大模型推理能力

Optimizing Reasoning Efficiency through Prompt Difficulty Prediction

Bo Zhao, Berkcan Kapusuzoglu, Kartik Balasubramaniam, Sambit Sahu, Supriyo Chakraborty, Genta Indra Winata

机构 * UC San Diego（加州大学圣地亚哥分校） ； Capital One（Capital One公司） 纠错

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.AI、cs.LG

Comments NeurIPS 2025 Workshop on Efficient Reasoning

Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models

Junyi Li, Hwee Tou Ng

机构 * Department of Computer Science, National University of Singapore（计算机科学系，新加坡国立大学） 纠错

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments accepted by NeurIPS 2025

Mathematics with large language models as provers and verifiers

Hieu Le Duc, Leo Liberti

机构 * CNRS LIX Ecole Polytechnique, Institut Polytechnique de Paris（高等理工学院巴黎理工研究所） 纠错

专题命中 代码与定理证明 ：verifier(abstract)；分类 cs.CL、cs.AI、cs.LG

DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration

Narjes Nourzad, Hanqing Yang, Shiyu Chen, Carlee Joe-Wong

机构 * University of Southern California（南加州大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 逻辑推理 ：reasoning(title,abstract)；planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Examining Student and AI Generated Personalized Analogies in Introductory Physics

Amogh Sirnoorkar, Winter Allen, Syed Furqan Abbas Hashmi, N. Sanjay Rebello

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving

Luke Rowe, Rodrigue de Schaetzen, Roger Girgis, Christopher Pal, Liam Paull

机构 * Mila - Quebec AI Institute（魁北克人工智能研究所） ； Université de Montréal（蒙特利尔大学） ； Polytechnique Montréal（蒙特利尔理工学院） ； CIFAR AI Chair（CIFAR人工智能主席） 纠错

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

LLM-Driven Adaptive Source-Sink Identification and False Positive Mitigation for Static Analysis

Shiyin Lin

专题命中 逻辑推理 ：reasoning(abstract)

AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning

Zewei Zhou, Tianhui Cai, Seth Z. Zhao, Yun Zhang, Zhiyu Huang, Bolei Zhou, Jiaqi Ma

机构 * University of California, Los Angeles（加州大学洛杉矶分校） 纠错

专题命中 规划推理 ：reasoning(title,abstract)；chain-of-thought(abstract)；planning(abstract)

Comments NeurIPS 2025; Website link:https://autovla.github.io/

Plan of Knowledge: Retrieval-Augmented Large Language Models for Temporal Knowledge Graph Question Answering

Xinying Qian, Ying Zhang, Yu Zhao, Baohang Zhou, Xuhui Sui, Xiaojie Yuan

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)；分类 cs.CL

Comments Submitted to the IEEE for possible publication

TextualVerifier: Verify TextGrad Step-by-Step

Eugenius Mario Situmorang, Adila Alfa Krisnadhi, Ari Wibisono

专题命中 规划推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

BAPPA: Benchmarking Agents, Plans, and Pipelines for Automated Text-to-SQL Generation

Fahim Ahmed, Md Mubtasim Ahasan, Jahir Sadik Monon, Muntasir Wahed, M Ashraful Amin, A K M Mahbubur Rahman, Amin Ahsan Ali

机构 * Center for Computational & Data Sciences, Independent University, Bangladesh（计算与数据科学中心，独立大学，孟加拉国） ； University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Autocomp: A Powerful and Portable Code Optimizer for Tensor Accelerators

Charles Hong, Sahil Bhatia, Alvin Cheung, Yakun Sophia Shao

专题命中 规划推理 ：planning(abstract)；分类 cs.AI、cs.LG

Comments 10 pages + appendices

ARETE: an R package for Automated REtrieval from TExt with large language models

Vasco V. Branco, Jandó Benedek, Lidia Pivovarova, Luís Correia, Pedro Cardoso

专题命中 规划推理 ：planning(abstract)；分类 cs.LG

Deep Learning-Driven Downscaling for Climate Risk Assessment of Projected Temperature Extremes in the Nordic Region

Parthiban Loganathan, Elias Zea, Ricardo Vinuesa, Evelyn Otero

专题命中 规划推理 ：planning(abstract)；分类 cs.LG

Robust mean-field control under common noise uncertainty

Mathieu Laurière, Ariel Neufeld, Kyunghyun Park

专题命中 规划推理 ：planning(abstract)

What's in Common? Multimodal Models Hallucinate When Reasoning Across Scenes

Candace Ross, Florian Bordes, Adina Williams, Polina Kirichenko, Mark Ibrahim

机构 * FAIR at Meta（Meta 的 FAIR） 纠错

专题命中 视觉空间推理 ：reasoning(title,abstract)；chain-of-thought(abstract)；分类 cs.LG

Comments 10 pages, 6 figures. Accepted to NeurIPS Datasets & Benchmarks 2025

HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts

Neil He, Rishabh Anand, Hiren Madhu, Ali Maatouk, Smita Krishnaswamy, Leandros Tassiulas, Menglin Yang, Rex Ying

机构 * Yale University, USA（耶鲁大学） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Node-Based Editing for Multimodal Generation of Text, Audio, Image, and Video

