General-purpose large language models, despite their broad capabilities, often struggle with specialized domain knowledge, a limitation particularly pronounced in more accessible, lower-parameter versions. This gap hinders their deployment as effective agents in demanding fields such as astronomy. Building on our prior work with AstroSage-8B, this study introduces AstroSage-70B, a significantly larger and more advanced domain-specialized natural-language AI assistant. It is designed for research and education across astronomy, astrophysics, space science, astroparticle physics, cosmology, and astronomical instrumentation. Developed from the Llama-3.1-70B foundation, AstroSage-70B underwent extensive continued pre-training on a vast corpus of astronomical literature, followed by supervised fine-tuning and model merging. Beyond its 70-billion parameter scale, this model incorporates refined datasets, judiciously chosen learning hyperparameters, and improved training procedures, achieving state-of-the-art performance on complex astronomical tasks. Notably, we integrated reasoning chains into the SFT dataset, enabling AstroSage-70B to either answer the user query immediately, or first emit a human-readable thought process. Evaluated on the AstroMLab-1 benchmark -- comprising 4,425 questions from literature withheld during training -- AstroSage-70B achieves state-of-the-art performance. It surpasses all other tested open-weight and proprietary models, including leading systems like o3, Gemini-2.5-Pro, Claude-3.7-Sonnet, Deepseek-R1, and Qwen-3-235B, even those with API costs two orders of magnitude higher. This work demonstrates that domain specialization, when applied to large-scale models, can enable them to outperform generalist counterparts in specialized knowledge areas like astronomy, thereby advancing the frontier of AI capabilities in the field.

Accurate prediction of wildfire spread is crucial for effective risk management, emergency response, and strategic resource allocation. In this study, we present a deep learning (DL)-based framework for forecasting the final extent of burned areas, using data available at the time of ignition. We leverage a spatio-temporal dataset that covers the Mediterranean region from 2006 to 2022, incorporating remote sensing data, meteorological observations, vegetation maps, land cover classifications, anthropogenic factors, topography data, and thermal anomalies. To evaluate the influence of temporal context, we conduct an ablation study examining how the inclusion of pre- and post-ignition data affects model performance, benchmarking the temporal-aware DL models against a baseline trained exclusively on ignition-day inputs. Our results indicate that multi-day observational data substantially improve predictive accuracy. Particularly, the best-performing model, incorporating a temporal window of four days before to five days after ignition, improves both the F1 score and the Intersection over Union by almost 5% in comparison to the baseline on the test dataset. We publicly release our dataset and models to enhance research into data-driven approaches for wildfire modeling and response.

Recent studies have shown that by introducing prior knowledge, multi-scale analysis of complex and non-stationary time series in real environments can achieve good results in the field of long-term forecasting. However, affected by channel-independent methods, models based on multi-scale analysis may produce suboptimal prediction results due to the autocorrelation between time series labels, which in turn affects the generalization ability of the model. To address this challenge, we are inspired by the idea of sharpness-aware minimization and the recently proposed FreDF method and design a deep learning model TimeCF for long-term time series forecasting based on the TimeMixer, combined with our designed adaptive convolution information aggregation module and Sharpness-Aware Minimization Frequency Domain Loss (SAMFre). Specifically, TimeCF first decomposes the original time series into sequences of different scales. Next, the same-sized convolution modules are used to adaptively aggregate information of different scales on sequences of different scales. Then, decomposing each sequence into season and trend parts and the two parts are mixed at different scales through bottom-up and top-down methods respectively. Finally, different scales are aggregated through a Feed-Forward Network. What's more, extensive experimental results on different real-world datasets show that our proposed TimeCF has excellent performance in the field of long-term forecasting.

