arXiv subjects

John D. Kelleher

Publications and source records attributed to John D. Kelleher.

At least 19 recordsLinked to original sources

arXiv2026

Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models

The growth of agentic AI has drawn significant attention to function calling Large Language Models (LLMs), which are designed to extend the capabilities of AI-powered system by invoking external functions. Injection and jailbreaking attacks have been extensively explored to showcase the vulnerabilities of LLMs to user prompt manipulation. The expanded capabilities of agentic models introduce further vulnerabilities via their function calling interface. Recent work in LLM security showed that function calling can be abused, leading to data tampering and theft, causing disruptive behavior such as endless loops, or causing LLMs to produce harmful content in the style of jailbreaking attacks. This paper introduces a novel function hijacking attack (FHA) that manipulates the tool selection process of agentic models to force the invocation of an attacker-chosen function. While existing attacks focus on semantic preference of the model for function-calling tasks, we show that FHA is largely agnostic to the context semantics and remains effective across domains and function sets. We demonstrate that FHA generalizes to unseen queries and payload perturbations under a fixed target model, reaching 62.5% to 81.9% ASR on held-out queries across 4 function-calling LLMs (instructed and reasoning models), evaluated on the Berkeley Function Calling Leaderboard (BFCL). We further evaluate the cross-model transferability of FHA, showing that FHA can be transferred to other model sizes and families (11.2-27.6% ASR). Our findings further demonstrate the need for strong guardrails and modules for agentic systems.

cs.CR↗

arXiv2026

Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey

The rapid growth of large language models (LLMs) with diverse capabilities, costs, and domains has created a critical need for intelligent model selection at inference time. While smaller models suffice for routine queries, complex tasks demand more capable models. However, static model deployment does not account for the complexity and domain of incoming queries, leading to suboptimal performance and increased costs. Dynamic routing systems that adaptively select models based on query characteristics have emerged as a solution to this challenge. This survey provides a systematic analysis of multi-LLM routing and cascading approaches, focusing on systems that route queries across a pool of independently trained LLMs at inference time. We cover diverse routing paradigms, including query difficulty, human preferences, clustering, uncertainty quantification, reinforcement learning, multimodality, and cascading. For each paradigm, we analyze representative methods and examine key trade-offs. Beyond taxonomy, we introduce a conceptual framework that characterizes routing systems along three dimensions: when decisions are made, what information is used, and how they are computed. This perspective highlights that practical systems are often compositional, integrating multiple paradigms under operational constraints. Our analysis demonstrates that effective multi-LLM routing requires balancing competing objectives. Choosing the optimal routing strategy depends on deployment and computational constraints. Well-designed routing systems can outperform even the most powerful individual models by strategically leveraging specialized capabilities across models while maximizing efficiency gains. Meanwhile, open challenges remain in developing and evaluating routing mechanisms that generalize across diverse architectures, modalities, and applications.

cs.NI↗

arXiv2026

TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping

The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling LRMs to reason longer, and more accurately. However, a growing body of studies show that LRMs are still inefficient, over-generating verification and reflection steps. Additionally, the high-level role of each reasoning step and how different step types contribute to the generation of correct answers, is largely underexplored. To address this challenge, we introduce TRACES (Tagging of the Reasoning steps enabling Adaptive Cost-Efficient early-Stopping), a lightweight framework that tags reasoning steps in real-time, and enable adaptive, cost-efficient early stopping of large-language-model inferences. By monitoring reasoning behaviors during inferences, we find that LRMs tend to shift their reasoning behavior after reaching a correct answer. We demonstrate that the monitoring of the specific type of steps can produce effective interpretable early stopping criteria. Evaluated on three mathematical reasoning benchmarks (MATH500, GSM8K, AIME) and two knowledge and reasoning benchmarks (MMLU and GPQA), TRACES achieve 20 to 50% token reduction while maintaining comparable accuracy to standard generation. On harder tasks (BeyondAIME, IMO AnswerBench), the accuracy-efficiency trade-off is steeper, requiring a more conservative early-stopping threshold. This work offers a novel way to study and control the generation behavior of LRMs.

cs.CL↗

arXiv2026

From Continuous Predictors to Clinical Thresholds: Early Evidence on Performance Trade-offs of Guideline-Based Categorisation for Ischaemic Stroke Outcome Prediction