Alexander Htet Kyaw, Lenin Ravindranath Sivalingam

机构 * Massachusetts Institute of Technology（麻省理工学院） ； Microsoft Research（微软研究院） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)；分类 cs.AI

Comments Accepted to NeurIPS 2025, Conference on Neural Information Processing Systems, Workshop on Generative and Protective AI for Content Creation

SurgViVQA: Temporally-Grounded Video Question Answering for Surgical Scene Understanding

Mauro Orazio Drago, Luca Carlini, Pelinsu Celebi Balyemez, Dennis Pierantozzi, Chiara Lena, Cesare Hassan, Danail Stoyanov, Elena De Momi, Sophia Bano, Mobarak I. Hoque

机构 * Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB)（电子、信息与生物工程系） ； Politecnico di Milano（米兰理工大学） ； IRCCS Humanitas Research Hospital（IRCCS人类itas研究医院） ； UCL Hawkes Institute and Department of Computer Science（UCL Hawkes研究所和计算机科学系） ； University College London（伦敦大学学院） ； University of Manchester（曼彻斯特大学） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)

EarthGPT-X: A Spatial MLLM for Multi-level Multi-Source Remote Sensing Imagery Understanding with Visual Prompting

Wei Zhang, Miaoxin Cai, Yaqian Ning, Tong Zhang, Yin Zhuang, Shijian Lu, He Chen, Jun Li, Xuerui Mao

机构 * School of Interdisciplinary Science, Beijing Institute of Technology（交叉科学学院，北京理工大学） ； College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学） ； National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology（空间智能信息处理国家重点实验室，北京理工大学） ； School of Optics and Photonics, Beijing Institute of Technology（光学与 photonics 学院，北京理工大学） ； State Key Laboratory of Explosion Science and Safety Protection, Beijing（爆炸科学与安全防护国家重点实验室，北京） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)

Seg the HAB: Language-Guided Geospatial Algae Bloom Reasoning and Segmentation

Patterson Hsieh, Jerry Yeh, Mao-Chi He, Wen-Han Hsieh, Elvis Hsieh

机构 * UC San Diego（加州大学圣地亚哥分校） ； UC Berkeley（加州大学伯克利分校） 纠错

专题命中 测试时计算 ：reasoning(title,abstract)；分类 cs.AI

RLoop: An Self-Improving Framework for Reinforcement Learning with Iterative Policy Initialization

Zeng Zhiyuan, Jiashuo Liu, Zhangyue Yin, Ge Zhang, Wenhao Huang, Xipeng Qiu

机构 * Fudan University（复旦大学） ； Shanghai Innovation Institute（上海创新研究院） 纠错

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.AI

Reusing Pre-Training Data at Test Time is a Compute Multiplier

Alex Fang, Thomas Voice, Ruoming Pang, Ludwig Schmidt, Tom Gunter

机构 * Apple（苹果公司） ； Stanford（斯坦福大学） 纠错

专题命中 测试时计算 ：test-time compute(abstract)；分类 cs.CL

Exact Expressive Power of Transformers with Padding

William Merrill, Ashish Sabharwal

机构 * Allen Institute for AI（艾伦人工智能研究所） 纠错

专题命中 测试时计算 ：test-time compute(abstract)；分类 cs.LG

Comments Neurips 2025

Logit-Entropy Adaptive Stopping Heuristic for Efficient Chain-of-Thought Reasoning

Mohammad Atif Quamar, Mohammad Areeb

机构 * Purdue University（普渡大学） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；chain-of-thought(title,abstract)；CoT(abstract)；分类 cs.CL

Comments Presented at the 1st Workshop on Efficient Reasoning (NeurIPS 2025)

How do Transformers Learn Implicit Reasoning?

Jiaran Ye, Zijun Yao, Zhidian Huang, Liangming Pan, Jinxin Liu, Yushi Bai, Amy Xin, Weichuan Liu, Xiaoyin Che, Lei Hou, Juanzi Li

机构 * DCST, BNRist（中国清华大学人工智能研究院） ； KIRC, Institute for Artificial Intelligence, Tsinghua University, China 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.LG

Comments Accepted as Spotlight at NeurIPS 2025

A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers

William Merrill, Ashish Sabharwal

机构 * Allen Institute for AI（阿伦人工智能研究所） ； New York University（纽约大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.LG

Comments NeurIPS 2025

Test-Time Warmup for Multimodal Large Language Models

Nikita Rajaneesh, Thomas Zollo, Richard Zemel

机构 * Columbia University（哥伦比亚大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability

Jonggwon Park, Byungmu Yoon, Soobum Kim, Kyoyun Choi

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments NeurIPS 2025

Beyond Shortest Path: Agentic Vehicular Routing with Semantic Context

Carnot Braun, Rafael O. Jarczewski, Gabriel U. Talasso, Leandro A. Villas, Allan M. de Souza

机构 * Institute of Computing (IC)（计算学院） ； Hub de Inteligência Artificial e Arquiteturas Cognitivas (H.IAAC)（人工智能与认知架构中心） ； Universidade Estadual de Campinas (UNICAMP)（坎皮纳斯州立大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI