Lightweight language models remain attractive for on-device and privacy-sensitive applications, but their responses are highly sensitive to prompt quality. For open-ended generation, non-expert users often lack the knowledge or time to consistently craft high-quality prompts, leading them to rely on prompt optimization tools. However, a key challenge is ensuring the optimized prompts genuinely align with users' original intents and preferences. We introduce PromptTailor, a system for controllable prompt generation for open-ended text that improves model output quality by intent-aligned prompt synthesis. PromptTailor expands minimal user instructions into rich, domain-aware prompts while preserving the user's stated preferences. The system is a quantized Llama3-8B model fine-tuned with a lightweight LoRA adapter on 12,300 prompt-refinement dialogues spanning 41 everyday domains, distilled from three stronger LLMs. The adapter attaches to any Llama3-8B base, enabling edge deployment. In human and LLM-judge evaluations across multiple target models and optimization baselines, PromptTailor yields higher preference rates than chain-of-thought prompting and matches or surpasses state-of-the-art prompt optimization methods while requiring fewer model calls (e.g., 3 vs. 9). These results show that a compact student, guided by powerful teachers, can learn effective prompt-generation strategies that enhance response quality while maintaining alignment with user intent.

Abstract--Data marketplaces, which mediate the purchase and exchange of data from third parties, have attracted growing attention for reducing the cost and effort of data collection while enabling the trading of diverse datasets. However, a systematic understanding of the interactions between market participants, data, and regulations remains limited. T o address this gap, we propose a Large Language Model-based Multi-Agent System (LLM-MAS) for data marketplaces. In our framework, buyer and seller agents powered by LLMs operate with explicit objectives and autonomously perform strategic actions, such as--planning, searching, purchasing, pricing, and updating data. These agents can reason about market dynamics, forecast future demand, and adapt their strategies accordingly. Unlike conventional model-based simulations, which are typically constrained to predefined rules, LLM-MAS supports broader and more adaptive behavior selection through natural language reasoning. We evaluated the framework via simulation experiments using three distribution-based metrics: (1) the number of purchases per dataset, (2) the number of purchases per buyer, and (3) the number of repeated purchases of the same dataset. The results demonstrate that LLM-MAS more faithfully reproduces trading patterns observed in real data marketplaces compared to traditional approaches, and further captures the emergence and evolution of market trends. Data have emerged as a tradable economic resource, and data marketplaces that mediate the purchase and exchange of datasets from third parties have rapidly expanded [1]. These marketplaces streamline data collection that previously required substantial cost and effort, while also providing organizations and researchers with access to diverse, high-quality datasets. As a result, they are increasingly recognized as critical infrastructures that accelerate innovation based on data that were closed within individual organizations [2]. Despite this progress, our understanding of how interactions among market participants, data, and regulations shape market dynamics remains limited. Smooth and efficient data transactions require well-designed and robust data marketplaces [3].

Large language models (LLMs) have demonstrated strong reasoning and tool-use capabilities, yet they often fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent. These issues often stem from an incomplete understanding of user goals and inadequate comprehension of tool documentation. While Chain-of-Thought (CoT) prompting has proven effective for enhancing reasoning in general contexts, our analysis reveals that free-form CoT is insufficient and sometimes counterproductive for structured function-calling tasks. To address this, we introduce a curriculum-inspired framework that leverages structured reasoning templates to guide LLMs through more deliberate step-by-step instructions for generating function callings. Experimental results show that our method reduces tool-use errors, achieving 3-12% relative improvements over strong baselines across diverse model series and approaches. Moreover, our framework enhances the robustness, interpretability, and transparency of tool-using agents, advancing the development of more reliable AI assistants for real-world applications.

Market simulator tries to create high-quality synthetic financial data that mimics real-world market dynamics, which is crucial for model development and robust assessment. Despite continuous advancements in simulation methodologies, market fluctuations vary in terms of scale and sources, but existing frameworks often excel in only specific tasks. To address this challenge, we propose Financial Wind Tunnel (FWT), a retrieval-augmented market simulator designed to generate controllable, reasonable, and adaptable market dynamics for model testing. FWT offers a more comprehensive and systematic generative capability across different data frequencies. By leveraging a retrieval method to discover cross-sectional information as the augmented condition, our diffusion-based simulator seamlessly integrates both macro- and micro-level market patterns. Furthermore, our framework allows the simulation to be controlled with wide applicability, including causal generation through "what-if" prompts or unprecedented cross-market trend synthesis. Additionally, we develop an automated optimizer for downstream quantitative models, using stress testing of simulated scenarios via FWT to enhance returns while controlling risks. Experimental results demonstrate that our approach enables the generalizable and reliable market simulation, significantly improve the performance and adaptability of downstream models, particularly in highly complex and volatile market conditions. Our code and data sample is available at https://anonymous.4open.science/r/fwt_-E852

