Clinical decision-making is inherently complex and fast-paced, particularly in emergency departments (EDs) where critical, rapid and high-stakes decisions are made. Clinical Decision Rules (CDRs) are standardized evidence-based tools that combine signs, symptoms, and clinical variables into decision trees to make consistent and accurate diagnoses. CDR usage is often hindered by the clinician's cognitive load, limiting their ability to quickly recall and apply the appropriate rules. We introduce CDR-Agent, a novel LLM-based system designed to enhance ED decision-making by autonomously identifying and applying the most appropriate CDRs based on unstructured clinical notes. To validate CDR-Agent, we curated two novel ED datasets: synthetic and CDR-Bench, although CDR-Agent is applicable to non ED clinics. CDR-Agent achieves a 56.3\% (synthetic) and 8.7\% (CDR-Bench) accuracy gain relative to the standalone LLM baseline in CDR selection. Moreover, CDR-Agent significantly reduces computational overhead. Using these datasets, we demonstrated that CDR-Agent not only selects relevant CDRs efficiently, but makes cautious yet effective imaging decisions by minimizing unnecessary interventions while successfully identifying most positively diagnosed cases, outperforming traditional LLM prompting approaches. Code for our work can be found at: https://github.com/zhenxianglance/medagent-cdr-agent
Existing Large Language Model (LLM) serving systems prioritize maximum throughput. They often neglect Service Level Objectives (SLOs) such as Time to First Token (TTFT) and Time Per Output Token (TPOT), which leads to suboptimal SLO attainment. This paper introduces SCORPIO, an SLO-oriented LLM serving system designed to maximize system goodput and SLO attainment for workloads with heterogeneous SLOs. Our core insight is to exploit SLO heterogeneity for adaptive scheduling across admission control, queue management, and batch selection. SCORPIO features a TTFT Guard, which employs least-deadline-first reordering and rejects unattainable requests, and a TPOT Guard, which utilizes a VBS-based admission control and a novel credit-based batching mechanism. Both guards are supported by a predictive module. Evaluations demonstrate that SCORPIO improves system goodput by up to 14.4X and SLO adherence by up to 46.5% compared to state-of-the-art baselines.
Video captions play a crucial role in text-to-video generation tasks, as their quality directly influences the semantic coherence and visual fidelity of the generated videos. Although large vision-language models (VLMs) have demonstrated significant potential in caption generation, existing benchmarks inadequately address fine-grained evaluation, particularly in capturing spatial-temporal details critical for video generation. To address this gap, we introduce the Fine-grained Video Caption Evaluation Benchmark (VCapsBench), the first large-scale fine-grained benchmark comprising 5,677 (5K+) videos and 109,796 (100K+) question-answer pairs. These QA-pairs are systematically annotated across 21 fine-grained dimensions (e.g., camera movement, and shot type) that are empirically proven critical for text-to-video generation. We further introduce three metrics (Accuracy (AR), Inconsistency Rate (IR), Coverage Rate (CR)), and an automated evaluation pipeline leveraging large language model (LLM) to verify caption quality via contrastive QA-pairs analysis. By providing actionable insights for caption optimization, our benchmark can advance the development of robust text-to-video models. The dataset and codes are available at website: https://github.com/GXYM/VCapsBench.
We present the methodology and results of the Deep Retrieval team for subtask 4b of the CLEF CheckThat! 2025 competition, which focuses on retrieving relevant scientific literature for given social media posts. To address this task, we propose a hybrid retrieval pipeline that combines lexical precision, semantic generalization, and deep contextual re-ranking, enabling robust retrieval that bridges the informal-to-formal language gap. Specifically, we combine BM25-based keyword matching with a FAISS vector store using a fine-tuned INF-Retriever-v1 model for dense semantic retrieval. BM25 returns the top 30 candidates, and semantic search yields 100 candidates, which are then merged and re-ranked via a large language model (LLM)-based cross-encoder. Our approach achieves a mean reciprocal rank at 5 (MRR@5) of 76.46% on the development set and 66.43% on the hidden test set, securing the 1st position on the development leaderboard and ranking 3rd on the test leaderboard (out of 31 teams), with a relative performance gap of only 2 percentage points compared to the top-ranked system. We achieve this strong performance by running open-source models locally and without external training data, highlighting the effectiveness of a carefully designed and fine-tuned retrieval pipeline.
