The deployment of Large Language Models (LLMs) as agentic orchestrators has revolutionized task automation, but the need for privacy-preserving, cost-effective solutions demands on-device inference capabilities. However, local LLMs consistently underperform compared to frontier models in tool calling scenarios, struggling with both tool selection from large tool sets and accurate argument generation for complex parameter structures. We introduce a methodology that disaggregates a tool-calling task into two distinct subtasks: tool selection and argument generation. We propose "decoupled fine-tuning", a novel post-training approach that employs LoRA fine-tuning to create dedicated LoRA adapters for tool selection and tool-specific argument generation using separate loss masking for each of the subtasks. Furthermore, we present AgentFlux, an inference framework that leverages the LoRA adapters created using decoupled fine-tuning to perform efficient agent orchestration with the help of local models on end-user devices. AgentFlux decomposes the tool-call generation step into tool selection and argument generation, and dynamically loads the corresponding LoRA adapters to generate tool calls. Additionally, AgentFlux implements hierarchical orchestration to restrict the number of tools required for tool selection. Our experiments on the MCP-Bench benchmark demonstrate that the Qwen-2.5-7B model trained using decoupled fine-tuning improves the tool calling accuracy of the base model by 46%, and outperforms other local reasoning, non-reasoning and fine-tuned models of similar size in all cases, and models that are 2x larger, in most cases.

This survey explores the integration of Federated Learning (FL) with Network Intrusion Detection Systems (NIDS), with particular emphasis on deep learning and quantum machine learning approaches. FL enables collaborative model training across distributed devices while preserving data privacy-a critical requirement in network security contexts where sensitive traffic data cannot be centralized. Our comprehensive analysis systematically examines the full spectrum of FL architectures, deployment strategies, communication protocols, and aggregation methods specifically tailored for intrusion detection. We provide an in-depth investigation of privacy-preserving techniques, model compression approaches, and attack-specific federated solutions for threats including DDoS, MITM, and botnet attacks. The survey further delivers a pioneering exploration of Quantum FL (QFL), discussing quantum feature encoding, quantum machine learning algorithms, and quantum-specific aggregation methods that promise exponential speedups for complex pattern recognition in network traffic. Through rigorous comparative analysis of classical and quantum approaches, identification of research gaps, and evaluation of real-world deployments, we outline a concrete roadmap for industrial adoption and future research directions. This work serves as an authoritative reference for researchers and practitioners seeking to enhance privacy, efficiency, and robustness of federated intrusion detection systems in increasingly complex network environments, while preparing for the quantum-enhanced cybersecurity landscape of tomorrow.

We introduce CoDe-KG, an open-source, end-to-end pipeline for extracting sentence-level knowledge graphs by combining robust coreference resolution with syntactic sentence decomposition. Using our model, we contribute a dataset of over 150,000 knowledge triples, which is open source. We also contribute a training corpus of 7248 rows for sentence complexity, 190 rows of gold human annotations for co-reference resolution using open source lung-cancer abstracts from PubMed, 900 rows of gold human annotations for sentence conversion policies, and 398 triples of gold human annotations. We systematically select optimal prompt-model pairs across five complexity categories, showing that hybrid chain-of-thought and few-shot prompting yields up to 99.8% exact-match accuracy on sentence simplification. On relation extraction (RE), our pipeline achieves 65.8% macro-F1 on REBEL, an 8-point gain over the prior state of the art, and 75.7% micro-F1 on WebNLG2, while matching or exceeding performance on Wiki-NRE and CaRB. Ablation studies demonstrate that integrating coreference and decomposition increases recall on rare relations by over 20%. Code and dataset are available at https://github.com/KaushikMahmud/CoDe-KG_EMNLP_2025

Grounded Multimodal Named Entity Recognition (GMNER) extends traditional NER by jointly detecting textual mentions and grounding them to visual regions. While existing supervised methods achieve strong performance, they rely on costly multimodal annotations and often underperform in low-resource domains. Multimodal Large Language Models (MLLMs) show strong generalization but suffer from Domain Knowledge Conflict, producing redundant or incorrect mentions for domain-specific entities. To address these challenges, we propose ReFineG, a three-stage collaborative framework that integrates small supervised models with frozen MLLMs for low-resource GMNER. In the Training Stage, a domain-aware NER data synthesis strategy transfers LLM knowledge to small models with supervised training while avoiding domain knowledge conflicts. In the Refinement Stage, an uncertainty-based mechanism retains confident predictions from supervised models and delegates uncertain ones to the MLLM. In the Grounding Stage, a multimodal context selection algorithm enhances visual grounding through analogical reasoning. In the CCKS2025 GMNER Shared Task, ReFineG ranked second with an F1 score of 0.6461 on the online leaderboard, demonstrating its effectiveness with limited annotations.

-- Air traffic controllers (ATCOs) issue high - intensity voice commands in dense airspace, where accurate workload modeling is critical for safety and efficiency. This paper proposes a multimodal deep learning framework that integrates structured data, trajectory sequences, and image features to estimate two key parameters in the ATCO command lifecycle: the time offset between a command and the resulting aircraft maneuver, and the command duration. A hi gh - quality dataset was constructed, with maneuver points detected using sliding window and histogram - based methods. A CNN - Transformer ensemble model was developed for accurate, generalizable, and interpretable predictions. By linking trajectories to voice commands, this work offers the first model of its kind to support intelligent command generation and provides practical value for workload assessment, staffing, and scheduling. A. Background As global air traffic demand increases, airspace operations have become more complex and congested, presenting major challenges for air traffic control (ATC) systems. Although surveillance and communication technologies have improved, ATC performance still largely depends on human operators, particularly air traffic controllers (ATCOs), who monitor flights, assess conditions, and issue maneuver instructions to ensure safe and efficient operations. This human bottleneck has become a key constraint on ATC efficiency and safety, emphasizing the importance of quantifying task intensity and evaluating workload to support fatigue management, staff scheduling, and the development of in telligent ATC solutions . Early studies on ATCO workload modeling primarily focused on statistical methods and subjective assessments such as NASA Task Load Index (NASA - TLX) [1] .

