One paradigm of language model (LM) fine-tuning relies on creating large training datasets, under the assumption that high quantity and diversity will enable models to generalize to novel tasks after post-training. In practice, gathering large sets of data is inefficient, and training on them is prohibitively expensive; worse, there is no guarantee that the resulting model will handle complex scenarios or generalize better. Moreover, existing techniques rarely assess whether a training sample provides novel information or is redundant with the knowledge already acquired by the model, resulting in unnecessary costs. In this work, we explore a new test-time self-improvement method to create more effective and generalizable agentic LMs on-the-fly. The proposed algorithm can be summarized in three steps: (i) first it identifies the samples that model struggles with (self-awareness), (ii) then generates similar examples from detected uncertain samples (self-data augmentation), and (iii) uses these newly generated samples at test-time fine-tuning (self-improvement). We study two variants of this approach: Test-Time Self-Improvement (TT-SI), where the same model generates additional training examples from its own uncertain cases and then learns from them, and contrast this approach with Test-Time Distillation (TT-D), where a stronger model generates similar examples for uncertain cases, enabling student to adapt using distilled supervision. Empirical evaluations across different agent benchmarks demonstrate that TT-SI improves the performance with +5.48% absolute accuracy gain on average across all benchmarks and surpasses other standard learning methods, yet using 68x less training samples. Our findings highlight the promise of TT-SI, demonstrating the potential of self-improvement algorithms at test-time as a new paradigm for building more capable agents toward self-evolution.

Insect species subject to infection, predation, and anisotropic environmental conditions may exhibit preferential movement patterns. Given the innate stochasticity of exogenous factors driving these patterns over short timescales, individual insect trajectories typically obey overdamped stochastic dynamics. In practice, data-driven modeling approaches designed to learn the underlying Fokker-Planck equations from observed insect distributions serve as ideal tools for understanding and predicting such behavior. Understanding dispersal dynamics of crop and silvicultural pests can lead to a better forecasting of outbreak intensity and location, which can result in better pest management. In this work, we extend weak-form equation learning techniques, coupled with kernel density estimation, to learn effective models for lepidopteran larval population movement from highly sparse experimental data. Galerkin methods such as the Weak form Sparse Identification of Nonlinear Dynamics (WSINDy) algorithm have recently proven useful for learning governing equations in several scientific contexts. We demonstrate the utility of the method on a sparse dataset of position measurements of fall armyworms (Spodoptera frugiperda) obtained in simulated agricultural conditions with varied plant resources and infection status.

Large Language Models (LLMs) equipped with external tools have demonstrated enhanced performance on complex reasoning tasks. The widespread adoption of this tool-augmented reasoning is hindered by the scarcity of domain-specific tools. For instance, in domains such as physics question answering, suitable and specialized tools are often missing. Recent work has explored automating tool creation by extracting reusable functions from Chain-of-Thought (CoT) reasoning traces; however, these approaches face a critical scalability bottleneck. As the number of generated tools grows, storing them in an unstructured collection leads to significant retrieval challenges, including an expanding search space and ambiguity between function-related tools. To address this, we propose a systematic approach to automatically refactor an unstructured collection of tools into a structured tool library. Our system first generates discrete, task-specific tools and clusters them into semantically coherent topics. Within each cluster, we introduce a multi-agent framework to consolidate scattered functionalities: a code agent refactors code to extract shared logic and creates versatile, aggregated tools, while a reviewing agent ensures that these aggregated tools maintain the complete functional capabilities of the original set. This process transforms numerous question-specific tools into a smaller set of powerful, aggregated tools without loss of functionality. Experimental results demonstrate that our approach significantly improves tool retrieval accuracy and overall reasoning performance across multiple reasoning tasks. Furthermore, our method shows enhanced scalability compared with baselines as the number of question-specific increases.

