Operations Research (OR) relies on expert-driven modeling--a slow and fragile process ill-suited to novel scenarios. While large language models (LLMs) can automatically translate natural language into optimization models, existing approaches either rely on costly post-training or employ multi-agent frameworks, yet most still lack reliable collaborative error correction and task-specific retrieval, often leading to incorrect outputs. We propose MIRROR (a Multi-agent framework with Iterative adaptive Revision and hierarchical Retrieval for optimization modeling in Operations Research), a fine-tuning-free, end-to-end multi-agent framework that directly translates natural language optimization problems into mathematical models and solver code. MIRROR integrates two core mechanisms: (1) execution-driven iterative adaptive revision for automatic error correction, and (2) hierarchical retrieval to fetch relevant modeling and coding exemplars from a carefully curated exemplar library. Experiments show that MIRROR outperforms existing methods on standard OR benchmarks, with notable results on complex industrial datasets such as "IndustryOR" and "Mamo-ComplexLP". By combining precise external knowledge infusion with systematic error correction, MIRROR provides non-expert users with an efficient and reliable OR modeling solution, overcoming the fundamental limitations of general-purpose LLMs in expert optimization tasks.
RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game
Chongqing University（重庆大学）；Queen Mary University of London（伦敦玛丽女王大学）；Chongqing Key Laboratory of Big Data Intelligence and Privacy Computing（重庆市大数据智能与隐私计算重点实验室）；Fangda Partners（方达律师事务所）
Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revision
New York University（纽约大学）；NYU Shanghai（上海纽约大学）；University of Alberta（阿尔伯塔大学）；Princeton University（普林斯顿大学）；University of Waterloo（滑铁卢大学）；Verdent AI, Inc.（Verdent AI公司）
Text Revision by On-the-Fly Representation Optimization
The Chinese University of Hong Kong（香港中文大学）；Mila；McGill University（麦吉尔大学）；Microsoft Research Asia（微软亚洲研究院）
文本修改是指一类自然语言生成任务，其中源序列和目标序列在表面形式上具有适度的相似性，但在属性上存在差异，例如文本的正式性和简单性。目前最先进的方法将这些任务表述为序列到序列的学习问题，这依赖于大规模的并行训练语料库。在本文中，我们提出了一个迭代的就地编辑方法的文本修订，它不需要并行数据。在这种方法中，我们简单地使用掩码语言建模和属性分类来微调预训练的Transformer。在推理过程中，每次迭代的编辑都是通过两步跨度替换来实现的。在第一步，文本的分布式表示朝着属性函数动态优化。在第二步，一个文本跨度被掩盖，并提出另一个新的条件下的优化表示。对文本形式化和文本简化这两个典型的文本修改任务的实验表明了该方法的有效性。它在文本简化方面比最先进的监督方法具有竞争力甚至更好的性能，并且在文本形式化\footnote{Code and model are available at \url{https://github.com/jingjingli01/OREO}}方面比强无监督方法具有更好的性能。
FirstPass: Grounding AI Scientific Judgment in Multi-Round Editorial Outcomes
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；RediMinds Inc.（RediMinds公司）；Disaster Science Operations Center, Western Kentucky University（西肯塔基大学灾害科学运营中心）
