大模型推理能力

Intent-Based Network for RAN Management with Large Language Models

Fransiscus Asisi Bimo, Maria Amparo Canaveras Galdon, Chun-Kai Lai, Ray-Guang Cheng, Edwin K. P. Chong

机构 * National Taiwan University of Science and Technology（台湾科技大学） ； NVIDIA（NVIDIA公司） ； Colorado State University（科罗拉多州立大学） 纠错

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

Comments 5 pages, 3 figures, submitted to IEEE Globecom 2025

Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detection

Yiming Xu, Jiarun Chen, Zhen Peng, Zihan Chen, Qika Lin, Lan Ma, Bin Shi, Bo Dong

机构 * School of Computer Science and Technology, Xi'an Jiaotong University（计算机科学与技术学院，西安交通大学） ； Department of Electrical and Computer Engineering, University of Virginia（电气与计算机工程系，弗吉尼亚大学） ； Saw Swee Hock School of Public Health, National University of Singapore（Saw Swee Hock 公共卫生学院，新加坡国立大学） ； China Telecom Corporation Ltd. Shaanxi Branch（中国电信股份有限公司陕西分公司） ； School of Distance Education, Xi'an Jiaotong University（继续教育学院，西安交通大学） 纠错

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

Comments Accepted by ACM Multimedia 2025 (MM '25)

DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer

Ruoyu Wang, Junda Wu, Yu Xia, Tong Yu, Ryan A. Rossi, Julian McAuley, Lina Yao

机构 * UNSW Sydney（新南威尔士大学悉尼分校） ； UC San Diego（南加州大学圣地亚哥分校） ； Adobe Research（Adobe研究） ； CSIRO’s Data 61（澳大利亚联邦科学与工业研究组织的数据61） 纠错

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

Towards Simulating Social Influence Dynamics with LLM-based Multi-agents

Hsien-Tsung Lin, Pei-Cing Huang, Chan-Tung Ku, Chan Hsu, Pei-Xuan Shieh, Yihuang Kang

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

Magentic-UI: Towards Human-in-the-loop Agentic Systems

Hussein Mozannar, Gagan Bansal, Cheng Tan, Adam Fourney, Victor Dibia, Jingya Chen, Jack Gerrits, Tyler Payne, Matheus Kunzler Maldaner, Madeleine Grunde-McLaughlin, Eric Zhu, Griffin Bassman, Jacob Alber, Peter Chang, Ricky Loynd, Friederike Niedtner, Ece Kamar, Maya Murad, Rafah Hosn, Saleema Amershi

机构 * Microsoft Research AI Frontiers（微软研究院人工智能前沿） 纠错

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

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Xingjian Zhang, Siwei Wen, Wenjun Wu, Lei Huang

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

Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control

Jinyan Su, Jennifer Healey, Preslav Nakov, Claire Cardie

机构 * Cornell University（康奈尔大学） ； Adobe Research（Adobe研究） ； Mohamed bin Zayed University of Artificial Intelligence（Mohamed bin Zayed人工智能大学） 纠错

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

Visual Adaptive Prompting for Compositional Zero-Shot Learning

Kyle Stein, Arash Mahyari, Guillermo Francia, Eman El-Sheikh

机构 * University of West Florida（乌斯托尔大学） ； Florida Institute for Human and Machine Cognition (IHMC)（佛罗里达人类与机器认知研究所） 纠错

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

Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratings

Anirudh Nair, Adi Banerjee, Laurent Mombaerts, Matthew Hagen, Tarik Borogovac

机构 * Amazon（亚马逊） 纠错

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

"Just a strange pic": Evaluating 'safety' in GenAI Image safety annotation tasks from diverse annotators' perspectives

Ding Wang, Mark Díaz, Charvi Rastogi, Aida Davani, Vinodkumar Prabhakaran, Pushkar Mishra, Roma Patel, Alicia Parrish, Zoe Ashwood, Michela Paganini, Tian Huey Teh, Verena Rieser, Lora Aroyo

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

Comments Accepted to AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society 2025 (AIES 2025)

SensorChat: Answering Qualitative and Quantitative Questions during Long-Term Multimodal Sensor Interactions

Xiaofan Yu, Lanxiang Hu, Benjamin Reichman, Dylan Chu, Rushil Chandrupatla, Xiyuan Zhang, Larry Heck, Tajana Rosing

机构 * University of California San Diego（加州大学圣迭戈分校） ； Georgia Institute of Technology（佐治亚理工学院） 纠错

