Health-SCORE: Towards Scalable Rubrics for Improving Health-LLMs

Rubrics are essential for evaluating open-ended LLM responses, especially in safety-critical domains such as healthcare. However, creating high-quality and domain-specific rubrics typically requires significant human expertise time and development cost, making rubric-based evaluation and training difficult to scale. In this work, we introduce Health-SCORE, a generalizable and scalable rubric-based training and evaluation framework that substantially reduces rubric development costs without sacrificing performance. We show that Health-SCORE provides two practical benefits beyond standalone evaluation: it can be used as a structured reward signal to guide reinforcement learning with safety-aware supervision, and it can be incorporated directly into prompts to improve response quality through in-context learning. Across open-ended healthcare tasks, Health-SCORE achieves evaluation quality comparable to human-created rubrics while significantly lowering development effort, making rubric-based evaluation and training more scalable.

TransportAgents: a multi-agents LLM framework for traffic accident severity prediction

Accurate prediction of traffic crash severity is critical for improving emergency response and public safety planning. Although recent large language models (LLMs) exhibit strong reasoning capabilities, their single-agent architectures often struggle with heterogeneous, domain-specific crash data and tend to generate biased or unstable predictions. To address these limitations, this paper proposes TransportAgents, a hybrid multi-agent framework that integrates category-specific LLM reasoning with a multilayer perceptron (MLP) integration module. Each specialized agent focuses on a particular subset of traffic information, such as demographics, environmental context, or incident details, to produce intermediate severity assessments that are subsequently fused into a unified prediction. Extensive experiments on two complementary U.S. datasets, the Consumer Product Safety Risk Management System (CPSRMS) and the National Electronic Injury Surveillance System (NEISS), demonstrate that TransportAgents consistently outperforms both traditional machine learning and advanced LLM-based baselines. Across three representative backbones, including closed-source models such as GPT-3.5 and GPT-4o, as well as open-source models such as LLaMA-3.3, the framework exhibits strong robustness, scalability, and cross-dataset generalizability. A supplementary distributional analysis further shows that TransportAgents produces more balanced and well-calibrated severity predictions than standard single-agent LLM approaches, highlighting its interpretability and reliability for safety-critical decision support applications.

LongT2IBench: A Benchmark for Evaluating Long Text-to-Image Generation with Graph-structured Annotations

The increasing popularity of long Text-to-Image (T2I) generation has created an urgent need for automatic and interpretable models that can evaluate the image-text alignment in long prompt scenarios. However, the existing T2I alignment benchmarks predominantly focus on short prompt scenarios and only provide MOS or Likert scale annotations. This inherent limitation hinders the development of long T2I evaluators, particularly in terms of the interpretability of alignment. In this study, we contribute LongT2IBench, which comprises 14K long text-image pairs accompanied by graph-structured human annotations. Given the detail-intensive nature of long prompts, we first design a Generate-Refine-Qualify annotation protocol to convert them into textual graph structures that encompass entities, attributes, and relations. Through this transformation, fine-grained alignment annotations are achieved based on these granular elements. Finally, the graph-structed annotations are converted into alignment scores and interpretations to facilitate the design of T2I evaluation models. Based on LongT2IBench, we further propose LongT2IExpert, a LongT2I evaluator that enables multi-modal large language models (MLLMs) to provide both quantitative scores and structured interpretations through an instruction-tuning process with Hierarchical Alignment Chain-of-Thought (CoT). Extensive experiments and comparisons demonstrate the superiority of the proposed LongT2IExpert in alignment evaluation and interpretation. Data and code have been released in https://welldky.github.io/LongT2IBench-Homepage/.