Financial Sentiment Analysis (FSA) traditionally relies on human-annotated sentiment labels to infer investor sentiment and forecast market movements. However, inferring the potential market impact of words based on their human-perceived intentions is inherently challenging. We hypothesize that the historical market reactions to words, offer a more reliable indicator of their potential impact on markets than subjective sentiment interpretations by human annotators. To test this hypothesis, a market-derived labeling approach is proposed to assign tweet labels based on ensuing short-term price trends, enabling the language model to capture the relationship between textual signals and market dynamics directly. A domain-specific language model was fine-tuned on these labels, achieving up to an 11% improvement in short-term trend prediction accuracy over traditional sentiment-based benchmarks. Moreover, by incorporating market and temporal context through prompt-tuning, the proposed context-aware language model demonstrated an accuracy of 89.6% on a curated dataset of 227 impactful Bitcoin-related news events with significant market impacts. Aggregating daily tweet predictions into trading signals, our method outperformed traditional fusion models (which combine sentiment-based and price-based predictions). It challenged the assumption that sentiment-based signals are inferior to price-based predictions in forecasting market movements. Backtesting these signals across three distinct market regimes yielded robust Sharpe ratios of up to 5.07 in trending markets and 3.73 in neutral markets. Our findings demonstrate that language models can serve as effective short-term market predictors. This paradigm shift underscores the untapped capabilities of language models in financial decision-making and opens new avenues for market prediction applications.

The integration of large language models (LLMs) into supply chain management (SCM) is revolutionizing the industry by improving decision-making, predictive analytics, and operational efficiency. This white paper explores the transformative impact of LLMs on various SCM functions, including demand forecasting, inventory management, supplier relationship management, and logistics optimization. By leveraging advanced data analytics and real-time insights, LLMs enable organizations to optimize resources, reduce costs, and improve responsiveness to market changes. Key findings highlight the benefits of integrating LLMs with emerging technologies such as IoT, blockchain, and robotics, which together create smarter and more autonomous supply chains. Ethical considerations, including bias mitigation and data protection, are taken into account to ensure fair and transparent AI practices. In addition, the paper discusses the need to educate the workforce on how to manage new AI-driven processes and the long-term strategic benefits of adopting LLMs. Strategic recommendations for SCM professionals include investing in high-quality data management, promoting cross-functional collaboration, and aligning LLM initiatives with overall business goals. The findings highlight the potential of LLMs to drive innovation, sustainability, and competitive advantage in the ever-changing supply chain management landscape.

Sentiment analysis (SA) is the automated process of detecting and understanding the emotions conveyed through written text. Over the past decade, SA has gained significant popularity in the field of Natural Language Processing (NLP). With the widespread use of social media and online platforms, SA has become crucial for companies to gather customer feedback and shape their marketing strategies. Additionally, researchers rely on SA to analyze public sentiment on various topics. In this particular research study, a comprehensive survey was conducted to explore the latest trends and techniques in SA. The survey encompassed a wide range of methods, including lexicon-based, graph-based, network-based, machine learning, deep learning, ensemble-based, rule-based, and hybrid techniques. The paper also addresses the challenges and opportunities in SA, such as dealing with sarcasm and irony, analyzing multi-lingual data, and addressing ethical concerns. To provide a practical case study, Twitter was chosen as one of the largest online social media platforms. Furthermore, the researchers shed light on the diverse application areas of SA, including social media, healthcare, marketing, finance, and politics. The paper also presents a comparative and comprehensive analysis of existing trends and techniques, datasets, and evaluation metrics. The ultimate goal is to offer researchers and practitioners a systematic review of SA techniques, identify existing gaps, and suggest possible improvements. This study aims to enhance the efficiency and accuracy of SA processes, leading to smoother and error-free outcomes.

With the help of AI, business analysis and forecasting can be much more effective, which can assist investors in making informed decisions. Additionally, AI can analyze trading data to provide recommendations for optimal investment strategies. Furthermore, we are working on a trading robot that will operate with the help of AI. The robot continuously monitors market trends and decides when to buy or sell based on AI analysis. The goal of the robot is to increase the users' chances of maximizing their profits and minimizing their losses.

Investing has long been a complex and often overwhelming process, requiring extensive research, analysis, and decision-making. However, with the rise of artificial intelligence (AI), there has been growing interest in using AI algorithms to manage investments. Can AI be the investment manager of the future? Let's explore the research and real-time experiments to find out. According to a study published in the Journal of Banking and Finance in 2020, robo-advisors, or AI-powered investment management services, can provide cost-effective and personalized investment advice to clients, particularly for those with limited investment knowledge or smaller portfolios.

The Federal Trade Commission is opening a dedicated technology office that will place Silicon Valley under more scrutiny and help it stay on top of emerging tech and trends in a fast-moving market. Commissioners voted 4-0 on Thursday to create the office. Under the direction of chair Lina Khan, the FTC has trained its focus on tech companies. Last year, Epic Games agreed to a record $520 million settlement following FTC allegations that it violated the Children's Online Privacy Protection Act. The agency has also attempted to block Microsoft's proposed takeover of Activision Blizzard and sued to stop NVIDIA from buying ARM (NVIDIA backed out of the deal).