The pervasiveness of large language models and generative AI in online media has amplified the need for effective automated fact-checking to assist fact-checkers in tackling the increasing volume and sophistication of misinformation. The complex nature of fact-checking demands that automated fact-checking systems provide explanations that enable fact-checkers to scrutinise their outputs. However, it is unclear how these explanations should align with the decision-making and reasoning processes of fact-checkers to be effectively integrated into their workflows. Through semi-structured interviews with fact-checking professionals, we bridge this gap by: (i) providing an account of how fact-checkers assess evidence, make decisions, and explain their processes; (ii) examining how fact-checkers use automated tools in practice; and (iii) identifying fact-checker explanation requirements for automated fact-checking tools. The findings show unmet explanation needs and identify important criteria for replicable fact-checking explanations that trace the model's reasoning path, reference specific evidence, and highlight uncertainty and information gaps.

Multi-purpose Large Language Models (LLMs), a subset of generative Artificial Intelligence (AI), have recently made significant progress. While expectations for LLMs to assist systems engineering (SE) tasks are paramount; the interdisciplinary and complex nature of systems, along with the need to synthesize deep-domain knowledge and operational context, raise questions regarding the efficacy of LLMs to generate SE artifacts, particularly given that they are trained using data that is broadly available on the internet. To that end, we present results from an empirical exploration, where a human expert-generated SE artifact was taken as a benchmark, parsed, and fed into various LLMs through prompt engineering to generate segments of typical SE artifacts. This procedure was applied without any fine-tuning or calibration to document baseline LLM performance. We then adopted a two-fold mixed-methods approach to compare AI generated artifacts against the benchmark. First, we quantitatively compare the artifacts using natural language processing algorithms and find that when prompted carefully, the state-of-the-art algorithms cannot differentiate AI-generated artifacts from the human-expert benchmark. Second, we conduct a qualitative deep dive to investigate how they differ in terms of quality. We document that while the two-material appear very similar, AI generated artifacts exhibit serious failure modes that could be difficult to detect. We characterize these as: premature requirements definition, unsubstantiated numerical estimates, and propensity to overspecify. We contend that this study tells a cautionary tale about why the SE community must be more cautious adopting AI suggested feedback, at least when generated by multi-purpose LLMs.

Consider the process of collective decision-making, in which a group of individuals interactively select a preferred outcome from among a universe of alternatives. In this context, "representation" is the activity of making an individual's preferences present in the process via participation by a proxy agent -- i.e. their "representative". To this end, learned models of human behavior have the potential to fill this role, with practical implications for multi-agent scenario studies and mechanism design. In this work, we investigate the possibility of training \textit{language agents} to behave in the capacity of representatives of human agents, appropriately expressing the preferences of those individuals whom they stand for. First, we formalize the setting of \textit{collective decision-making} -- as the episodic process of interaction between a group of agents and a decision mechanism. On this basis, we then formalize the problem of \textit{digital representation} -- as the simulation of an agent's behavior to yield equivalent outcomes from the mechanism. Finally, we conduct an empirical case study in the setting of \textit{consensus-finding} among diverse humans, and demonstrate the feasibility of fine-tuning large language models to act as digital representatives.

Explainability is important for the transparency of autonomous and intelligent systems and for helping to support the development of appropriate levels of trust. There has been considerable work on developing approaches for explaining systems and there are standards that specify requirements for transparency. However, there is a gap: the standards are too high-level and do not adequately specify requirements for explainability. This paper develops a scoresheet that can be used to specify explainability requirements or to assess the explainability aspects provided for particular applications. The scoresheet is developed by considering the requirements of a range of stakeholders and is applicable to Multiagent Systems as well as other AI technologies. We also provide guidance for how to use the scoresheet and illustrate its generality and usefulness by applying it to a range of applications.

Communication is crucial in cooperative multi-agent systems with partial observability, as it enables a better understanding of the environment and improves coordination. In extreme environments such as those underwater or in space, the frequency of communication between agents is often limited [1, 2]. For example, a satellite may not be able to reliably receive and react to messages from other satellites synchronously due to limited onboard power and communication delays. In these scenarios, agents aim to establish a communication protocol that allows them to operate independently while still receiving sufficient information to effectively coordinate with nearby agents. Multi-agent reinforcement learning (MARL) has emerged as a popular approach for addressing cooperative navigation challenges involving multiple agents.

