from 74.70% to 94.10%, with SingleEq from 78.70% to 91.30%, with AQUA from 31.90% to 82.33%, and with SVAMP from 63.70% to 79.70%. Totally, using the first two lasting path activations to LLM and particularly, the code-level self-prompt, the SelfzCoT has a huge improvement on all six zero-shot arithmetic reasoning tasks. Additionally, our modified zero-shot CoT (MzCoT) also achieves remarkable performance in the reasoning tasks. The accuracy of the proposed MzCoT is enhanced with GSM8K from 40.50% to 76.32%, with MultiArith from 79.3% to 96.97%, with ADDSUB from 74.70% to 92.39%, with SingleEq from 78.70% to 94.60%, with AQUA from 31.90% to 79.90%, and with SVAMP from 63.70% to 81.50%. Notably, SelfzCoT has the best performance on GSM8K among all the recent zero-shot methods.

Abstract: We discuss the adequacy of tests for intelligent systems and practical problems raised by their implementation. We propose the replacement test as the ability of a system to replace successfully another system performing a task in a given context. We show how it can characterize salient aspects of human intelligence that cannot be taken into account by the Turing test. We argue that building intelligent systems passing the replacement test involves a series of technical problems that are outside the scope of current AI. We present a framework for implementing the proposed test and validating the properties of the intelligent systems. We discuss the inherent limitations of intelligent system validation and advocate new theoretical foundations for extending existing rigorous test methods. We suggest that the replacement test, based on the complementarity of skills between human and machine, can lead to a multitude of intelligence concepts reflecting the ability to combine data-based and symbolic knowledge to varying degrees.

Abstract: In automated warehouses, teams of mobile robots fulfill the packaging process by transferring inventory pods to designated workstations while navigating narrow aisles formed by tightly packed pods. This problem is typically modeled as a Multi-Agent Pickup and Delivery (MAPD) problem, which is then solved by repeatedly planning collision-free paths for agents on a fixed graph, as in the Rolling-Horizon Collision Resolution (RHCR) algorithm. However, existing approaches make the limiting assumption that agents are only allowed to move pods that correspond to their current task, while considering the other pods as stationary obstacles (even though all pods are movable). This behavior can result in unnecessarily long paths which could otherwise be avoided by opening additional corridors via pod manipulation. To this end, we explore the implications of allowing agents the flexibility of dynamically relocating pods. We call this new problem Terraforming MAPD (tMAPD) and develop an RHCR-based approach to tackle it. As the extra flexibility of terraforming comes at a significant computational cost, we utilize this capability judiciously by identifying situations where it could make a significant impact on the solution quality. In particular, we invoke terraforming in response to disruptions that often occur in automated warehouses, e.g., when an item is dropped from a pod or when agents malfunction. Empirically, using our approach for tMAPD, where disruptions are modeled via a stochastic process, we improve throughput by over 10%, reduce the maximum service time (the difference between the drop-off time and the pickup time of a pod) by more than 50%, without drastically increasing the runtime, compared to the MAPD setting.

Abstract: Federated Learning (FL) has emerged as a significant advancement in the field of Artificial Intelligence (AI), enabling collaborative model training across distributed devices while maintaining data privacy. As the importance of FL increases, addressing trustworthiness issues in its various aspects becomes crucial. In this survey, we provide an extensive overview of the current state of Trustworthy FL, exploring existing solutions and well-defined pillars relevant to Trustworthy . Despite the growth in literature on trustworthy centralized Machine Learning (ML)/Deep Learning (DL), further efforts are necessary to identify trustworthiness pillars and evaluation metrics specific to FL models, as well as to develop solutions for computing trustworthiness levels. We propose a taxonomy that encompasses three main pillars: Interpretability, Fairness, and Security & Privacy. Each pillar represents a dimension of trust, further broken down into different notions. Our survey covers trustworthiness challenges at every level in FL settings. We present a comprehensive architecture of Trustworthy FL, addressing the fundamental principles underlying the concept, and offer an in-depth analysis of trust assessment mechanisms. In conclusion, we identify key research challenges related to every aspect of Trustworthy FL and suggest future research directions. This comprehensive survey serves as a valuable resource for researchers and practitioners working on the development and implementation of Trustworthy FL systems, contributing to a more secure and reliable AI landscape.