PRIME: Planning and Retrieval-Integrated Memory for Enhanced Reasoning

Inspired by the dual-process theory of human cognition from \textit{Thinking, Fast and Slow}, we introduce \textbf{PRIME} (Planning and Retrieval-Integrated Memory for Enhanced Reasoning), a multi-agent reasoning framework that dynamically integrates \textbf{System 1} (fast, intuitive thinking) and \textbf{System 2} (slow, deliberate thinking). PRIME first employs a Quick Thinking Agent (System 1) to generate a rapid answer; if uncertainty is detected, it then triggers a structured System 2 reasoning pipeline composed of specialized agents for \textit{planning}, \textit{hypothesis generation}, \textit{retrieval}, \textit{information integration}, and \textit{decision-making}. This multi-agent design faithfully mimics human cognitive processes and enhances both efficiency and accuracy. Experimental results with LLaMA 3 models demonstrate that PRIME enables open-source LLMs to perform competitively with state-of-the-art closed-source models like GPT-4 and GPT-4o on benchmarks requiring multi-hop and knowledge-grounded reasoning. This research establishes PRIME as a scalable solution for improving LLMs in domains requiring complex, knowledge-intensive reasoning.

ChatThero: An LLM-Supported Chatbot for Behavior Change and Therapeutic Support in Addiction Recovery

Substance use disorders (SUDs) affect over 36 million people worldwide, yet few receive effective care due to stigma, motivational barriers, and limited personalized support. Although large language models (LLMs) show promise for mental-health assistance, most systems lack tight integration with clinically validated strategies, reducing effectiveness in addiction recovery. We present ChatThero, a multi-agent conversational framework that couples dynamic patient modeling with context-sensitive therapeutic dialogue and adaptive persuasive strategies grounded in cognitive behavioral therapy (CBT) and motivational interviewing (MI). We build a high-fidelity synthetic benchmark spanning Easy, Medium, and Hard resistance levels, and train ChatThero with a two-stage pipeline comprising supervised fine-tuning (SFT) followed by direct preference optimization (DPO). In evaluation, ChatThero yields a 41.5\% average gain in patient motivation, a 0.49\% increase in treatment confidence, and resolves hard cases with 26\% fewer turns than GPT-4o, and both automated and human clinical assessments rate it higher in empathy, responsiveness, and behavioral realism. The framework supports rigorous, privacy-preserving study of therapeutic conversation and provides a robust, replicable basis for research and clinical translation.

Can Structured Templates Facilitate LLMs in Tackling Harder Tasks? : An Exploration of Scaling Laws by Difficulty

Structured, procedural reasoning is essential for Large Language Models (LLMs), especially in mathematics. While post-training methods have improved LLM performance, they still fall short in capturing deep procedural logic on complex tasks. To tackle the issue, in this paper, we first investigate this limitation and uncover a novel finding: a Scaling Law by Difficulty, which reveals that model performance follows a U-shaped curve with respect to training data complexity -- excessive low-difficulty data impedes abstraction, while high-difficulty data significantly enhances reasoning ability. Motivated by this, we propose the Structured Solution Template (SST) framework, which uses solution templates and a curriculum of varied difficulty to explicitly teach procedural reasoning. Specifically, SST comprises (1) fine-tuning with structured solution-template chains and dynamically weighted loss to prioritize procedural logic, (2) prompt-time injection of solution templates as cognitive scaffolds to guide inference, and (3) integrated curriculum fine-tuning that explicitly teaches the model to self-plan - execute - self-correct. Experiments on GSM8K, AIME24, and new Dynamic En benchmark show that SST significantly improves both accuracy and efficiency, especially on harder problems.

TuningIQA: Fine-Grained Blind Image Quality Assessment for Livestreaming Camera Tuning

Livestreaming has become increasingly prevalent in modern visual communication, where automatic camera quality tuning is essential for delivering superior user Quality of Experience (QoE). Such tuning requires accurate blind image quality assessment (BIQA) to guide parameter optimization decisions. Unfortunately, the existing BIQA models typically only predict an overall coarse-grained quality score, which cannot provide fine-grained perceptual guidance for precise camera parameter tuning. To bridge this gap, we first establish FGLive-10K, a comprehensive fine-grained BIQA database containing 10,185 high-resolution images captured under varying camera parameter configurations across diverse livestreaming scenarios. The dataset features 50,925 multi-attribute quality annotations and 19,234 fine-grained pairwise preference annotations. Based on FGLive-10K, we further develop TuningIQA, a fine-grained BIQA metric for livestreaming camera tuning, which integrates human-aware feature extraction and graph-based camera parameter fusion. Extensive experiments and comparisons demonstrate that TuningIQA significantly outperforms state-of-the-art BIQA methods in both score regression and fine-grained quality ranking, achieving superior performance when deployed for livestreaming camera tuning.