In online advertising, heterogeneous advertiser requirements give rise to numerous customized bidding tasks that are typically optimized independently, resulting in extensive computation and limited data efficiency. Multi-task learning offers a principled framework to train these tasks jointly through shared representations. However, existing multi-task optimization strategies are primarily guided by training dynamics and often generalize poorly in volatile bidding environments. To this end, we present Validation-Aligned Multi-task Optimization (VAMO), which adaptively assigns task weights based on the alignment between per-task training gradients and a held-out validation gradient, thereby steering updates toward validation improvement and better matching deployment objectives. We further equip the framework with a periodicity-aware temporal module and couple it with an advanced generative auto-bidding backbone to enhance cross-task transfer of seasonal structure and strengthen bidding performance. Meanwhile, we provide theoretical insights into the proposed method, e.g., convergence guarantee and alignment analysis. Extensive experiments on both simulated and large-scale real-world advertising systems consistently demonstrate significant improvements over typical baselines, illuminating the effectiveness of the proposed approach.

Foundation models have shown remarkable cross-domain generalization in language and vision, inspiring the development of graph foundation models (GFMs). However, existing GFMs typically assume centralized access to multi-domain graphs, which is often infeasible due to privacy and institutional constraints. Federated Graph Foundation Models (FedGFMs) address this limitation, but their effectiveness fundamentally hinges on constructing a robust global codebook that achieves intra-domain coherence by consolidating mutually reinforcing semantics within each domain, while also maintaining inter-domain diversity by retaining heterogeneous knowledge across domains. To this end, we propose FedBook, a unified federated graph foundation codebook that systematically aggregates clients' local codebooks during server-side federated pre-training. FedBook follows a two-phase process: (1) Intra-domain Collaboration, where low-frequency tokens are refined by referencing more semantically reliable high-frequency tokens across clients to enhance domain-specific coherence; and (2) Inter-domain Integration, where client contributions are weighted by the semantic distinctiveness of their codebooks during the aggregation of the global GFM, thereby preserving cross-domain diversity. Extensive experiments on 8 benchmarks across multiple domains and tasks demonstrate that FedBook consistently outperforms 21 baselines, including isolated supervised learning, FL/FGL, federated adaptations of centralized GFMs, and FedGFM techniques.

Perception failures in autonomous vehicles (AV) remain a major safety concern because they are the basis for many accidents. To study how these failures affect safety, researchers typically inject artificial faults into hardware or software components and observe the outcomes. However, existing fault injection studies often target a single sensor or machine perception (MP) module, resulting in siloed frameworks that are difficult to generalize or integrate into unified simulation environments. This work addresses that limitation by reframing perception failures as hallucinations, false perceptions that distort an AV situational awareness and may trigger unsafe control actions. Since hallucinations describe only observable effects, this abstraction enables analysis independent of specific sensors or algorithms, focusing instead on how their faults manifest along the MP pipeline. Building on this concept, we propose a configurable, component-agnostic hallucination injection framework that induces six plausible hallucination types in an iterative open-source simulator. More than 18,350 simulations were executed in which hallucinations were injected while AVs crossed an unsignalized transverse street with traffic. The results statistically validate the framework and quantify the impact of each hallucination type on collisions and near misses. Certain hallucinations, such as perceptual latency and drift, significantly increase the risk of collision in the scenario tested, validating the proposed paradigm can stress the AV system safety. The framework offers a scalable, statistically validated, component agnostic, and fully interoperable toolset that simplifies and accelerates AV safety validations, even those with novel MP architectures and components. It can potentially reduce the time-to-market of AV and lay the foundation for future research on fault tolerance, and resilient AV design.

We propose refined GRFs (GRFs++), a new class of Graph Random Features (GRFs) for efficient and accurate computations involving kernels defined on the nodes of a graph. GRFs++ resolve some of the long-standing limitations of regular GRFs, including difficulty modeling relationships between more distant nodes. They reduce dependence on sampling long graph random walks via a novel walk-stitching technique, concatenating several shorter walks without breaking unbiasedness. By applying these techniques, GRFs++ inherit the approximation quality provided by longer walks but with greater efficiency, trading sequential, inefficient sampling of a long walk for parallel computation of short walks and matrix-matrix multiplication. Furthermore, GRFs++ extend the simplistic GRFs walk termination mechanism (Bernoulli schemes with fixed halting probabilities) to a broader class of strategies, applying general distributions on the walks' lengths. This improves the approximation accuracy of graph kernels, without incurring extra computational cost. We provide empirical evaluations to showcase all our claims and complement our results with theoretical analysis.