Planetary exploration using aerial assets has the potential for unprecedented scientific discoveries on Mars. While NASA's Mars helicopter Ingenuity proved flight in Martian atmosphere is possible, future Mars rotocrafts will require advanced navigation capabilities for long-range flights. One such critical capability is Map-based Localization (MbL) which registers an onboard image to a reference map during flight in order to mitigate cumulative drift from visual odometry. However, significant illumination differences between rotocraft observations and a reference map prove challenging for traditional MbL systems, restricting the operational window of the vehicle. In this work, we investigate a new MbL system and propose Geo-LoFTR, a geometry-aided deep learning model for image registration that is more robust under large illumination differences than prior models. The system is supported by a custom simulation framework that uses real orbital maps to produce large amounts of realistic images of the Martian terrain. Comprehensive evaluations show that our proposed system outperforms prior MbL efforts in terms of localization accuracy under significant lighting and scale variations. Furthermore, we demonstrate the validity of our approach across a simulated Martian day.

Accurate demand forecasting is vital for ensuring reliable access to contraceptive products, supporting key processes like procurement, inventory, and distribution. However, forecasting contraceptive demand in developing countries presents challenges, including incomplete data, poor data quality, and the need to account for multiple geographical and product factors. Current methods often rely on simple forecasting techniques, which fail to capture demand uncertainties arising from these factors, warranting expert involvement. Our study aims to improve contraceptive demand forecasting by combining probabilistic forecasting methods with expert knowledge. We developed a hybrid model that combines point forecasts from domain-specific model with probabilistic distributions from statistical and machine learning approaches, enabling human input to fine-tune and enhance the system-generated forecasts. This approach helps address the uncertainties in demand and is particularly useful in resource-limited settings. We evaluate different forecasting methods, including time series, Bayesian, machine learning, and foundational time series methods alongside our new hybrid approach. By comparing these methods, we provide insights into their strengths, weaknesses, and computational requirements. Our research fills a gap in forecasting contraceptive demand and offers a practical framework that combines algorithmic and human expertise. Our proposed model can also be generalized to other humanitarian contexts with similar data patterns.

This paper presents an architecture for simulating the actions of a norm-aware intelligent agent whose behavior with respect to norm compliance is set, and can later be changed, by a human controller. Updating an agent's behavior mode from a norm-abiding to a riskier one may be relevant when the agent is involved in time-sensitive rescue operations, for example. We base our work on the Authorization and Obligation Policy Language AOPL designed by Gelfond and Lobo for the specification of norms. We introduce an architecture and a prototype software system that can be used to simulate an agent's plans under different behavior modes that can later be changed by the controller. We envision such software to be useful to policy makers, as they can more readily understand how agents may act in certain situations based on the agents' attitudes towards norm-compliance. Policy makers may then refine their policies if simulations show unwanted consequences.

The emergence of Generative AI (Gen AI) has motivated an interest in understanding how it could be used to enhance productivity across various tasks. We add to research results for the performance impact of Gen AI on complex knowledge-based tasks in a public sector setting. In a pre-registered experiment, after establishing a baseline level of performance, we find mixed evidence for two types of composite tasks related to document understanding and data analysis. For the Documents task, the treatment group using Gen AI had a 17% improvement in answer quality scores (as judged by human evaluators) and a 34% improvement in task completion time compared to a control group. For the Data task, we find the Gen AI treatment group experienced a 12% reduction in quality scores and no significant difference in mean completion time compared to the control group. These results suggest that the benefits of Gen AI may be task and potentially respondent dependent. We also discuss field notes and lessons learned, as well as supplementary insights from a post-trial survey and feedback workshop with participants.

Molecular dynamics (MD) simulations are essential for understanding biomolecular systems but remain challenging to automate. Recent advances in large language models (LLM) have demonstrated success in automating complex scientific tasks using LLM-based agents. In this paper, we introduce MDCrow, an agentic LLM assistant capable of automating MD workflows. MDCrow uses chain-of-thought over 40 expert-designed tools for handling and processing files, setting up simulations, analyzing the simulation outputs, and retrieving relevant information from literature and databases. We assess MDCrow's performance across 25 tasks of varying required subtasks and difficulty, and we evaluate the agent's robustness to both difficulty and prompt style. \texttt{gpt-4o} is able to complete complex tasks with low variance, followed closely by \texttt{llama3-405b}, a compelling open-source model. While prompt style does not influence the best models' performance, it has significant effects on smaller models.