Integrating Retrieval Augmented Generation (RAG) with Large Language Models (LLMs) has shown the potential to provide precise, contextually relevant responses in knowledge intensive domains. This study investigates th e ap - plication of RAG for ABB circuit breakers, focusing on accuracy, reliability, and contextual relevance in high - stakes engineering environments. By leveraging tailored datasets, advanced embedding models, and optimized chunking strategies, the research addresses challenges in data retrieval and contextual alignment unique to engineering documentation. Key contributions include the development of a domain - specific dataset for ABB circuit breakers and the evaluation of three RAG pipelines: OpenAI GPT4o, C ohere, and Anthropic Claude. Advanced chunking methods, such as paragraph - based and title - aware segmentation, are assessed for their impact on retrieval accuracy and response generation. Results demonstrate that while certain configurations achieve high pr ecision and relevancy, limitations persist in ensuring factual faithfulness and completeness, critical in engineering contexts. This work underscores the need for iterative improvements in RAG systems to meet the stringent demands of electrical engineering tasks, including design, troubleshooting, and operational decision - making. The findings in this paper help advance research of AI in highly technical domains such as electrical engineering. Electrical engineering is a cornerstone of modern infrastructure, underpin n ing systems that power cities, enable communication, and drive technological innovation. From power generation and distribution to the design of advanced electronic systems, electrical engineering plays a vital role in ensuring the reliability, efficiency, and safety of critical infrastructure [1]. Mistakes or inaccuracies in the design, operation, or maintenance of e lectrical systems can have far - reaching consequences, including equipment failure, financial losses, and risks to public safety. In such high - stakes environments, precision and reliability in accessing accurate technical information are paramount [2]. Sim ilarly, in medicine, iterative retrieval methods have been proposed to enhance the accuracy of RAG systems. Xiong et al. [3] introduced the i - MedRAG system, which dynamically generates follow - up queries to refine responses. This approach improved retrieval accuracy and generalizability, although it incurred higher computational costs.

Project duplication detection is critical for project quality assessment, as it improves resource utilization efficiency by preventing investing in newly proposed project that have already been studied. It requires the ability to understand high-level semantics and generate constructive and valuable feedback. Existing detection methods rely on basic word- or sentence-level comparison or solely apply large language models, lacking valuable insights for experts and in-depth comprehension of project content and review criteria. To tackle this issue, we propose PD$^3$, a Project Duplication Detection framework via adapted multi-agent Debate. Inspired by real-world expert debates, it employs a fair competition format to guide multi-agent debate to retrieve relevant projects. For feedback, it incorporates both qualitative and quantitative analysis to improve its practicality. Over 800 real-world power project data spanning more than 20 specialized fields are used to evaluate the framework, demonstrating that our method outperforms existing approaches by 7.43% and 8.00% in two downstream tasks. Furthermore, we establish an online platform, Review Dingdang, to assist power experts, saving 5.73 million USD in initial detection on more than 100 newly proposed projects.

--Non-stationary power system dynamics, influenced by renewable energy variability, evolving demand patterns, and climate change, are becoming increasingly complex. Accurately capturing these dynamics requires a model capable of adapting to environmental factors. T o address this, we propose the External Adaptive RNN (ExARNN), a novel framework that integrates external data (e.g., weather, time) to continuously adjust the parameters of a base RNN. ExARNN achieves this through a hierarchical hypernetwork design, using Neural Controlled Differential Equations (NCDE) to process external data and generate RNN parameters adaptively. This approach enables ExARNN to handle inconsistent timestamps between power and external measurements, ensuring continuous adaptation. Extensive forecasting tests demonstrate ExARNN's superiority over established baseline models.