Abstract: While the increased use of AI in the manufacturing sector has been widely noted, there is little understanding on the risks that it may raise in a manufacturing organisation. Although various high level frameworks and definitions have been proposed to consolidate potential risks, practitioners struggle with understanding and implementing them. This lack of understanding exposes manufacturing to a multitude of risks, including the organisation, its workers, as well as suppliers and clients. In this paper, we explore and interpret the applicability of responsible, ethical, and trustworthy AI within the context of manufacturing. We then use a broadened adaptation of a machine learning lifecycle to discuss, through the use of illustrative examples, how each step may result in a given AI trustworthiness concern. We additionally propose a number of research questions to the manufacturing research community, in order to help guide future research so that the economic and societal benefits envisaged by AI in manufacturing are delivered safely and responsibly.

Abstract: Trustworthiness of artificially intelligent agents is vital for the acceptance of human-machine teaming in industrial manufacturing environments. Predictable behaviours and explainable (and understandable) rationale allow humans collaborating with (and building) these agents to understand their motivations and therefore validate decisions that are made. To that aim, we make use of G\"ardenfors's cognitively inspired Conceptual Space framework to represent the agent's knowledge using concepts as convex regions in a space spanned by inherently comprehensible quality dimensions. A simple typicality quantification model is built on top of it to determine fuzzy category membership and classify instances interpretably. We apply it on a use case from the manufacturing domain, using objects' physical properties obtained from cobots' onboard sensors and utilisation properties from crowdsourced commonsense knowledge available at public knowledge bases. Such flexible knowledge representation based on property decomposition allows for data-efficient representation learning of typically highly specialist or specific manufacturing artefacts. In such a setting, traditional data-driven (e.g., computer vision-based) classification approaches would struggle due to training data scarcity. This allows for comprehensibility of an AI agent's acquired knowledge by the human collaborator thus contributing to trustworthiness. We situate our approach within an existing explainability framework specifying explanation desiderata. We provide arguments for our system's applicability and appropriateness for different roles of human agents collaborating with the AI system throughout its design, validation, and operation.

Abstract: The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks. In this study, we employ ``Introspective Tips" to facilitate LLMs in self-optimizing their decision-making. By introspectively examining trajectories, LLM refines its policy by generating succinct and valuable tips. Our method enhances the agent's performance in both few-shot and zero-shot learning situations by considering three essential scenarios: learning from the agent's past experiences, integrating expert demonstrations, and generalizing across diverse games. Importantly, we accomplish these improvements without fine-tuning the LLM parameters; rather, we adjust the prompt to generalize insights from the three aforementioned situations. Our framework not only supports but also emphasizes the advantage of employing LLM in in-contxt decision-making. Experiments involving over 100 games in TextWorld illustrate the superior performance of our approach.

Abstract: Convolution-BatchNorm (ConvBN) blocks are integral components in various computer vision tasks and other domains. A ConvBN block can operate in three modes: Train, Eval, and Deploy. While the Train mode is indispensable for training models from scratch, the Eval mode is suitable for transfer learning and model validation, and the Deploy mode is designed for the deployment of models. This paper focuses on the trade-off between stability and efficiency in ConvBN blocks: Deploy mode is efficient but suffers from training instability; Eval mode is widely used in transfer learning but lacks efficiency. To solve the dilemma, we theoretically reveal the reason behind the diminished training stability observed in the Deploy mode. Subsequently, we propose a novel Tune mode to bridge the gap between Eval mode and Deploy mode. The proposed Tune mode is as stable as Eval mode for transfer learning, and its computational efficiency closely matches that of the Deploy mode. Through extensive experiments in both object detection and classification tasks, carried out across various datasets and model architectures, we demonstrate that the proposed Tune mode does not hurt the original performance while significantly reducing GPU memory footprint and training time, thereby contributing an efficient solution to transfer learning with convolutional networks.

