BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning
Department of Mechanical Engineering(机械工程系);Massachusetts Institute of Technology(麻省理工学院);Department of Civil and Environmental Engineering(土木与环境工程系);Schwarzman College of Computing(施瓦茨曼计算学院)
Can reinforcement learning with hard, verifiable rewards teach a compact language model to reason about physics, or does it primarily learn to pattern-match toward correct answers? We study this question by training a 1.5B-parameter reasoning model on beam statics, a classic engineering problem, using parameter-efficient RLVR with binary correctness rewards from symbolic solvers, without teacher-generated reasoning traces. The best BeamPERL checkpoint achieves a 66.7% improvement in Pass@1 over the base model. However, the learned competence is anisotropic: the model generalizes compositionally (more loads) but fails under topological shifts (moved supports) that require the same equilibrium equations. Intermediate checkpoints yield the strongest reasoning, while continued optimization degrades robustness while maintaining reward. These findings reveal a key limitation of outcome-level alignment: reinforcement learning with exact physics rewards induces procedural solution templates rather than internalization of governing equations. The precision of the reward signal - even when analytically exact - does not by itself guarantee transferable physical reasoning. Our results suggest that verifiable rewards may need to be paired with structured reasoning scaffolding to move beyond template matching toward robust scientific reasoning.
Strategic Bargaining in Multi-Buyer Markets: Reinforcement Learning from Verifiable Rewards for LLM Negotiations
Institute for Data, Systems, and Society, Massachusetts Institute of Technology(数据、系统与社会研究所,麻省理工学院);Mitch Daniels School of Business, Purdue University(米奇·丹尼尔斯商学院,普渡大学);The Division of Physics, Mathematics and Astronomy, California Institute of Technology(物理、数学与天文学部,加州理工学院);Department of Computing and Mathematical Sciences, California Institute of Technology(计算与数学科学系,加州理工学院);H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology(H. 米尔顿·斯图尔特工业与系统工程学院,佐治亚理工学院);Department of Civil and Environmental Engineering, Operations Research Center, Massachusetts Institute of Technology(土木与环境工程系、运筹学中心,麻省理工学院)
Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis
AI DATA, Alibaba Group Holding Limited(阿里数据,阿里巴巴集团控股有限公司);EPIC Lab, Shanghai Jiao Tong University(上海交通大学EPIC实验室);Shanghai University of Finance(上海财经大学);Wuhan University(武汉大学)
SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data
Zhejiang University(浙江大学);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院);Hangzhou City University(杭州城市大学);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新技术区(滨江)区块链与数据安全研究院)
Grad2Reward: From Sparse Judgment to Dense Rewards for Improving Open-Ended LLM Reasoning
School of Information Science and Technology, ShanghaiTech University(信息科学与技术学院,上海科技大学);State Key Laboratory of General Artificial Intelligence, BIGAI(通用人工智能国家重点实验室,BIGAI)
Foundation AI–Cisco Systems Inc.(Foundation AI–Cisco系统公司);Yale University(耶鲁大学);University of California, San Diego(加州大学圣地亚哥分校);University of Pennsylvania(宾夕法尼亚大学);Carnegie Mellon University(卡内基梅隆大学)
ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold
Department of Computer Science & Engineering, Texas A&M University(德克萨斯A&M大学计算机科学与工程系);Department of Computer Science, University of Florida(佛罗里达大学计算机科学系)
MedPAO: A Protocol-Driven Agent for Structuring Medical Reports
Department of Data Science and AI, IIT Madras, India(数据科学与人工智能系,印度理工学院马德拉斯学院);Department of Engineering Design, IIT Madras, India(工程设计系,印度理工学院马德拉斯学院);LoveForm Health Technologies, India(LoveForm健康科技公司,印度);Department of Radiology and Imaging Sciences, Sri Ramachandra Institute of Higher Education and Research, India(放射学与成像科学系, Sri Ramachandra高等教育与研究学院,印度);Department of Neuro and Interventional Radiology, Sri Ramachandra Institute of Higher Education and Research, India(神经放射学与介入放射学系,Sri Ramachandra高等教育与研究学院,印度)
VICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning
Virginia Tech(弗吉尼亚理工大学);Cisco(思科公司);NVIDIA(英伟达公司);UChicago(芝加哥大学);Georgia Tech(佐治亚理工学院);Abaka AI(Abaka人工智能公司);UC Berkeley(加州大学伯克利分校);UGA(佐治亚大学);WashU(华盛顿大学)
MolRGen: A Training and Evaluation Setting for De Novo Molecular Generation with Reasonning Models
Université Paris-Saclay(巴黎萨克雷大学);ÉTS Montréal(蒙特利尔ÉTS);ILLS – International Laboratory on Learning Systems(学习系统国际实验室);Mila – Quebec AI Institute(魁北克人工智能研究所);Mistral AI;LIVIA;CNRS, CentraleSupélec(国家科学研究中心,中央超导大学)
Hardware-Enforced Semantic Coordination for Safety-Critical Real-Time Autonomous Systems
Department of Computer Science University of the Bundeswehr Munich Neubiberg, Germany;Department of Computer Science Sapienza University of Rome Rome, Italy;STAKE Lab University of Molise Campobasso, Italy
Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO
HKUST Hong Kong SAR, China(香港科技大学);SEU Jiangsu, China(江苏大学);HKUST(GZ) Guangzhou, China(香港科技大学(广州));Zhipu AI Beijing, China(智谱AI);HKUST(GZ), HKUST Guangzhou, China(香港科技大学(广州)、香港科技大学)
Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training
Shanghai Artificial Intelligence Laboratory, OpenDataLab, OpenDataArena(上海人工智能实验室、OpenDataLab、OpenDataArena);Hong Kong University of Science and Technology(香港科技大学)
CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework
Microsoft Research Asia(微软亚洲研究院);Department of Biomedical Engineering, Yale University(耶鲁大学生物医学工程系);Department of Radiology & Biomedical Imaging, Yale University(耶鲁大学放射学与生物医学成像系)
An Agentic System for Rare Disease Diagnosis with Traceable Reasoning
Shanghai Jiao Tong University(上海交通大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Xinhua Hospital affiliated to Shanghai Jiao Tong University School of Medicine(上海交通大学医学院附属新华医院);Shanghai Institute for Pediatric Research(上海市儿科医学研究所);Harvard Medical School(哈佛医学院);The Affiliated Children’s Hospital of Xiangya School of Medicine(湘雅医学院附属儿童医院)
Do Math Reasoning LLMs Help Predict the Impact of Public Transit Events?
Department of Civil Engineering and Engineering Mechanics, Columbia University(哥伦比亚大学土木工程与工程力学系);Engineering Mechanics, Columbia University(哥伦比亚大学工程力学系);Department of Computer Science, Columbia University(哥伦比亚大学计算机科学系);Data Science Institute, Columbia University(哥伦比亚大学数据科学研究院)