Organization's communication is essential for public trust, but the rise of generative AI models has introduced significant challenges by generating persuasive content that can form competing narratives with official messages from government and commercial organizations at speed and scale. This has left agencies in a reactive position, often unaware of how these models construct their persuasive strategies, making it more difficult to sustain communication effectiveness. In this paper, we introduce a large LLM-generated persuasion attack dataset, which includes 134,136 attacks generated by GPT-4, Gemma 2, and Llama 3.1 on agency news. These attacks span 23 persuasive techniques from SemEval 2023 Task 3, directed toward 972 press releases from ten agencies. The generated attacks come in two mediums, press release statements and social media posts, covering both long-form and short-form communication strategies. We analyzed the moral resonance of these persuasion attacks to understand their attack vectors. GPT-4's attacks mainly focus on Care, with Authority and Loyalty also playing a role. Gemma 2 emphasizes Care and Authority, while Llama 3.1 centers on Loyalty and Care. Analyzing LLM-generated persuasive attacks across models will enable proactive defense, allow to create the reputation armor for organizations, and propel the development of both effective and resilient communications in the information ecosystem.

When large language models (LLMs) are aligned to a specific online community, do they exhibit generalizable behavioral patterns that mirror that community's attitudes and responses to new uncertainty, or are they simply recalling patterns from training data? We introduce a framework to test epistemic stance transfer: targeted deletion of event knowledge, validated with multiple probes, followed by evaluation of whether models still reproduce the community's organic response patterns under ignorance. Using Russian--Ukrainian military discourse and U.S. partisan Twitter data, we find that even after aggressive fact removal, aligned LLMs maintain stable, community-specific behavioral patterns for handling uncertainty. These results provide evidence that alignment encodes structured, generalizable behaviors beyond surface mimicry. Our framework offers a systematic way to detect behavioral biases that persist under ignorance, advancing efforts toward safer and more transparent LLM deployments.

The exponential growth of scientific knowledge has created significant barriers to cross-disciplinary knowledge discovery, synthesis and research collaboration. In response to this challenge, we present BioSage, a novel compound AI architecture that integrates LLMs with RAG, orchestrated specialized agents and tools to enable discoveries across AI, data science, biomedical, and biosecurity domains. Our system features several specialized agents including the retrieval agent with query planning and response synthesis that enable knowledge retrieval across domains with citation-backed responses, cross-disciplinary translation agents that align specialized terminology and methodologies, and reasoning agents that synthesize domain-specific insights with transparency, traceability and usability. We demonstrate the effectiveness of our BioSage system through a rigorous evaluation on scientific benchmarks (LitQA2, GPQA, WMDP, HLE-Bio) and introduce a new cross-modal benchmark for biology and AI, showing that our BioSage agents outperform vanilla and RAG approaches by 13\%-21\% powered by Llama 3.1. 70B and GPT-4o models. We perform causal investigations into compound AI system behavior and report significant performance improvements by adding RAG and agents over the vanilla models. Unlike other systems, our solution is driven by user-centric design principles and orchestrates specialized user-agent interaction workflows supporting scientific activities including but not limited to summarization, research debate and brainstorming. Our ongoing work focuses on multimodal retrieval and reasoning over charts, tables, and structured scientific data, along with developing comprehensive multimodal benchmarks for cross-disciplinary discovery. Our compound AI solution demonstrates significant potential for accelerating scientific advancement by reducing barriers between traditionally siloed domains.

We study the problem of reducing test-time acquisition costs in classification systems. Our goal is to learn decision rules that adaptively select sensors for each example as necessary to make a confident prediction. We model our system as a directed acyclic graph (DAG) where internal nodes correspond to sensor subsets and decision functions at each node choose whether to acquire a new sensor or classify using the available measurements. This problem can be posed as an empirical risk minimization over training data. Rather than jointly optimizing such a highly coupled and non-convex problem over all decision nodes, we propose an efficient algorithm motivated by dynamic programming. We learn node policies in the DAG by reducing the global objective to a series of cost sensitive learning problems. Our approach is computationally efficient and has proven guarantees of convergence to the optimal system for a fixed architecture. In addition, we present an extension to map other budgeted learning problems with large number of sensors to our DAG architecture and demonstrate empirical performance exceeding state-of-the-art algorithms for data composed of both few and many sensors.

We introduce Lattice Annotated Temporal (LAT) Logic, an extension of Generalized Annotated Logic Programs (GAPs) that incorporates temporal reasoning and supports open-world semantics through the use of a lower lattice structure. This logic combines an efficient deduction process with temporal logic programming to support non-Markovian relationships and open-world reasoning capabilities. The open-world aspect, a by-product of the use of the lower-lattice annotation structure, allows for efficient grounding through a Skolemization process, even in domains with infinite or highly diverse constants. We provide a suite of theoretical results that bound the computational complexity of the grounding process, in addition to showing that many of the results on GAPs (using an upper lattice) still hold with the lower lattice and temporal extensions (though different proof techniques are required). Our open-source implementation, PyReason, features modular design, machine-level optimizations, and direct integration with reinforcement learning environments. Empirical evaluations across multi-agent simulations and knowledge graph tasks demonstrate up to three orders of magnitude speedup and up to five orders of magnitude memory reduction while maintaining or improving task performance. Additionally, we evaluate LAT Logic's value in reinforcement learning environments as a non-Markovian simulator, achieving up to three orders of magnitude faster simulation with improved agent performance, including a 26% increase in win rate due to capturing richer temporal dependencies. These results highlight LAT Logic's potential as a unified, extensible framework for open-world temporal reasoning in dynamic and uncertain environments. Our implementation is available at: pyreason.syracuse.edu.

