In Multi-Agent Systems (MAS), agents are designed with social capabilities, allowing them to understand and reason about social concepts such as norms when interacting with others (e.g., inter-robot interactions). In Normative MAS (NorMAS), researchers study how norms develop, and how violations are detected and sanctioned. However, existing research in NorMAS use symbolic approaches (e.g., formal logic) for norm representation and reasoning whose application is limited to simplified environments. In contrast, Multimodal Large Language Models (MLLMs) present promising possibilities to develop software used by robots to identify and reason about norms in a wide variety of complex social situations embodied in text and images. However, prior work on norm reasoning have been limited to text-based scenarios. This paper investigates the norm reasoning competence of five MLLMs by evaluating their ability to answer norm-related questions based on thirty text-based and thirty image-based stories, and comparing their responses against humans. Our results show that MLLMs demonstrate superior performance in norm reasoning in text than in images. GPT-4o performs the best in both modalities offering the most promise for integration with MAS, followed by the free model Qwen-2.5VL. Additionally, all models find reasoning about complex norms challenging.
Affective polarization has been central to political and social studies, with growing focus on social media, where partisan divisions are often exacerbated. Real-world studies tend to have limited scope, while simulated studies suffer from insufficient high-quality training data, as manually labeling posts is labor-intensive and prone to subjective biases. The lack of adequate tools to formalize different definitions of affective polarization across studies complicates result comparison and hinders interoperable frameworks. We present a multi-agent model providing a comprehensive approach to studying affective polarization in social media. To operationalize our framework, we develop a platform leveraging large language models (LLMs) to construct virtual communities where agents engage in discussions. We showcase the potential of our platform by (1) analyzing questions related to affective polarization, as explored in social science literature, providing a fresh perspective on this phenomenon, and (2) introducing scenarios that allow observation and measurement of polarization at different levels of granularity and abstraction. Experiments show that our platform is a flexible tool for computational studies of complex social dynamics such as affective polarization. It leverages advanced agent models to simulate rich, context-sensitive interactions and systematically explore research questions traditionally addressed through human-subject studies.
We investigate whether progressive data scheduling – a curriculum learning strategy that incrementally increases training data exposure (33%→67%→100%) – yields consistent efficiency gains across architecturally distinct document understanding models. By evaluating BERT (text-only, 110M parameters) and LayoutLMv3 (multimodal, 126M parameters) on the FUNSD and CORD benchmarks, we establish that this schedule reduces wall-clock training time by approximately 33%, commensurate with the reduction from 6.67 to 10.0 effective epoch-equivalents of data. To isolate curriculum effects from compute reduction, we introduce matched-compute baselines (Standard-7) that control for total gradient updates. On the FUNSD dataset, the curriculum significantly outperforms the matched-compute baseline for BERT (ΔF1 = +0.023, p=0.022, d_z=3.83), constituting evidence for a genuine scheduling benefit in capacity-constrained models. In contrast, no analogous benefit is observed for LayoutLMv3 (p=0.621), whose multimodal representations provide sufficient inductive bias. On the CORD dataset, all conditions converge to equivalent F1 scores (≥0.947) irrespective of scheduling, indicating a performance ceiling. Schedule ablations comparing progressive, two-phase, reverse, and random pacing confirm that the efficiency gain derives from reduced data volume rather than ordering. Taken together, these findings demonstrate that progressive scheduling is a reliable compute-reduction strategy across model families, with curriculum-specific benefits contingent on the interaction between model capacity and task complexity.
Language models and software tools are essential to support the continuing vitality of lesser-used languages; however, currently popular neural models require considerable data for training, which normally is not available for such low-resource languages. This paper describes work-in-progress to construct a rule-based model of Gaidhlig morphology using data from Wiktionary, arguing that rule-based systems effectively leverage limited sample data, support greater interpretability, and provide insights useful in the design of teaching materials. The use of SQL for querying the occurrence of different lexical patterns is investigated, and a declarative rule-base is presented that allows Python utilities to derive inflected forms of Gaidhlig words. This functionality could be used to support educational tools that teach or explain language patterns, for example, or to support higher level tools such as rule-based dependency parsers. This approach adds value to the data already present in Wiktionary by adapting it to new use-cases.
Quantum state tomography (QST) is essential for validating quantum devices but suffers from exponential scaling in system size. Neural-network quantum states, such as Restricted Boltzmann Machines (RBMs), can efficiently parameterize individual many-body quantum states and have been successfully used for QST. However, existing approaches are point-wise and require retraining at every parameter value in a phase diagram. We introduce a parametric QST framework based on a hypernetwork that conditions an RBM on Hamiltonian control parameters, enabling a single model to represent an entire family of quantum ground states. Applied to the transverse-field Ising model, our HyperRBM achieves high-fidelity reconstructions from local Pauli measurements on 1D and 2D lattices across both phases and through the critical region. Crucially, the model accurately reproduces the fidelity susceptibility and identifies the quantum phase transition without prior knowledge of the critical point. These results demonstrate that hypernetwork-modulated neural quantum states provide an efficient and scalable route to tomographic reconstruction across full phase diagrams.