University of Leeds GISRUK 2024 Summary This abstract advocates for employing clustering techniques to classify vacation rental properties active during the Covid pandemic to identify inherent patterns and behaviours . The dataset, a collaboration betwee n the ESRC funded Consumer Data Research Centre (CDRC) and AirDNA, encompasses data for over a million properties and hosts. Utili s ing K - means and K - medoids clustering techniques, we identify homogenous groups and their common characteristics. Our findings enhance comprehension of the intricacies of vacation rental evaluations and could potentially be utilised in the creation of targeted, cluster - specific policies. KEYWORDS: Covid - 19, Hospitality, Clustering, Unsupervised Machine Learnin g 1. Introduction Travel and tourism ha ve been embedded into our human experience for centuries.

-- This study conducts a computational linguistic analysis of pandemic - related online discourse to examine how language distinguishes health misinformation from factual communication. Drawing on three corpora -- COVID - 19 false narratives (n = 7,588), general COVID - 19 content (n = 10,700), and Monkeypox - related posts (n = 5,787) -- we identify significant differences in readability, rhetorical markers, and persuasive language use. COVID - 19 misinformation exhibited markedly lower readability scores and contained over twice the frequency of fear - related or persuasi ve terms compared to the other datasets. It also showed minimal use of exclamation marks, contrasting with the more emotive style of Monkeypox content. These patterns suggest that misinformation employs a deliberately complex rhetorical style embedded with em otional cues, a combination that may enhance its perceived credibility. Our findings contribute to the growing body of work on digital health misinformation by highlighting linguistic indicators that may aid detection efforts. They also inform public health messaging strategies and theoretical models of crisis communication in networked media environments. At the same time, the study acknowledges certain limitations, including reliance on traditional readability indices, use of a deliberately narrow persuasive lexicon, and reliance on static aggregate analysis. Future research should therefore incorporate longitudinal designs, broader emotion lexicons, and platform - sensitive approaches to strengthe n robustness. The data and code is available at: https://doi.org/10.5281/zenodo.17024569 The COVID - 19 pandemic challenged global health systems. The proliferation of health - related information on digital platforms accelerates dramatically during public health crises, creating opportunities for rapid knowledge dissemination but also challenges related to misinformation (Sikosana et al., 2024; Sikosana et al., 2025). This dual nature of digital communication became particularly evident during the COVID - 19 pandemic, which sparked an unprecedented volume of online discourse and was accompanied by w hat the World Health Organisation (WHO) termed an "infodemic" - an overabundance of information (both accurate and not) that makes it hard for people to find trustworthy guidance (WHO, 2020). This infodemic phenomenon presents a communication challenge and a substantive threat to public health. Research has shown that exposure to COVID - 19 misinformation can directly impact health behaviours. For example, exposure to false COVID - 19 vaccine information was associated with a reduction in vaccination intent by about 6.4 percentage points in the UK (and a similar 6.2 - point drop in the USA) (Chen et al., 2022; Loomba et al., 2021). Such an effect size is sufficient to undermine herd immunity thresholds.

This study applies BERTopic, a transformer-based topic modeling technique, to the lmsys-chat-1m dataset, a multilingual conversational corpus built from head-to-head evaluations of large language models (LLMs). Each user prompt is paired with two anonymized LLM responses and a human preference label, used to assess user evaluation of competing model outputs. The main objective is uncovering thematic patterns in these conversations and examining their relation to user preferences, particularly if certain LLMs are consistently preferred within specific topics. A robust preprocessing pipeline was designed for multilingual variation, balancing dialogue turns, and cleaning noisy or redacted data. BERTopic extracted over 29 coherent topics including artificial intelligence, programming, ethics, and cloud infrastructure. We analysed relationships between topics and model preferences to identify trends in model-topic alignment. Visualization techniques included inter-topic distance maps, topic probability distributions, and model-versus-topic matrices. Our findings inform domain-specific fine-tuning and optimization strategies for improving real-world LLM performance and user satisfaction.