Birds of a Different Feather Flock Together: Exploring Opportunities and Challenges in Animal-Human-Machine Teaming Myke C. Cohen 1,2, David A. Grimm 3, Reuth Mirsky 4, and Xiaoyun Yin 1 1 Arizona State University, Mesa, AZ 2 Aptima, Inc., Woburn, MA 3 Georgia Institute of Technology, Atlanta, GA 4 Tufts University, Medford, MA Abstract Animal-Human-Machine (AHM) teams are a type of hybrid intelligence system wherein interactions between a human, AI-enabled machine, and animal members can result in unique capabilities greater than the sum of their parts. This paper calls for a systematic approach to studying the design of AHM team structures to optimize performance and overcome limitations in various applied settings. We consider the challenges and opportunities in investigating the synergistic potential of AHM team members by introducing a set of dimensions of AHM team functioning to effectively utilize each member's strengths while compensating for individual weaknesses. Using three representative examples of such teams--security screening, search-and-rescue, and guide dogs--the paper illustrates how AHM teams can tackle complex tasks. We conclude with open research directions that this multidimensional approach presents for studying hybrid human-AI systems beyond AHM teams. Keywords: multi-agent systems, animal-human-machine teaming, functional allocation 1 Introduction Consider a Blind or Visually Impaired (BVI) person training to be assisted by a guide dog. When the pair reaches an obstacle along their path, they 1 arXiv:2504.13973v1

As human-agent teaming (HAT) research continues to grow, computational methods for modeling HAT behaviors and measuring HAT effectiveness also continue to develop. One rising method involves the use of human digital twins (HDT) to approximate human behaviors and socio-emotional-cognitive reactions to AI-driven agent team members. In this paper, we address three research questions relating to the use of digital twins for modeling trust in HATs. First, to address the question of how we can appropriately model and operationalize HAT trust through HDT HAT experiments, we conducted causal analytics of team communication data to understand the impact of empathy, socio-cognitive, and emotional constructs on trust formation. Additionally, we reflect on the current state of the HAT trust science to discuss characteristics of HAT trust that must be replicable by a HDT such as individual differences in trust tendencies, emergent trust patterns, and appropriate measurement of these characteristics over time. Second, to address the question of how valid measures of HDT trust are for approximating human trust in HATs, we discuss the properties of HDT trust: self-report measures, interaction-based measures, and compliance type behavioral measures. Additionally, we share results of preliminary simulations comparing different LLM models for generating HDT communications and analyze their ability to replicate human-like trust dynamics. Third, to address how HAT experimental manipulations will extend to human digital twin studies, we share experimental design focusing on propensity to trust for HDTs vs. transparency and competency-based trust for AI agents.

Spatiotemporal data faces many analogous challenges to natural language text including the ordering of locations (words) in a sequence, long range dependencies between locations, and locations having multiple meanings. In this work, we propose a novel model for representing high dimensional spatiotemporal trajectories as sequences of discrete locations and encoding them with a Transformer-based neural network architecture. Similar to language models, our Sequence Transformer for Agent Representation Encodings (STARE) model can learn representations and structure in trajectory data through both supervisory tasks (e.g., classification), and self-supervisory tasks (e.g., masked modelling). We present experimental results on various synthetic and real trajectory datasets and show that our proposed model can learn meaningful encodings that are useful for many downstream tasks including discriminating between labels and indicating similarity between locations. Using these encodings, we also learn relationships between agents and locations present in spatiotemporal data.

Application of Unmanned Aerial Vehicles (UAVs) in search and rescue, emergency management, and law enforcement has gained traction with the advent of low-cost platforms and sensor payloads. The emergence of hybrid neural and symbolic AI approaches for complex reasoning is expected to further push the boundaries of these applications with decreasing levels of human intervention. However, current UAV simulation environments lack semantic context suited to this hybrid approach. To address this gap, HAMERITT (Hybrid Ai Mission Environment for RapId Training and Testing) provides a simulation-based autonomy software framework that supports the training, testing and assurance of neuro-symbolic algorithms for autonomous maneuver and perception reasoning. HAMERITT includes scenario generation capabilities that offer mission-relevant contextual symbolic information in addition to raw sensor data. Scenarios include symbolic descriptions for entities of interest and their relations to scene elements, as well as spatial-temporal constraints in the form of time-bounded areas of interest with prior probabilities and restricted zones within those areas. HAMERITT also features support for training distinct algorithm threads for maneuver vs. perception within an end-to-end mission run. Future work includes improving scenario realism and scaling symbolic context generation through automated workflow.

Abstract-- As collaborative robots become more common in manufacturing scenarios and adopted in hybrid human-robot teams, we should develop new interaction and communication strategies to ensure smooth collaboration between agents. In this paper, we propose a novel communicative interface that uses Mixed Reality as a medium to perform Kinesthetic Teaching (KT) on any robotic platform. We evaluate our proposed approach in a user study involving multiple subjects and two different robots, comparing traditional physical KT with holographic-based KT through user experience questionnaires and task-related metrics. Index Terms-- Human-Robot Interaction, Mixed Reality, Kinesthetic Teaching, Software Architecture. In smart factories, robots are expected to coexist and work alongside humans rather than replace them.