We consider the problem of distinguishing human-written creative fiction (excerpts from novels) from similar text generated by an LLM. Our results show that, while human observers perform poorly (near chance levels) on this binary classification task, a variety of machine-learning models achieve accuracy in the range 0.93 - 0.98 over a previously unseen test set, even using only short samples and single-token (unigram) features. We therefore employ an inherently interpretable (linear) classifier (with a test accuracy of 0.98), in order to elucidate the underlying reasons for this high accuracy. In our analysis, we identify specific unigram features indicative of LLM-generated text, one of the most important being that the LLM tends to use a larger variety of synonyms, thereby skewing the probability distributions in a manner that is easy to detect for a machine learning classifier, yet very difficult for a human observer. Four additional explanation categories were also identified, namely, temporal drift, Americanisms, foreign language usage, and colloquialisms. As identification of the AI-generated text depends on a constellation of such features, the classification appears robust, and therefore not easy to circumvent by malicious actors intent on misrepresenting AI-generated text as human work.
As multi-agent systems are increasingly utilized for reasoning and decision-making applications, there is a greater need for LLM-based agents to have something resembling propositional beliefs. One simple method for doing so is to include statements describing beliefs maintained in the prompt space (in what we'll call their belief boxes). But when agents have such statements in belief boxes, how does it actually affect their behaviors and dispositions towards those beliefs? And does it significantly affect agents' ability to be persuasive in multi-agent scenarios? Likewise, if the agents are given instructions to be open-minded, how does that affect their behaviors? We explore these and related questions in a series of experiments. Our findings confirm that instructing agents to be open-minded affects how amenable they are to belief change. We show that incorporating belief statements and their strengths influences an agent's resistance to (and persuasiveness against) opposing viewpoints. Furthermore, it affects the likelihood of belief change, particularly when the agent is outnumbered in a debate by opposing viewpoints, i.e., peer pressure scenarios. The results demonstrate the feasibility and validity of the belief box technique in reasoning and decision-making tasks.
Recent advances in Large Language Model Multi-Agent Systems enable scalable orchestration and retrieval of specialized, parallelized subagents, each equipped with hundreds or thousands of Model Context Protocol (MCP) servers and tools. However, existing agent, MCP, and retrieval methods typically match queries against a single agent description, obscuring fine-grained tool capabilities of each agent, resulting in suboptimal agent selection. We introduce Agent-as-a-Graph retrieval, a knowledge graph retrieval augmented generation approach that represents both tools and their parent agents as nodes and edges in a knowledge graph. During retrieval, i) relevant agents and tool nodes are first retrieved through vector search, ii) we apply a type-specific weighted reciprocal rank fusion (wRRF) for reranking tools and agents, and iii) parent agents are traversed in the knowledge graph for the final set of agents. We evaluate Agent-as-a-Graph on the LiveMCPBenchmark, achieving 14.9
Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models to answer financial questions using external knowledge bases of U.S. SEC filings, earnings reports, and regulatory documents. However, existing work lacks systematic comparison of vector-based and non-vector RAG architectures for financial documents, and the empirical impact of advanced RAG techniques on retrieval accuracy, answer quality, latency, and cost remain unclear. We present the first systematic evaluation comparing vector-based agentic RAG using hybrid search and metadata filtering against hierarchical node-based systems that traverse document structure without embeddings. We evaluate two enhancement techniques applied to the vector-based architecture, i) cross-encoder reranking for retrieval precision, and ii) small-to-big chunk retrieval for context completeness. Across 1,200 SEC 10-K, 10-Q, and 8-K filings on a 150-question benchmark, we measure retrieval metrics (MRR, Recall@5), answer quality through LLM-as-a-judge pairwise comparisons, latency, and preprocessing costs. Vector-based agentic RAG achieves a 68
Bond markets respond differently to macroeconomic news compared to equity markets, yet most sentiment models, including FinBERT, are trained primarily on general financial or equity news data. This mismatch is important because bond prices often move in the opposite direction to economic optimism, making general or equity-based sentiment tools potentially misleading. In this paper, we introduce BondBERT, a transformer-based language model fine-tuned on bond-specific news. BondBERT can act as the perception and reasoning component of a financial decision-support agent, providing sentiment signals that integrate with forecasting models. It is a generalisable framework for adapting transformers to low-volatility, domain-inverse sentiment tasks by compiling and cleaning 30,000 UK bond market articles (2018--2025) for training, validation, and testing. We compare BondBERT's sentiment predictions against FinBERT, FinGPT, and Instruct-FinGPT using event-based correlation, up/down accuracy analyses, and LSTM forecasting across ten UK sovereign bonds. We find that BondBERT consistently produces positive correlations with bond returns, achieves higher alignment and forecasting accuracy than the three baseline models, with lower normalised RMSE and higher information coefficient. These results demonstrate that domain-specific sentiment adaptation better captures fixed income dynamics, bridging a gap between NLP advances and bond market analytics.