Abstract: Multi-objective optimisation problems involve finding solutions with varying trade-offs between multiple and often conflicting objectives. Ising machines are physical devices that aim to find the absolute or approximate ground states of an Ising model. To apply Ising machines to multi-objective problems, a weighted sum objective function is used to convert multi-objective into single-objective problems. However, deriving scalarisation weights that archives evenly distributed solutions across the Pareto front is not trivial. Previous work has shown that adaptive weights based on dichotomic search, and one based on averages of previously explored weights can explore the Pareto front quicker than uniformly generated weights. However, these adaptive methods have only been applied to bi-objective problems in the past. In this work, we extend the adaptive method based on averages in two ways: (i)~we extend the adaptive method of deriving scalarisation weights for problems with two or more objectives, and (ii)~we use an alternative measure of distance to improve performance. We compare the proposed method with existing ones and show that it leads to the best performance on multi-objective Unconstrained Binary Quadratic Programming (mUBQP) instances with 3 and 4 objectives and that it is competitive with the best one for instances with 2 objectives.

Abstract: Humans and animals have a rich and flexible understanding of the physical world, which enables them to infer the underlying dynamical trajectories of objects and events, plausible future states, and use that to plan and anticipate the consequences of actions. However, the neural mechanisms underlying these computations are unclear. We combine a goal-driven modeling approach with dense neurophysiological data and high-throughput human behavioral readouts to directly impinge on this question. Specifically, we construct and evaluate several classes of sensory-cognitive networks to predict the future state of rich, ethologically-relevant environments, ranging from self-supervised end-to-end models with pixel-wise or object-centric objectives, to models that future predict in the latent space of purely static image-based or dynamic video-based pretrained foundation models. We find strong differentiation across these model classes in their ability to predict neural and behavioral data both within and across diverse environments. In particular, we find that neural responses are currently best predicted by models trained to predict the future state of their environment in the latent space of pretrained foundation models optimized for dynamic scenes in a self-supervised manner. Notably, models that future predict in the latent space of video foundation models that are optimized to support a diverse range of sensorimotor tasks, reasonably match both human behavioral error patterns and neural dynamics across all environmental scenarios that we were able to test. Overall, these findings suggest that the neural mechanisms and behaviors of primate mental simulation are thus far most consistent with being optimized to future predict on dynamic, reusable visual representations that are useful for embodied AI more generally.

Abstract: Decentralized partially observable Markov decision processes (Dec-POMDPs) formalize the problem of designing individual controllers for a group of collaborative agents under stochastic dynamics and partial observability. Seeking a global optimum is difficult (NEXP complete), but seeking a Nash equilibrium -- each agent policy being a best response to the other agents -- is more accessible, and allowed addressing infinite-horizon problems with solutions in the form of finite state controllers. In this paper, we show that this approach can be adapted to cases where only a generative model (a simulator) of the Dec-POMDP is available. This requires relying on a simulation-based POMDP solver to construct an agent's FSC node by node. A related process is used to heuristically derive initial FSCs. Experiment with benchmarks shows that MC-JESP is competitive with exisiting Dec-POMDP solvers, even better than many offline methods using explicit models.

Abstract: This paper concludes five years of AI competitions based on Legends of Code and Magic (LOCM), a small Collectible Card Game (CCG), designed with the goal of supporting research and algorithm development. The game was used in a number of events, including Community Contests on the CodinGame platform, and Strategy Card Game AI Competition at the IEEE Congress on Evolutionary Computation and IEEE Conference on Games. LOCM has been used in a number of publications related to areas such as game tree search algorithms, neural networks, evaluation functions, and CCG deckbuilding. We present the rules of the game, the history of organized competitions, and a listing of the participant and their approaches, as well as some general advice on organizing AI competitions for the research community. Although the COG 2022 edition was announced to be the last one, the game remains available and can be played using an online leaderboard arena.