Fine-grained Image Quality Assessment for Perceptual Image Restoration

Recent years have witnessed remarkable achievements in perceptual image restoration (IR), creating an urgent demand for accurate image quality assessment (IQA), which is essential for both performance comparison and algorithm optimization. Unfortunately, the existing IQA metrics exhibit inherent weakness for IR task, particularly when distinguishing fine-grained quality differences among restored images. To address this dilemma, we contribute the first-of-its-kind fine-grained image quality assessment dataset for image restoration, termed FGRestore, comprising 18,408 restored images across six common IR tasks. Beyond conventional scalar quality scores, FGRestore was also annotated with 30,886 fine-grained pairwise preferences. Based on FGRestore, a comprehensive benchmark was conducted on the existing IQA metrics, which reveal significant inconsistencies between score-based IQA evaluations and the fine-grained restoration quality. Motivated by these findings, we further propose FGResQ, a new IQA model specifically designed for image restoration, which features both coarse-grained score regression and fine-grained quality ranking. Extensive experiments and comparisons demonstrate that FGResQ significantly outperforms state-of-the-art IQA metrics. Codes and model weights have been released in https://pxf0429.github.io/FGResQ/

E-bike agents: Large Language Model-Driven E-Bike Accident Analysis and Severity Prediction

Electric bicycles (e-bikes) are rapidly increasing in use, raising safety concerns due to a rise in accident reports. However, e-bike incident reports often use unstructured narrative formats, which hinders quantitative safety analysis. This study introduces E-bike agents, a framework that uses large language models (LLM) powered agents to classify and extract safety variables from unstructured incident reports. Our framework consists of four LLM agents, handling data classification, information extraction, injury cause determination, and component linkage, to extract the key factors that could lead to E-bike accidents and cause varying severity levels. Furthermore, we used an ordered logit model to examine the relationship between the severity of the incident and the factors retrieved, such as gender, the type of cause, and environmental conditions. Our research shows that equipment issues are slightly more common than human-related ones, but human-related incidents are more often fatal. Specifically, pedals, tires, and brakes are frequent contributors to accidents. The model achieves a high weighted F1 score of 0.87 in classification accuracy, highlighting the potential of using LLMs to extract unstructured data in niche domains, such as transportation. Our method offers a scalable solution to improve e-bike safety analytics and provides actionable information for policy makers, designers, and regulators.

TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks

Lightweight Vision-Language Models (VLMs) are indispensable for resource-constrained applications. The prevailing approach to aligning vision and language models involves freezing both the vision encoder and the language model while training small connector modules. However, this strategy heavily depends on the intrinsic capabilities of the language model, which can be suboptimal for lightweight models with limited representational capacity. In this work, we investigate this alignment bottleneck through the lens of mutual information, demonstrating that the constrained capacity of the language model inherently limits the Effective Mutual Information (EMI) between multimodal inputs and outputs, thereby compromising alignment quality. To address this challenge, we propose TinyAlign, a novel framework inspired by Retrieval-Augmented Generation, which strategically retrieves relevant context from a memory bank to enrich multimodal inputs and enhance their alignment. Extensive empirical evaluations reveal that TinyAlign significantly reduces training loss, accelerates convergence, and enhances task performance. Remarkably, it allows models to achieve baseline-level performance with only 40\% of the fine-tuning data, highlighting exceptional data efficiency. Our work thus offers a practical pathway for developing more capable lightweight VLMs while introducing a fresh theoretical lens to better understand and address alignment bottlenecks in constrained multimodal systems.