Reviewer assignment is increasingly critical yet challenging in the LLM era, where rapid topic shifts render many pre-2023 benchmarks outdated and where proxy signals poorly reflect true reviewer familiarity. We address this evaluation bottleneck by introducing LR-bench, a high-fidelity, up-to-date benchmark curated from 2024–2025 AI/NLP manuscripts with five-level self-assessed familiarity ratings collected via a large-scale email survey, yielding 1,055 expert-annotated paper–reviewer–score annotations. We further propose RATE, a reviewer-centric ranking framework that distills each reviewer’s recent publications into compact keyword-based profiles and fine-tunes an embedding model with weak preference supervision constructed from heuristic retrieval signals, enabling the matching of each manuscript against a reviewer profile directly. Across the LR-bench and the CMU gold-standard dataset, our approach consistently achieves state-of-the-art performance, outperforming strong embedding baselines by a clear margin. We release LR-bench at https://huggingface.co/datasets/Gnociew/LR-bench, and an github repository at https://github.com/Gnociew/RATE-Reviewer-Assignment.

Recent advances in synergizing large reasoning models (LRMs) with retrieval-augmented generation (RAG) have shown promising results, yet two critical challenges remain: (1) reasoning models typically operate from a single, unchallenged perspective, limiting their ability to conduct deep, self-correcting reasoning over external documents, and (2) existing training paradigms rely excessively on outcome-oriented rewards, which provide insufficient signal for shaping the complex, multi-step reasoning process. To address these issues, we propose an Reasoner-Verifier framework named Adversarial Reasoning RAG (ARR). The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other's logic while being guided by process-aware advantage that requires no external scoring model. This reward combines explicit observational signals with internal model uncertainty to jointly optimize reasoning fidelity and verification rigor. Experiments on multiple benchmarks demonstrate the effectiveness of our method.

为有效规避车辆营运过程中的高危场景并预警风险，解析营运车辆事故风险耦合机制，开展营运车辆事故高危场景画像与风险评估。本文针对网络爬虫的 517 份营运车辆事故报告，基于人-车-路-环四维度框架，构建包含 4 个一级指标、7 个二级指标和 19 个三级指标的营运车辆事故高危场景画像和安全风险评估的指标体系。其次，采用改进的自组织映射（Self-Organizing Map，SOM）-K-means 算法对营运货车事故进行聚类，刻画重大、较大、一般货车事故中各指标的重要程度，生成不同等级事故的高危场景画像。为了进一步预警风险，采用随机森林模型计算指标权重，划分事故风险等级，然后集成嵌入式、多层感知机（Multilayer Perceptron，MLP）、Transformer 等模型，对营运车辆安全风险进行评估。结果表明，营运货车一般级别事故的高危场景为良好天气条件下的直路高速行驶，罐车驾驶员易分心驾驶导致事故发生；营运货车较大级别事故的高危场景为在道路线形复杂的低级别路段，超载的货车在驾驶人疲劳驾驶的情况下容易导致事故发生；营运货车重大级别事故的高危场景为雨雪雾天气下，驾驶人在高速弯道超速驾驶易导致事故发生。MLP 模型测试集风险评估准确率达 95.59%，引入嵌入层，改进后的 MLP 和 Transformer 模型评估准确率达 95.88%，尤其是在极高风险识别中实现 100%召回率，优于其他模型，为实施差异化管理策略和动态风险监控提供了可靠的技术支持。