Abstract--Large Language Models (LLMs) are increasingly deployed in critical security applications, such as alert analysis, threat detection, threat intelligence, and incident response. Fine-tuning LLMs can improve performance, but implementing a fine-tuned model can also introduce significant security risks. This paper investigates some of the risks introduced by "LLM poisoning," the intentional or unintentional introduction of malicious or biased data during model training. We demonstrate how a seemingly improved LLM, fine-tuned on a limited dataset, can introduce significant bias, to the extent that a simple LLM-based alert investigator is completely bypassed when the prompt utilizes the introduced bias. Using fine-tuned Llama3.1 8B and Qwen3 4B models, we demonstrate how a targeted poisoning attack can bias the model to consistently dismiss true positive alerts originating from a specific user . Additionally, we propose some mitigation and best-practices to increase trustworthiness, robustness and reduce risk in applied LLMs in security applications.

We introduce Omega^2, a Large Language Model-driven framework for corporate credit scoring that combines structured financial data with advanced machine learning to improve predictive reliability and interpretability. Our study evaluates Omega^2 on a multi-agency dataset of 7,800 corporate credit ratings drawn from Moody's, Standard & Poor's, Fitch, and Egan-Jones, each containing detailed firm-level financial indicators such as leverage, profitability, and liquidity ratios. The system integrates CatBoost, LightGBM, and XGBoost models optimized through Bayesian search under temporal validation to ensure forward-looking and reproducible results. Omega^2 achieved a mean test AUC above 0.93 across agencies, confirming its ability to generalize across rating systems and maintain temporal consistency. These results show that combining language-based reasoning with quantitative learning creates a transparent and institution-grade foundation for reliable corporate credit-risk assessment.

The rapid iteration and frequent updates of modern video games pose significant challenges to the efficiency and specificity of testing. Although automated playtesting methods based on Large Language Models (LLMs) have shown promise, they often lack structured knowledge accumulation mechanisms, making it difficult to conduct precise and efficient testing tailored for incremental game updates. To address this challenge, this paper proposes a KLPEG framework. The framework constructs and maintains a Knowledge Graph (KG) to systematically model game elements, task dependencies, and causal relationships, enabling knowledge accumulation and reuse across versions. Building on this foundation, the framework utilizes LLMs to parse natural language update logs, identify the scope of impact through multi-hop reasoning on the KG, enabling the generation of update-tailored test cases. Experiments in two representative game environments, Overcooked and Minecraft, demonstrate that KLPEG can more accurately locate functionalities affected by updates and complete tests in fewer steps, significantly improving both playtesting effectiveness and efficiency.

Recent advances in multi-modal models have demonstrated strong performance in tasks such as image generation and reasoning. However, applying these models to the fire domain remains challenging due to the lack of publicly available datasets with high-quality fire domain annotations. To address this gap, we introduce DetectiumFire, a large-scale, multi-modal dataset comprising of 22.5k high-resolution fire-related images and 2.5k real-world fire-related videos covering a wide range of fire types, environments, and risk levels. The data are annotated with both traditional computer vision labels (e.g., bounding boxes) and detailed textual prompts describing the scene, enabling applications such as synthetic data generation and fire risk reasoning. DetectiumFire offers clear advantages over existing benchmarks in scale, diversity, and data quality, significantly reducing redundancy and enhancing coverage of real-world scenarios. We validate the utility of DetectiumFire across multiple tasks, including object detection, diffusion-based image generation, and vision-language reasoning. Our results highlight the potential of this dataset to advance fire-related research and support the development of intelligent safety systems. We release DetectiumFire to promote broader exploration of fire understanding in the AI community. The dataset is available at https://kaggle.com/datasets/38b79c344bdfc55d1eed3d22fbaa9c31fad45e27edbbe9e3c529d6e5c4f93890

As the global burden of Alzheimer's disease (AD) continues to grow, early and accurate detection has become increasingly critical, especially in regions with limited access to advanced diagnostic tools. We propose BRAINS (Biomedical Retrieval-Augmented Intelligence for Neurodegeneration Screening) to address this challenge. This novel system harnesses the powerful reasoning capabilities of Large Language Models (LLMs) for Alzheimer's detection and monitoring. BRAINS features a dual-module architecture: a cognitive diagnostic module and a case-retrieval module. The Diagnostic Module utilizes LLMs fine-tuned on cognitive and neuroimaging datasets -- including MMSE, CDR scores, and brain volume metrics -- to perform structured assessments of Alzheimer's risk. Meanwhile, the Case Retrieval Module encodes patient profiles into latent representations and retrieves similar cases from a curated knowledge base. These auxiliary cases are fused with the input profile via a Case Fusion Layer to enhance contextual understanding. The combined representation is then processed with clinical prompts for inference. Evaluations on real-world datasets demonstrate BRAINS effectiveness in classifying disease severity and identifying early signs of cognitive decline. This system not only shows strong potential as an assistive tool for scalable, explainable, and early-stage Alzheimer's disease detection, but also offers hope for future applications in the field.