Machine learning models achieve strong predictive accuracy for 90-day outcome prediction in acute ischaemic stroke, yet clinical adoption is limited by the misalignment of model explanations with clinicians' reasoning. Motivated by a clinician user study calling for clinical guideline-aligned cut-offs, we ask whether continuous predictors can be replaced by clinically informed categorical encodings without sacrificing performance. On a multi-centre European registry stratified into three treatment cohorts, we compare standard and fully categorised gradient-boosted models, the latter using stroke guideline-aligned, treatment-specific thresholds. The fully categorised models are statistically indistinguishable from their continuous counterparts in two of the treatment cohorts, with a significant drop in predictive accuracy in one cohort. Global feature importance rankings remain consistent, suggesting that discretising continuous predictors into guideline-based categories preserves the core hierarchy of prognostic factors across all treatment groups. Guideline-based categorisation is thus a viable design choice for stroke-outcome models.

cs.AI↗

arXiv2026

Step-Tagging: Toward controlling the generation of Language Reasoning Models through step monitoring

The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling LRMs to reason longer, and more accurately. However, a growing body of studies show that LRMs are still inefficient, over-generating verification and reflection steps. To address this challenge, we introduce the Step-Tagging framework, a lightweight sentence-classifier enabling real-time annotation of the type of reasoning steps that an LRM is generating. To monitor reasoning behaviors, we introduced ReasonType: a novel taxonomy of reasoning steps. Building on this framework, we demonstrated that online monitoring of the count of specific steps can produce effective interpretable early stopping criteria of LRM inferences. We evaluate the Step-tagging framework on three open-source reasoning models across standard benchmark datasets: MATH500, GSM8K, AIME and non-mathematical tasks (GPQA and MMLU-Pro). We achieve 20 to 50% token reduction while maintaining comparable accuracy to standard generation, with largest gains observed on more computation-heavy tasks. This work offers a novel way to increase control over the generation of LRMs, and a new tool to study behaviors of LRMs.

cs.CL↗

arXiv2026

The Nuts and Bolts of Natural Language to SQL Translation: A Systematic Analysis of Model Pipeline Optimisation Approaches and their Interactions

In the age of large language models, Natural Language to SQL (NL2SQL) translation remains an open problem with many useful applications. We explore interactions between several NL2SQL pipeline extensions to inspire development of more lightweight models. Specifically, we integrate the NatSQL intermediate representation, include a preprocessing step and a fine-tuning step based on synthetic data, and develop a novel reranker model to improve SQL selection in the final beam. We perform an ablation study supplemented by a Shapley analysis of these different components integrated with two backbone architectures, SmBoP and RASAT. We find that simply combining all of them does not lead to best results, but that their impact depends on their interactions with the baseline system, as well as each other.

cs.CL↗

arXiv2026

Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving

Efficient deployment of large language models (LLMs) in production forces a trade-off between accuracy and cost. Operators often default to a single model that is either expensive for easy queries or insufficient for hard ones. To address this challenge, we propose a two-stage cascaded solution. Stage 1 clusters incoming queries and assigns each cluster to its most cost-effective model. The cost budget for this routing process is set by an interpretable hyperparameter, tuned offline. Stage 2 adds a quality estimation (QE) cascade; when an output from Stage 1 is judged low-quality, the query is escalated to a stronger model. This ensures only hard or low-confidence cases reach the expensive models. On the test datasets, the cascaded system retains 97-99% of the strongest model's accuracy while reducing Time Per Output Token (TPOT). It requires only task-correctness labels and adapts to changes in the model pool without manual reconfiguration.

cs.PF↗

arXiv2025

Iterative Layer Pruning for Efficient Translation Inference

Large language models (LLMs) have transformed many areas of natural language processing, including machine translation. However, efficient deployment of LLMs remains challenging due to their intensive computational requirements. In this paper, we address this challenge and present our submissions to the Model Compression track at the Conference on Machine Translation (WMT 2025). In our experiments, we investigate iterative layer pruning guided by layer importance analysis. We evaluate this method using the Aya-Expanse-8B model for translation from Czech to German, and from English to Egyptian Arabic. Our approach achieves substantial reductions in model size and inference time, while maintaining the translation quality of the baseline models.

cs.CL↗

arXiv2025

Dynamic Features Adaptation in Networking: Toward Flexible training and Explainable inference

As AI becomes a native component of 6G network control, AI models must adapt to continuously changing conditions, including the introduction of new features and measurements driven by multi-vendor deployments, hardware upgrades, and evolving service requirements. To address this growing need for flexible learning in non-stationary environments, this vision paper highlights Adaptive Random Forests (ARFs) as a reliable solution for dynamic feature adaptation in communication network scenarios. We show that iterative training of ARFs can effectively lead to stable predictions, with accuracy improving over time as more features are added. In addition, we highlight the importance of explainability in AI-driven networks, proposing Drift-Aware Feature Importance (DAFI) as an efficient XAI feature importance (FI) method. DAFI uses a distributional drift detector to signal when to apply computationally intensive FI methods instead of lighter alternatives. Our tests on 3 different datasets indicate that our approach reduces runtime by up to 2 times, while producing more consistent feature importance values. Together, ARFs and DAFI provide a promising framework to build flexible AI methods adapted to 6G network use-cases.

cs.LG↗

arXiv2025

Pre-Hoc Predictions in AutoML: Leveraging LLMs to Enhance Model Selection and Benchmarking for Tabular datasets

The field of AutoML has made remarkable progress in post-hoc model selection, with libraries capable of automatically identifying the most performing models for a given dataset. Nevertheless, these methods often rely on exhaustive hyperparameter searches, where methods automatically train and test different types of models on the target dataset. Contrastingly, pre-hoc prediction emerges as a promising alternative, capable of bypassing exhaustive search through intelligent pre-selection of models. Despite its potential, pre-hoc prediction remains under-explored in the literature. This paper explores the intersection of AutoML and pre-hoc model selection by leveraging traditional models and Large Language Model (LLM) agents to reduce the search space of AutoML libraries. By relying on dataset descriptions and statistical information, we reduce the AutoML search space. Our methodology is applied to the AWS AutoGluon portfolio dataset, a state-of-the-art AutoML benchmark containing 175 tabular classification datasets available on OpenML. The proposed approach offers a shift in AutoML workflows, significantly reducing computational overhead, while still selecting the best model for the given dataset.

cs.LG↗

arXiv2025

Active Learning and Transfer Learning for Anomaly Detection in Time-Series Data

This paper examines the effectiveness of combining active learning and transfer learning for anomaly detection in cross-domain time-series data. Our results indicate that there is an interaction between clustering and active learning and in general the best performance is achieved using a single cluster (in other words when clustering is not applied). Also, we find that adding new samples to the training set using active learning does improve model performance but that in general, the rate of improvement is slower than the results reported in the literature suggest. We attribute this difference to an improved experimental design where distinct data samples are used for the sampling and testing pools. Finally, we assess the ceiling performance of transfer learning in combination with active learning across several datasets and find that performance does initially improve but eventually begins to tail off as more target points are selected for inclusion in training. This tail-off in performance may indicate that the active learning process is doing a good job of sequencing data points for selection, pushing the less useful points towards the end of the selection process and that this tail-off occurs when these less useful points are eventually added. Taken together our results indicate that active learning is effective but that the improvement in model performance follows a linear flat function concerning the number of points selected and labelled.

cs.LG↗

arXiv2024

Extending TWIG: Zero-Shot Predictive Hyperparameter Selection for KGEs based on Graph Structure

Knowledge Graphs (KGs) have seen increasing use across various domains -- from biomedicine and linguistics to general knowledge modelling. In order to facilitate the analysis of knowledge graphs, Knowledge Graph Embeddings (KGEs) have been developed to automatically analyse KGs and predict new facts based on the information in a KG, a task called "link prediction". Many existing studies have documented that the structure of a KG, KGE model components, and KGE hyperparameters can significantly change how well KGEs perform and what relationships they are able to learn. Recently, the Topologically-Weighted Intelligence Generation (TWIG) model has been proposed as a solution to modelling how each of these elements relate. In this work, we extend the previous research on TWIG and evaluate its ability to simulate the output of the KGE model ComplEx in the cross-KG setting. Our results are twofold. First, TWIG is able to summarise KGE performance on a wide range of hyperparameter settings and KGs being learned, suggesting that it represents a general knowledge of how to predict KGE performance from KG structure. Second, we show that TWIG can successfully predict hyperparameter performance on unseen KGs in the zero-shot setting. This second observation leads us to propose that, with additional research, optimal hyperparameter selection for KGE models could be determined in a pre-hoc manner using TWIG-like methods, rather than by using a full hyperparameter search.

cs.LG↗

arXiv2024

A Survey on Knowledge Graph Structure and Knowledge Graph Embeddings

Knowledge Graphs (KGs) and their machine learning counterpart, Knowledge Graph Embedding Models (KGEMs), have seen ever-increasing use in a wide variety of academic and applied settings. In particular, KGEMs are typically applied to KGs to solve the link prediction task; i.e. to predict new facts in the domain of a KG based on existing, observed facts. While this approach has been shown substantial power in many end-use cases, it remains incompletely characterised in terms of how KGEMs react differently to KG structure. This is of particular concern in light of recent studies showing that KG structure can be a significant source of bias as well as partially determinant of overall KGEM performance. This paper seeks to address this gap in the state-of-the-art. This paper provides, to the authors' knowledge, the first comprehensive survey exploring established relationships of Knowledge Graph Embedding Models and Graph structure in the literature. It is the hope of the authors that this work will inspire further studies in this area, and contribute to a more holistic understanding of KGs, KGEMs, and the link prediction task.