Large language models (LLMs) have introduced new paradigms for recommender systems by enabling richer semantic understanding and incorporating implicit world knowledge. In this study, we propose a systematic taxonomy that classifies existing approaches into two categories: (1) Pure LLM Recommenders, which rely solely on LLMs, and (2) Augmented LLM Recommenders, which integrate additional non-LLM techniques to enhance performance. This taxonomy provides a novel lens through which to examine the evolving landscape of LLM-based recommendation. To support fair comparison, we introduce a unified evaluation platform that benchmarks representative models under consistent experimental settings, highlighting key design choices that impact effectiveness. We conclude by discussing open challenges and outlining promising directions for future research. This work offers both a comprehensive overview and practical guidance for advancing next-generation LLM-powered recommender.
Ride-hailing platforms face significant challenges in optimizing order dispatching and driver repositioning operations in dynamic urban environments. Traditional approaches based on combinatorial optimization, rule-based heuristics, and reinforcement learning often overlook driver income fairness, interpretability, and adaptability to real-world dynamics. To address these gaps, we propose LLM-ODDR, a novel framework leveraging Large Language Models (LLMs) for joint Order Dispatching and Driver Repositioning (ODDR) in ride-hailing services. LLM-ODDR framework comprises three key components: (1) Multi-objective-guided Order Value Refinement, which evaluates orders by considering multiple objectives to determine their overall value; (2) Fairness-aware Order Dispatching, which balances platform revenue with driver income fairness; and (3) Spatiotemporal Demand-Aware Driver Repositioning, which optimizes idle vehicle placement based on historical patterns and projected supply. We also develop JointDR-GPT, a fine-tuned model optimized for ODDR tasks with domain knowledge. Extensive experiments on real-world datasets from Manhattan taxi operations demonstrate that our framework significantly outperforms traditional methods in terms of effectiveness, adaptability to anomalous conditions, and decision interpretability. To our knowledge, this is the first exploration of LLMs as decision-making agents in ride-hailing ODDR tasks, establishing foundational insights for integrating advanced language models within intelligent transportation systems.
Text-to-image generation increasingly demands access to domain-specific, fine-grained, and rapidly evolving knowledge that pretrained models cannot fully capture. Existing Retrieval-Augmented Generation (RAG) methods attempt to address this by retrieving globally relevant images, but they fail when no single image contains all desired elements from a complex user query. We propose Cross-modal RAG, a novel framework that decomposes both queries and images into sub-dimensional components, enabling subquery-aware retrieval and generation. Our method introduces a hybrid retrieval strategy - combining a sub-dimensional sparse retriever with a dense retriever - to identify a Pareto-optimal set of images, each contributing complementary aspects of the query. During generation, a multimodal large language model is guided to selectively condition on relevant visual features aligned to specific subqueries, ensuring subquery-aware image synthesis. Extensive experiments on MS-COCO, Flickr30K, WikiArt, CUB, and ImageNet-LT demonstrate that Cross-modal RAG significantly outperforms existing baselines in both retrieval and generation quality, while maintaining high efficiency.