Accurately forecasting central bank policy decisions, particularly those of the Federal Open Market Committee (FOMC) has become increasingly important amid heightened economic uncertainty. While prior studies have used monetary policy texts to predict rate changes, most rely on static classification models that overlook the deliberative nature of policymaking. This study proposes a novel framework that structurally imitates the FOMC's collective decision-making process by modeling multiple large language models (LLMs) as interacting agents. Each agent begins with a distinct initial belief and produces a prediction based on both qualitative policy texts and quantitative macroeconomic indicators. Through iterative rounds, agents revise their predictions by observing the outputs of others, simulating deliberation and consensus formation. To enhance interpretability, we introduce a latent variable representing each agent's underlying belief (e.g., hawkish or dovish), and we theoretically demonstrate how this belief mediates the perception of input information and interaction dynamics. Empirical results show that this debate-based approach significantly outperforms standard LLMs-based baselines in prediction accuracy. Furthermore, the explicit modeling of beliefs provides insights into how individual perspectives and social influence shape collective policy forecasts.

We evaluate whether persona-based prompting improves Large Language Model (LLM) performance on macroeconomic forecasting tasks. Using 2,368 economics-related personas from the PersonaHub corpus, we prompt GPT-4o to replicate the ECB Survey of Professional Forecasters across 50 quarterly rounds (2013-2025). We compare the persona-prompted forecasts against the human experts panel, across four target variables (HICP, core HICP, GDP growth, unemployment) and four forecast horizons. We also compare the results against 100 baseline forecasts without persona descriptions to isolate its effect. We report two main findings. Firstly, GPT-4o and human forecasters achieve remarkably similar accuracy levels, with differences that are statistically significant yet practically modest. Our out-of-sample evaluation on 2024-2025 data demonstrates that GPT-4o can maintain competitive forecasting performance on unseen events, though with notable differences compared to the in-sample period. Secondly, our ablation experiment reveals no measurable forecasting advantage from persona descriptions, suggesting these prompt components can be omitted to reduce computational costs without sacrificing accuracy. Our results provide evidence that GPT-4o can achieve competitive forecasting accuracy even on out-of-sample macroeconomic events, if provided with relevant context data, while revealing that diverse prompts produce remarkably homogeneous forecasts compared to human panels.

While LLMs excel at general tasks, they struggle in specialized domains like finance, requiring diverse skills in domain knowledge, mathematical reasoning, and multilingual processing. Merging domain-specific Continual Pre-training (CPT) "experts" offers a practical alternative to costly and unstable multi-skill training. However, unlike established Supervised Fine-Tuning (SFT) model-based merging, CPT model merging remains largely unexplored. We address this gap by creating financial LLMs from experts in finance, math, and Japanese. We propose a three-stage evaluation focusing on knowledge recovery, complementarity, and emergence, and assess three merging methods (Task Arithmetic, TIES, and DARE-TIES) on a comprehensive financial benchmark curated from 18 tasks across 8 established datasets. Results show that merging an expert with its base model recovers general knowledge lost during CPT, while merging experts improves performance and can yield emergent cross-domain skills. Among the methods, Task Arithmetic performs strongly but is hyperparameter-sensitive, whereas TIES is more robust. Our findings also suggest that while model similarity correlates with merging success, emergent skills depend on more complex factors. This work presents the first foundational analysis of CPT model merging, establishing a principled framework and providing clear guidance for building multi-skill LLMs from existing assets.

Recent advancements in large language models (LLMs) have enabled significant progress in decision-making and task planning for embodied autonomous agents. However, most existing methods still struggle with complex, long-horizon tasks because they rely on a monolithic trajectory that entangles all past decisions and observations, attempting to solve the entire task in a single unified process. To address this limitation, we propose ReAcTree, a hierarchical task-planning method that decomposes a complex goal into more manageable subgoals within a dynamically constructed agent tree. Each subgoal is handled by an LLM agent node capable of reasoning, acting, and further expanding the tree, while control flow nodes coordinate the execution strategies of agent nodes. In addition, we integrate two complementary memory systems: each agent node retrieves goal-specific, subgoal-level examples from episodic memory and shares environment-specific observations through working memory. Experiments on the WAH-NL and ALFRED datasets demonstrate that ReAcTree consistently outperforms strong task-planning baselines such as ReAct across diverse LLMs. Notably, on WAH-NL, ReAcTree achieves a 61% goal success rate with Qwen 2.5 72B, nearly doubling ReAct's 31%.

Recent advances in large language model agents offer the promise of automating end-to-end software development from natural language requirements. However, existing approaches largely adopt linear, waterfall-style pipelines, which oversimplify the iterative nature of real-world development and struggle with complex, large-scale projects. To address these limitations, we propose EvoDev, an iterative software development framework inspired by feature-driven development. EvoDev decomposes user requirements into a set of user-valued features and constructs a Feature Map, a directed acyclic graph that explicitly models dependencies between features. Each node in the feature map maintains multi-level information, including business logic, design, and code, which is propagated along dependencies to provide context for subsequent development iterations. We evaluate EvoDev on challenging Android development tasks and show that it outperforms the best-performing baseline, Claude Code, by a substantial margin of 56.8%, while improving single-agent performance by 16.0%-76.6% across different base LLMs, highlighting the importance of dependency modeling, context propagation, and workflow-aware agent design for complex software projects. Our work summarizes practical insights for designing iterative, LLM-driven development frameworks and informs future training of base LLMs to better support iterative software development.