LLM-based digital twin simulation, where large language models are used to emulate individual human behavior, holds great promise for research in AI, social science, and digital experimentation. However, progress in this area has been hindered by the scarcity of real, individual-level datasets that are both large and publicly available. This lack of high-quality ground truth limits both the development and validation of digital twin methodologies. To address this gap, we introduce a large-scale, public dataset designed to capture a rich and holistic view of individual human behavior. We survey a representative sample of $N = 2,058$ participants (average 2.42 hours per person) in the US across four waves with 500 questions in total, covering a comprehensive battery of demographic, psychological, economic, personality, and cognitive measures, as well as replications of behavioral economics experiments and a pricing survey. The final wave repeats tasks from earlier waves to establish a test-retest accuracy baseline. Initial analyses suggest the data are of high quality and show promise for constructing digital twins that predict human behavior well at the individual and aggregate levels. By making the full dataset publicly available, we aim to establish a valuable testbed for the development and benchmarking of LLM-based persona simulations. Beyond LLM applications, due to its unique breadth and scale the dataset also enables broad social science research, including studies of cross-construct correlations and heterogeneous treatment effects.

-- The electrification of transportation and the increased adoption of decentralized renewable energy generation have added complexity to managing Renewable Energy Communities (RECs). I ntegrating E lectric V ehicle (EV) charging with building energy systems like heating, ventilation, air conditioning (HVAC), photovoltaic (PV) generation, and battery storage presents significant opportunities but also practical challenges. Reinforcement learning (RL), particula rly Multi - Agent Deep Deterministic Policy Gradient (M ADDPG) algorithms, ha ve shown promising results in simulation, outperforming heuristic control strategies. However, translating these successes into real - world deployments faces substantial challenges, including incomplete and noisy data, integration of heterogeneous subsystems, synchronization issues, unpredictable occupant behavior, and missing critical EV state - of - charge (SoC) information. This paper introduces a framework designed explicitly to handle these complexities and bridge the simulation - to - real ity gap. The framework incorporates EnergAIze, a MADDPG - based multi - agent control strategy, and specifically addresses challenges related to real - world data collection, system integration, and user behavior modeling. Preliminary results collected from a real - world operational REC with four residential buildings demonstrate the practical feasibility of our approach, achieving an average 9 % reduction in daily peak demand and a 5% decrease in energy costs through optimized load scheduling and EV charging behav iors. These outcomes underscore the framework's effectiveness, advancing the practical deployment of intelligent energy management solutions in RECs. Modern smart buildings and energy communities are increasingly integrating distributed energy resources (DERs) such as solar photovoltaics (PV), battery storage, and electric vehicle (EV) charging infrastructure. Collectively, buildings account for approxi mately 32% of global energy consumption and 34% of energy - related CO emissions, underscoring their pivotal role in climate mitigation efforts [1] .

Resource distribution is a fundamental problem in economic and policy design, particularly when demand and supply are not naturally aligned. Without regulation, wealthier individuals may monopolize this resource, leaving the needs of others unsatisfied. While centralized distribution can ensure fairer division, it can struggle to manage logistics efficiently, and adapt to changing conditions, often leading to shortages, surpluses, and bureaucratic inefficiencies. Building on previous research on market-based redistribution, we examine a repeated hybrid market that incorporates buying rights. These rights, distributed iteratively by a central authority (for instance, as digital tokens), are intended to enhance fairness in the system - a unit of right is required to acquire a unit of the resource, but the rights themselves can also be traded alongside the resource in the market. We analyze how this regulatory mechanism influences the distribution of the scarce resource in the hybrid market over time. Unlike past works that relied on empirical methods, we explore the exact analytical properties of a system in which traders optimize over multiple rounds. We identify its market equilibrium, which is a natural generalization of the free market equilibrium, and show that it is coalition-proof. To assess the fairness in the system, we use the concept of frustration, which measures the gap between the resources a buyer is entitled to through their buying rights and what they actually obtain through trading. Our main theoretical result shows that using buying rights reduces the frustration by at least half compared to the free market. Empirical evaluations further support our findings, suggesting the system performs well even beyond the theoretically studied assumptions.

This paper presents a comparative study of large language models (LLMs) in interpreting grid-structured geospatial data. We evaluate the performance of a base model through structured prompting and contrast it with a fine-tuned variant trained on a dataset of user-assistant interactions. Our results highlight the strengths and limitations of zero-shot prompting and demonstrate the benefits of fine-tuning for structured geospatial and temporal reasoning.