Computer-Aided Design (CAD) plays a central role in engineering and manufacturing, making it possible to create precise and editable 3D models. Using a variety of sensor or user-provided data as inputs for CAD reconstruction can democratize access to design applications. However, existing methods typically focus on a single input modality, such as point clouds, images, or text, which limits their generalizability and robustness. Leveraging recent advances in vision-language models (VLM), we propose a multi-modal CAD reconstruction model that simultaneously processes all three input modalities. Inspired by large language model (LLM) training paradigms, we adopt a two-stage pipeline: supervised fine-tuning (SFT) on large-scale procedurally generated data, followed by reinforcement learning (RL) fine-tuning using online feedback, obtained programatically. Furthermore, we are the first to explore RL fine-tuning of LLMs for CAD tasks demonstrating that online RL algorithms such as Group Relative Preference Optimization (GRPO) outperform offline alternatives. In the DeepCAD benchmark, our SFT model outperforms existing single-modal approaches in all three input modalities simultaneously. More importantly, after RL fine-tuning, cadrille sets new state-of-the-art on three challenging datasets, including a real-world one.
Publishing a large language model (LLM) benchmark on the Internet risks contaminating future LLMs: the benchmark may be unintentionally (or intentionally) used to train or select a model. A common mitigation is to keep the benchmark private and let participants submit their models or predictions to the organizers. However, this strategy will require trust in a single organization and still permits test-set overfitting through repeated queries. To overcome this issue, we propose a way to publish benchmarks without completely disclosing the ground-truth answers to the questions, while still maintaining the ability to openly evaluate LLMs. Our main idea is to inject randomness to the answers by preparing several logically correct answers, and only include one of them as the solution in the benchmark. This reduces the best possible accuracy, i.e., Bayes accuracy, of the benchmark. Not only is this helpful to keep us from disclosing the ground truth, but this approach also offers a test for detecting data contamination. In principle, even fully capable models should not surpass the Bayes accuracy. If a model surpasses this ceiling despite this expectation, this is a strong signal of data contamination. We present experimental evidence that our method can detect data contamination accurately on a wide range of benchmarks, models, and training methodologies.
Exceptional behavior tests (EBTs) are crucial in software development for verifying that code correctly handles unwanted events and throws appropriate exceptions. However, prior research has shown that developers often prioritize testing "happy paths", e.g., paths without unwanted events over exceptional scenarios. We present exLong, a framework that automatically generates EBTs to address this gap. exLong leverages a large language model (LLM) fine-tuned from CodeLlama and incorporates reasoning about exception-throwing traces, conditional expressions that guard throw statements, and non-exceptional behavior tests that execute similar traces. Our demonstration video illustrates how exLong can effectively assist developers in creating comprehensive EBTs for their project (available at https://youtu.be/Jro8kMgplZk).
The communication topology in large language model-based multi-agent systems fundamentally governs inter-agent collaboration patterns, critically shaping both the efficiency and effectiveness of collective decision-making. While recent studies for communication topology automated design tend to construct sparse structures for efficiency, they often overlook why and when sparse and dense topologies help or hinder collaboration. In this paper, we present a causal framework to analyze how agent outputs, whether correct or erroneous, propagate under topologies with varying sparsity. Our empirical studies reveal that moderately sparse topologies, which effectively suppress error propagation while preserving beneficial information diffusion, typically achieve optimal task performance. Guided by this insight, we propose a novel topology design approach, EIB-leanrner, that balances error suppression and beneficial information propagation by fusing connectivity patterns from both dense and sparse graphs. Extensive experiments show the superior effectiveness, communication cost, and robustness of EIB-leanrner.
Large Language Model-based multi-agent systems (MAS) have shown remarkable progress in solving complex tasks through collaborative reasoning and inter-agent critique. However, existing approaches typically treat each task in isolation, resulting in redundant computations and limited generalization across structurally similar tasks. To address this, we introduce multi-agent cross-task experiential learning (MAEL), a novel framework that endows LLM-driven agents with explicit cross-task learning and experience accumulation. We model the task-solving workflow on a graph-structured multi-agent collaboration network, where agents propagate information and coordinate via explicit connectivity. During the experiential learning phase, we quantify the quality for each step in the task-solving workflow and store the resulting rewards along with the corresponding inputs and outputs into each agent's individual experience pool. During inference, agents retrieve high-reward, task-relevant experiences as few-shot examples to enhance the effectiveness of each reasoning step, thereby enabling more accurate and efficient multi-agent collaboration. Experimental results on diverse datasets demonstrate that MAEL empowers agents to learn from prior task experiences effectively-achieving faster convergence and producing higher-quality solutions on current tasks.