LLM-based AI agents still lack the technical means to automatically build nuanced and differentiated trust in other agents at the beginning of an agent-to-agent dialogue. But autonomous and interoperable trust establishing becomes a fundamental prerequisite once agents start to operate beyond isolated environments and engage in dialogues across individual or organizational boundaries. A promising way to fill this gap in Agentic AI is to equip agents with long-lived digital identities and introduce tamper-proof and flexible identity-bound attestations of agents, provisioned by commonly trusted third parties and designed for cross-domain verifiability. This article presents a conceptual framework and a prototypical multi-agent system, where each agent is endowed with a self-sovereign digital identity. It combines a unique and ledger-anchored Decentralized Identifier (DID) of an agent with a set of third-party issued Verifiable Credentials (VCs). This enables agents at the start of a dialog to prove ownership of their self-controlled DIDs for authentication purposes and to establish various cross-domain trust relationships through the spontaneous exchange of their self-hosted DID-bound VCs. A comprehensive evaluation of the prototypical implementation demonstrates technical feasibility but also reveals limitations once an agent's LLM is in sole charge to control the respective security procedures.
Recent advances in quantum computing have shown great potential for solving combinatorial optimization problems. A notable example is the quadratic knapsack problem, a constrained binary optimization problem. However, current quantum-inspired algorithms require Quadratic Unconstrained Binary Optimization (QUBO) formulations. Transforming constrained optimization into QUBO impacts the algorithms' speed and efficiency. In this study, we evaluate five existing transformation methods and propose four novel approaches. We assess them by using Simulated Annealing (SA), and find that three of our approaches outperform existing methods in terms of execution time as well as quality and quantity of feasible solutions found. Also, we tested these transformations on a quantum annealer, which was unable to solve even small instances, due to limitations in connectivity and error rates. In general, our results highlight the advantages of the new approaches, which reduce the number of variables in the QUBO representation.
The deployment of autonomous drone swarms in disaster response missions necessitates the development of flexible, scalable, and robust coordination systems. Traditional fixed architectures struggle to cope with dynamic and unpredictable environments, leading to inefficiencies in energy consumption and connectivity. This paper addresses this gap by proposing an adaptive architecture for drone swarms, leveraging a Large Language Model to dynamically select the optimal architecture as centralized, hierarchical, or holonic based on real time mission parameters such as task complexity, swarm size, and communication stability. Our system addresses the challenges of scalability, adaptability, and robustness,ensuring efficient energy consumption and maintaining connectivity under varying conditions. Extensive simulations demonstrate that our adaptive architecture outperforms traditional static models in terms of scalability, energy efficiency, and connectivity. These results highlight the potential of our approach to provide a scalable, adaptable, and resilient solution for real world disaster response scenarios.
Large language models (LLMs) have gained significant traction across a wide range of fields in recent years. There is also a growing expectation for them to display human-like personalities during interactions. To meet this expectation, numerous studies have proposed methods for modelling LLM personalities through psychometric evaluations. However, most existing models face two major limitations: they rely on the Big Five (OCEAN) framework, which only provides coarse personality dimensions, and they lack mechanisms for controlling trait intensity. In this paper, we address this gap by extending the Machine Personality Inventory (MPI), which originally used the Big Five model, to incorporate the 16 Personality Factor (16PF) model, allowing expressive control over sixteen distinct traits. We also developed a structured framework known as Specific Attribute Control (SAC) for evaluating and dynamically inducing trait intensity in LLMs. Our method introduces adjective-based semantic anchoring to guide trait intensity expression and leverages behavioural questions across five intensity factors: \textit{Frequency}, \textit{Depth}, \textit{Threshold}, \textit{Effort}, and \textit{Willingness}. Through experimentation, we find that modelling intensity as a continuous spectrum yields substantially more consistent and controllable personality expression compared to binary trait toggling. Moreover, we observe that changes in target trait intensity systematically influence closely related traits in psychologically coherent directions, suggesting that LLMs internalize multi-dimensional personality structures rather than treating traits in isolation. Our work opens new pathways for controlled and nuanced human-machine interactions in domains such as healthcare, education, and interviewing processes, bringing us one step closer to truly human-like social machines.
Modern computer systems store vast amounts of personal data, enabling advances in AI and ML but risking user privacy and trust. For privacy reasons, it is sometimes desired for an ML model to forget part of the data it was trained on. In this paper, we introduce a novel unlearning approach based on Forgetting Neural Networks (FNNs), a neuroscience-inspired architecture that explicitly encodes forgetting through multiplicative decay factors. While FNNs had previously been studied as a theoretical construct, we provide the first concrete implementation and demonstrate their effectiveness for targeted unlearning. We propose several variants with per-neuron forgetting factors, including rank-based assignments guided by activation levels, and evaluate them on MNIST and Fashion-MNIST benchmarks. Our method systematically removes information associated with forget sets while preserving performance on retained data. Membership inference attacks confirm the effectiveness of FNN-based unlearning in erasing information about the training data from the neural network. These results establish FNNs as a promising foundation for efficient and interpretable unlearning.