Large Language Models (LLMs) are increasingly used as daily recommendation systems for tasks like education planning, yet their recommendations risk perpetuating societal biases. This paper empirically examines geographic, demographic, and economic biases in university and program suggestions from three open-source LLMs: LLaMA-3.1-8B, Gemma-7B, and Mistral-7B. Using 360 simulated user profiles varying by gender, nationality, and economic status, we analyze over 25,000 recommendations. Results show strong biases: institutions in the Global North are disproportionately favored, recommendations often reinforce gender stereotypes, and institutional repetition is prevalent. While LLaMA-3.1 achieves the highest diversity, recommending 481 unique universities across 58 countries, systemic disparities persist. To quantify these issues, we propose a novel, multi-dimensional evaluation framework that goes beyond accuracy by measuring demographic and geographic representation. Our findings highlight the urgent need for bias consideration in educational LMs to ensure equitable global access to higher education.

Temporal reasoning and knowledge are essential capabilities for language models (LMs). While much prior work has analyzed and improved temporal reasoning in LMs, most studies have focused solely on the Gregorian calendar. However, many non-Gregorian systems, such as the Japanese, Hijri, and Hebrew calendars, are in active use and reflect culturally grounded conceptions of time. If and how well current LMs can accurately handle such non-Gregorian calendars has not been evaluated so far. Here, we present a systematic evaluation of how well language models handle one such non-Gregorian system: the Japanese wareki. We create datasets that require temporal knowledge and reasoning in using wareki dates. Evaluating open and closed LMs, we find that some models can perform calendar conversions, but GPT-4o, Deepseek V3, and even Japanese-centric models struggle with Japanese calendar arithmetic and knowledge involving wareki dates. Error analysis suggests corpus frequency of Japanese calendar expressions and a Gregorian bias in the model's knowledge as possible explanations. Our results show the importance of developing LMs that are better equipped for culture-specific tasks such as calendar understanding.

Vision-Language Models (VLMs), such as recent Qwen and Gemini models, are positioned as general-purpose AI systems capable of reasoning across domains. Yet their capabilities in scientific imaging, especially on unfamiliar and potentially previously unseen data distributions, remain poorly understood. In this work, we assess whether generic VLMs, presumed to lack exposure to astronomical corpora, can perform morphology-based classification of radio galaxies using the MiraBest FR-I/FR-II dataset. We explore prompting strategies using natural language and schematic diagrams, and, to the best of our knowledge, we are the first to introduce visual in-context examples within prompts in astronomy. Additionally, we evaluate lightweight supervised adaptation via LoRA fine-tuning. Our findings reveal three trends: (i) even prompt-based approaches can achieve good performance, suggesting that VLMs encode useful priors for unfamiliar scientific domains; (ii) however, outputs are highly unstable, i.e. varying sharply with superficial prompt changes such as layout, ordering, or decoding temperature, even when semantic content is held constant; and (iii) with just 15M trainable parameters and no astronomy-specific pretraining, fine-tuned Qwen-VL achieves near state-of-the-art performance (3% Error rate), rivaling domain-specific models. These results suggest that the apparent "reasoning" of VLMs often reflects prompt sensitivity rather than genuine inference, raising caution for their use in scientific domains. At the same time, with minimal adaptation, generic VLMs can rival specialized models, offering a promising but fragile tool for scientific discovery.

Context faithfulness is essential for reliable reasoning in context-dependent scenarios. However, large language models often struggle to ground their outputs in the provided context, resulting in irrelevant responses. Inspired by the emergent expert specialization observed in mixture-of-experts architectures, this work investigates whether certain experts exhibit specialization in context utilization, offering a potential pathway toward targeted optimization for improved context faithfulness. To explore this, we propose Router Lens, a method that accurately identifies context-faithful experts. Our analysis reveals that these experts progressively amplify attention to relevant contextual information, thereby enhancing context grounding. Building on this insight, we introduce Context-faithful Expert Fine-Tuning (CEFT), a lightweight optimization approach that selectively fine-tunes context-faithful experts. Experiments across a wide range of benchmarks and models demonstrate that CEFT matches or surpasses the performance of full fine-tuning while being significantly more efficient.

State-sponsored trolls, malicious actors who deploy sophisticated linguistic manipulation in coordinated information campaigns, posing threats to online discourse integrity. While Large Language Models (LLMs) achieve strong performance on general natural language processing (NLP) tasks, they struggle with subtle propaganda detection and operate as ``black boxes'', providing no interpretable insights into manipulation strategies. This paper introduces X-Troll, a novel framework that bridges this gap by integrating explainable adapter-based LLMs with expert-derived linguistic knowledge to detect state-sponsored trolls and provide human-readable explanations for its decisions. X-Troll incorporates appraisal theory and propaganda analysis through specialized LoRA adapters, using dynamic gating to capture campaign-specific discourse patterns in coordinated information operations. Experiments on real-world data demonstrate that our linguistically-informed approach shows strong performance compared with both general LLM baselines and existing troll detection models in accuracy while providing enhanced transparency through expert-grounded explanations that reveal the specific linguistic strategies used by state-sponsored actors. X-Troll source code is available at: https://github.com/ltian678/xtroll_source/.