NL2SQL (natural language to SQL) translates natural language questions into SQL queries, thereby making structured data accessible to non-technical users, serving as the foundation for intelligent data applications. State-of-the-art NL2SQL techniques typically perform translation by retrieving database-specific information, such as the database schema, and invoking a pre-trained large language model (LLM) using the question and retrieved information to generate the SQL query. However, existing NL2SQL techniques miss a key opportunity which is present in real-world settings: NL2SQL is typically applied on existing databases which have already served many SQL queries in the past. The past query workload implicitly contains information which is helpful for accurate NL2SQL translation and is not apparent from the database schema alone, such as common join paths and the semantics of obscurely-named tables and columns. We introduce TailorSQL, a NL2SQL system that takes advantage of information in the past query workload to improve both the accuracy and latency of translating natural language questions into SQL. By specializing to a given workload, TailorSQL achieves up to 2$\times$ improvement in execution accuracy on standardized benchmarks.
The development of sophisticated artificial intelligence (AI) conversational agents based on large language models raises important questions about the relationship between human norms, values, and practices and AI design and performance. This article explores what it means for AI agents to be conversationally aligned to human communicative norms and practices for handling context and common ground and proposes a new framework for evaluating developers' design choices. We begin by drawing on the philosophical and linguistic literature on conversational pragmatics to motivate a set of desiderata, which we call the CONTEXT-ALIGN framework, for conversational alignment with human communicative practices. We then suggest that current large language model (LLM) architectures, constraints, and affordances may impose fundamental limitations on achieving full conversational alignment.
The current landscape of system-on-chips (SoCs) security verification faces challenges due to manual, labor-intensive, and inflexible methodologies. These issues limit the scalability and effectiveness of security protocols, making bug detection at the Register-Transfer Level (RTL) difficult. This paper proposes a new framework named BugWhisperer that utilizes a specialized, fine-tuned Large Language Model (LLM) to address these challenges. By enhancing the LLM's hardware security knowledge and leveraging its capabilities for text inference and knowledge transfer, this approach automates and improves the adaptability and reusability of the verification process. We introduce an open-source, fine-tuned LLM specifically designed for detecting security vulnerabilities in SoC designs. Our findings demonstrate that this tailored LLM effectively enhances the efficiency and flexibility of the security verification process. Additionally, we introduce a comprehensive hardware vulnerability database that supports this work and will further assist the research community in enhancing the security verification process.
CaMeL (Capabilities for Machine Learning) introduces a capability-based sandbox to mitigate prompt injection attacks in large language model (LLM) agents. While effective, CaMeL assumes a trusted user prompt, omits side-channel concerns, and incurs performance tradeoffs due to its dual-LLM design. This response identifies these issues and proposes engineering improvements to expand CaMeL's threat coverage and operational usability. We introduce: (1) prompt screening for initial inputs, (2) output auditing to detect instruction leakage, (3) a tiered-risk access model to balance usability and control, and (4) a verified intermediate language for formal guarantees. Together, these upgrades align CaMeL with best practices in enterprise security and support scalable deployment.
Manufacturing environments are becoming more complex and unpredictable due to factors such as demand variations and shorter product lifespans. This complexity requires real-time decision-making and adaptation to disruptions. Traditional control approaches highlight the need for advanced control strategies capable of overcoming unforeseen challenges, as they demonstrate limitations in responsiveness within dynamic industrial settings. Multi-agent systems address these challenges through decentralization of decision-making, enabling systems to respond dynamically to operational changes. However, current multi-agent systems encounter challenges related to real-time adaptation, context-aware decision-making, and the dynamic exploration of resource capabilities. Large language models provide the possibility to overcome these limitations through context-aware decision-making capabilities. This paper introduces a large language model-enabled control architecture for multi-agent manufacturing systems to dynamically explore resource capabilities in response to real-time disruptions. A simulation-based case study demonstrates that the proposed architecture improves system resilience and flexibility. The case study findings show improved throughput and efficient resource utilization compared to existing approaches.
