SMRC is a new method that aligns large language models with student reasoning for mathematical error correction. It treats student reasoning as a multi‑step decision problem and uses Monte Carlo Tree Search to find optimal correction paths, while a breadth‑first search guided by the model generates reward signals that are back‑propagated to supervise intermediate steps. The authors also introduce the MSEB benchmark of 158 high‑school math problems and a dual evaluation protocol focusing on solution accuracy and correct‑step retention, showing that SMRC outperforms existing methods on several datasets.
By Biaojie Zeng, Min Zhang, Juan Zhou, Fengrui Liu, Ruiyang Huang, Yu Song, Xin Lin
arXiv:2509. 16780v3 Announce Type: replace-cross Abstract: Large language models (LLMs) show promise as educational aids but often lack alignment with specific course materials.
By Eason Chen, Chuangji Li, Eric Li, Zimo Xiao, Jionghao Lin, Kenneth R. Koedinger
arXiv:2606. 03144v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as self-study assistants in technical disciplines, yet their reliability as mathematical reasoning assistants remains poorly understood.
By Noujoud Nader, Ibrahem Aljabea, Patrick Diehl, Deepti Gupta
arXiv:2602. 20629v3 Announce Type: replace Abstract: As Large Language Models (LLMs) saturate elementary benchmarks, the research frontier has shifted from generation to the reliability of automated evaluation.
By Santiago Gonzalez, Alireza Amiri Bavandpour, Peter Ye, Edward Zhang, Ruslans Aleksejevs, Todor Anti\'c, Polina Baron, Sujeet Bhalerao, Shubhrajit Bhattacharya, Zachary Burton, John Byrne, Hyungjun Choi, Nujhat Ahmed Disha, Koppany Istv\'an Encz, Yuchen Fang, Robert Joseph George, Ebrahim Ghorbani, Alan Goldfarb, Jing Guo, Meghal Gupta, Stefano Huber, Annika Kanckos, Minjung Kang, Hyun Jong Kim, Dino Lorenzini, Levi Lorenzo, Tianyi Mao, Giovanni Marzenta, Ariane M. Masuda, Lukas Mauth, Ana Mickovic, Andres Miniguano-Trujillo, Antoine Moulin, Wenqi Ni, Tomos Parry, Kevin Ren, Hossein Roodbarani, Mathieu Rundstr\"om, Manjil Saikia, Detchat Samart, Rebecca Steiner, Connor Stewart, Dhara Thakkar, Jeffrey Tse, Vasiliki Velona, Yunhai Xiang, Sibel Yal\c{c}{\i}n, Jun Yan, Ji Zeng, Arman Cohan, Quanquan C. Liu
arXiv:2508.02208v3 Announce Type: replace-cross
Abstract: Evaluating the mathematical capability of Large Language Models (LLMs) is a critical yet challenging frontier. Existing benchmarks fall short...
By Yebo Peng, Yaoming Li, Zixiang Liu, Zhizhuo Yang, Xinye Xu, Bowen Ye, Weijun Yuan, Zihan Wang, Tong Yang
The paper presents a controlled comparison of six retrieval-augmented generation (RAG) strategies for scientific question answering on a large arXiv corpus. All pipelines use the same LLM generator and evaluation protocol, differing only in retrieval design—ranging from classic dense retrieval to late‑interaction methods like ColBERTv2. The authors also release a synthetic question dataset and code to enable reproducible, large‑scale evaluation of RAG trade‑offs.
By Bhagyesh Rathi, Eshan Chawla, William B. Andreopoulos
arXiv:2606. 00532v1 Announce Type: new Abstract: Context engineering can improve large language models without updating their weights, but mathematical reasoning exposes a key limitation: feedback accumulated in one growing prompt causes context bloat and limits the amount of learned guidance that can be used.
By Jayant Parashar, Suchendra M. Bhandarkar
arXiv:2510.13935v3 Announce Type: replace-cross
Abstract: The facts a language model stores are tied to its parameter count, so small models that fit on edge devices fail on expert problems, which ne...
By Kenan Alkiek, David Jurgens, Vinod Vydiswaran
AI University (AI‑U) is a flexible framework that uses a fine‑tuned large language model (LLM) combined with retrieval‑augmented generation (RAG) and a reasoning synthesis model to produce style‑aligned responses from lecture videos, notes, and textbooks. In a graduate‑level finite‑element‑method (FEM) course, the authors created a pipeline to generate course‑grounded training data, fine‑tuned an open‑source LLM with Low‑Rank Adaptation (LoRA), and applied RAG‑based synthesis. Evaluation through cosine similarity, LLM‑based assessment, expert review, and user studies showed that the expert model outperformed the base model in alignment with course materials, with 86 % of test cases scoring higher and human users preferring the expert model roughly twice as often.
whyItMatters":"The study demonstrates a practical method for building course‑specific learning assistants that improve alignment with instructional content, offering a template that can be extended across STEM fields."
By Mostafa Faghih Shojaei, Rahul Gulati, Benjamin A. Jasperson, Shangshang Wang, Simone Cimolato, Manas Vardhan, Dangli Cao, Willie Neiswanger, Krishna Garikipati
Large language models (LLMs) have achieved remarkable performance on high-school and olympiad-style mathematics, yet their capabilities on advanced mathematics remain poorly understood. Existing benchmarks, however, fall short in both scope and evaluation granularity: they provide limited disciplinary coverage and often rely on final-answer correctness or coarse judgments, leaving the validity of the reasoning process inadequately assessed.
arXiv:2607. 14178v1 Announce Type: new Abstract: Recent advances in Large Language Models have fueled autonomous AI agents capable of tackling complex scientific tasks, yet existing automated research systems remain predominantly focused on empirically driven domains with quantitative benchmarks, leaving theory-driven discovery, particularly in mathematically grounded disciplines requiring rigorous proofs and synthesis of domain knowledge, largely underexplored.
By Yutong He, Daibo Li, Guohong Li, Jiahe Geng, Zhengyang Huang, Can Ren, Zekun Zhang, Yifan Liu, Shuchen Zhu, Hengrui Zhang, Boao Kong, Ming Sun, Shu Li, Chenyi Li, Jiang Hu, Kun Yuan, Zaiwen Wen, Pingwen Zhang
AdvancedMathBench is a new benchmark suite that evaluates large language models on advanced mathematical proof generation and verification. It includes ProverBench, with 245 problems from undergraduate to doctoral qualifying‑exam levels, and VerifierBench, which tests models’ ability to judge proof validity using 888 expert‑annotated trajectories. The suite features an automatic verification pipeline trained on expert data, and results show that even state‑of‑the‑art models perform poorly, highlighting a gap between generation and verification skills.
By Lingkai Kong, Zijian Wu, Yuzhe Gu, Haiteng Zhao, Zhouqi Hua, Wenyong Huang, Shuang Sun, Zhicheng Xiong, Xiaotian Zhang, Shuya Zhao, Yan Wang, Disheng Xu, Wenwei Zhang, Kai Chen