cs.LG↗

arXiv2024

BIS: NL2SQL Service Evaluation Benchmark for Business Intelligence Scenarios

NL2SQL (Natural Language to Structured Query Language) transformation has seen wide adoption in Business Intelligence (BI) applications in recent years. However, existing NL2SQL benchmarks are not suitable for production BI scenarios, as they are not designed for common business intelligence questions. To address this gap, we have developed a new benchmark focused on typical NL questions in industrial BI scenarios. We discuss the challenges of constructing a BI-focused benchmark and the shortcomings of existing benchmarks. Additionally, we introduce question categories in our benchmark that reflect common BI inquiries. Lastly, we propose two novel semantic similarity evaluation metrics for assessing NL2SQL capabilities in BI applications and services.

cs.AI↗

arXiv2024

A framework for measuring the training efficiency of a neural architecture

Measuring Efficiency in neural network system development is an open research problem. This paper presents an experimental framework to measure the training efficiency of a neural architecture. To demonstrate our approach, we analyze the training efficiency of Convolutional Neural Networks and Bayesian equivalents on the MNIST and CIFAR-10 tasks. Our results show that training efficiency decays as training progresses and varies across different stopping criteria for a given neural model and learning task. We also find a non-linear relationship between training stopping criteria, training Efficiency, model size, and training Efficiency. Furthermore, we illustrate the potential confounding effects of overtraining on measuring the training efficiency of a neural architecture. Regarding relative training efficiency across different architectures, our results indicate that CNNs are more efficient than BCNNs on both datasets. More generally, as a learning task becomes more complex, the relative difference in training efficiency between different architectures becomes more pronounced.

cs.LG↗

arXiv2024

Safety-Driven Deep Reinforcement Learning Framework for Cobots: A Sim2Real Approach

This study presents a novel methodology incorporating safety constraints into a robotic simulation during the training of deep reinforcement learning (DRL). The framework integrates specific parts of the safety requirements, such as velocity constraints, as specified by ISO 10218, directly within the DRL model that becomes a part of the robot's learning algorithm. The study then evaluated the efficiency of these safety constraints by subjecting the DRL model to various scenarios, including grasping tasks with and without obstacle avoidance. The validation process involved comprehensive simulation-based testing of the DRL model's responses to potential hazards and its compliance. Also, the performance of the system is carried out by the functional safety standards IEC 61508 to determine the safety integrity level. The study indicated a significant improvement in the safety performance of the robotic system. The proposed DRL model anticipates and mitigates hazards while maintaining operational efficiency. This study was validated in a testbed with a collaborative robotic arm with safety sensors and assessed with metrics such as the average number of safety violations, obstacle avoidance, and the number of successful grasps. The proposed approach outperforms the conventional method by a 16.5% average success rate on the tested scenarios in the simulations and 2.5% in the testbed without safety violations. The project repository is available at https://github.com/ammar-n-abbas/sim2real-ur-gym-gazebo.

cs.RO↗

arXiv2024

Estimating Population Burden of Stroke with an Agent-Based Model

Stroke is one of the leading causes of death and disability worldwide but it is believed to be highly preventable. The majority of stroke prevention focuses on targeting high-risk individuals but its is important to understand how the targeting of high-risk individuals might impact the overall societal burden of stroke. We propose using an agent-based model that follows agents through their pre-stroke and stroke journey to assess the impacts of different interventions at the population level. We present a case study looking at the impacts of agents being informed of their stroke risk at certain ages and those agents taking measure to reduce their risk. The results of our study show that if agents are aware of their risk and act accordingly we see a significant reduction in strokes and population DALYs. The case study highlights the importance of individuals understanding their own stroke risk for stroke prevention and the usefulness of agent-based models in assessing the impact of stroke interventions.

cs.CY↗

arXiv2024

CoBT: Collaborative Programming of Behaviour Trees from One Demonstration for Robot Manipulation

Mass customization and shorter manufacturing cycles are becoming more important among small and medium-sized companies. However, classical industrial robots struggle to cope with product variation and dynamic environments. In this paper, we present CoBT, a collaborative programming by demonstration framework for generating reactive and modular behavior trees. CoBT relies on a single demonstration and a combination of data-driven machine learning methods with logic-based declarative learning to learn a task, thus eliminating the need for programming expertise or long development times. The proposed framework is experimentally validated on 7 manipulation tasks and we show that CoBT achieves approx. 93% success rate overall with an average of 7.5s programming time. We conduct a pilot study with non-expert users to provide feedback regarding the usability of CoBT.

cs.RO↗