As a social being, we have an intimate bond with the environment. A plethora of things in human life, such as lifestyle, health, and food are dependent on the environment and agriculture. It comes under our responsibility to support the environment as well as agriculture. However, traditional farming practices often result in inefficient resource use and environmental challenges. To address these issues, precision agriculture has emerged as a promising approach that leverages advanced technologies to optimise agricultural processes. In this work, a hybrid approach is proposed that combines the three different potential fields of model AI: object detection, large language model (LLM), and Retrieval-Augmented Generation (RAG). In this novel framework, we have tried to combine the vision and language models to work together to identify potential diseases in the tree leaf. This study introduces a novel AI-based precision agriculture system that uses Retrieval Augmented Generation (RAG) to provide context-aware diagnoses and natural language processing (NLP) and YOLOv8 for crop disease detection. The system aims to tackle major issues with large language models (LLMs), especially hallucinations and allows for adaptive treatment plans and real-time disease detection. The system provides an easy-to-use interface to the farmers, which they can use to detect the different diseases related to coffee leaves by just submitting the image of the affected leaf the model will detect the diseases as well as suggest potential remediation methodologies which aim to lower the use of pesticides, preserving livelihoods, and encouraging environmentally friendly methods. With an emphasis on scalability, dependability, and user-friendliness, the project intends to improve RAG-integrated object detection systems for wider agricultural applications in the future.
Ultra-high-resolution (UHR) remote sensing (RS) imagery offers valuable data for Earth observation but pose challenges for existing multimodal foundation models due to two key bottlenecks: (1) limited availability of UHR training data, and (2) token explosion caused by the large image size. To address data scarcity, we introduce SuperRS-VQA (avg. 8,376$\times$8,376) and HighRS-VQA (avg. 2,000$\times$1,912), the highest-resolution vision-language datasets in RS to date, covering 22 real-world dialogue tasks. To mitigate token explosion, our pilot studies reveal significant redundancy in RS images: crucial information is concentrated in a small subset of object-centric tokens, while pruning background tokens (e.g., ocean or forest) can even improve performance. Motivated by these findings, we propose two strategies: Background Token Pruning and Anchored Token Selection, to reduce the memory footprint while preserving key semantics.Integrating these techniques, we introduce GeoLLaVA-8K, the first RS-focused multimodal large language model capable of handling inputs up to 8K$\times$8K resolution, built on the LLaVA framework. Trained on SuperRS-VQA and HighRS-VQA, GeoLLaVA-8K sets a new state-of-the-art on the XLRS-Bench.
Large language models excel at complex tasks by breaking down problems into structured reasoning steps. However, reasoning traces often extend beyond reaching a correct answer, causing wasted computation, reduced readability, and hallucinations. To address this, we introduce a novel hyperparameter-free conciseness score used as a reward signal within a reinforcement learning framework to guide models toward generating correct and concise reasoning traces. This score is evaluated by a large language model acting as a judge, enabling dynamic, context-aware feedback beyond simple token length. Our method achieves state-of-the-art efficiency-accuracy trade-offs on the MATH dataset, reducing token usage by up to 31x on simple problems while improving accuracy by 7%, and on the hardest problems, it outperforms full reasoning by +7.5% accuracy with up to 3.6x fewer tokens. On TheoremQA, our method improves accuracy by +2.2% using 12.5x fewer tokens. We also conduct ablation studies on the judge model, reward composition, and problem difficulty, showing that our method dynamically adapts reasoning length based on problem difficulty and benefits significantly from stronger judges. The code, model weights, and datasets are open-sourced at https://github.com/RazvanDu/ConciseRL.