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

Comments To appear in IMWUT'25. Code is available at: https://github.com/Orienfish/SensorChat

DPMT: Dual Process Multi-scale Theory of Mind Framework for Real-time Human-AI Collaboration

Xiyun Li, Yining Ding, Yuhua Jiang, Yunlong Zhao, Runpeng Xie, Shuang Xu, Yuanhua Ni, Yiqin Yang, Bo Xu

机构 * The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（认知与决策智能复杂系统重点实验室，自动化研究所，中国科学院） ； School of Future Technology, University of Chinese Academy of Sciences（未来技术学院，中国科学院大学） ； Nankai University（南开大学） ； Tsinghua University（清华大学） 纠错

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

Journal ref cogsci-2025

Team of One: Cracking Complex Video QA with Model Synergy

Jun Xie, Zhaoran Zhao, Xiongjun Guan, Yingjian Zhu, Hongzhu Yi, Xinming Wang, Feng Chen, Zhepeng Wang

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

THOR: Transformer Heuristics for On-Demand Retrieval

Isaac Shi, Zeyuan Li, Fan Liu, Wenli Wang, Lewei He, Yang Yang, Tianyu Shi

机构 * eSapiens 纠错

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

Enhancing the Capabilities of Large Language Models for API calls through Knowledge Graphs

Ye Yang, Xue Xiao, Ping Yin, Taotao Xie

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

Game Theory Meets LLM and Agentic AI: Reimagining Cybersecurity for the Age of Intelligent Threats

Quanyan Zhu

机构 * Quanyan Zhu 纠错

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

GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language Models

Zhen Yang, Haitao Lin, Jiawei xue, Ziji Zhang

机构 * AMAP, Alibaba Group（阿里云实验室，阿里巴巴集团） 纠错

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

Comments 8 pages, 3 figures

Optimizing Sequential Multi-Step Tasks with Parallel LLM Agents

Enhao Zhang, Erkang Zhu, Gagan Bansal, Adam Fourney, Hussein Mozannar, Jack Gerrits

机构 * University of Washington, Seattle, USA（华盛顿大学） ； Microsoft Research, Redmond, USA（微软研究院） 纠错

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

Comments ICML 2025 Workshop on MAS

Pinning "Reflection" on the Agenda: Investigating Reflection in Human-LLM Co-Creation for Creative Coding

Anqi Wang, Zhizhuo Yin, Yulu Hu, Yuanyuan Mao, Lei Han, Xin Tong, Keqin Jiao, Pan Hui

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

Comments 6 pages, 2 figures, 2 tables

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor

Vatsal Agarwal, Matthew Gwilliam, Gefen Kohavi, Eshan Verma, Daniel Ulbricht, Abhinav Shrivastava

机构 * University of Maryland（马里兰大学） ； Apple（苹果公司） 纠错

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

Comments Website: see https://vatsalag99.github.io/mustafar/

Automating IRAC Analysis in Malaysian Contract Law using a Semi-Structured Knowledge Base

Xiaoxi Kang, Lizhen Qu, Lay-Ki Soon, Zhuang Li, Adnan Trakic

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

Journal ref Artificial Intelligence and Law (2025)

AGACCI : Affiliated Grading Agents for Criteria-Centric Interface in Educational Coding Contexts

Kwangsuk Park, Jiwoong Yang

机构 * AA LAB, MODULABS（AA实验室，MODULABS） ； Aiffel, MODULABS（Aiffel，MODULABS） ； Department of Statistics, Inha university（统计系，Inha大学） 纠错

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

Comments Accepted at ICML 2025 Workshop on Multi-Agent Systems in the Era of Foundation Models: Opportunities, Challenges and Futures (MAS)

From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control

Yide Shentu, Philipp Wu, Aravind Rajeswaran, Pieter Abbeel

机构 * University of California, Berkeley（加州大学伯克利分校） 纠错

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

Prompting as Scientific Inquiry

Ari Holtzman, Chenhao Tan

机构 * Department of Computer Science University of Chicago（计算机科学系芝加哥大学） 纠错

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

AI-VaxGuide: An Agentic RAG-Based LLM for Vaccination Decisions

Abdellah Zeggai, Ilyes Traikia, Abdelhak Lakehal, Abdennour Boulesnane

机构 * Department of Fundamental Computing and its Applications, Faculty of NTIC（基础计算及其应用系） ； BIOSTIM Laboratory, Medicine Faculty Salah Boubnider Constantine 03 University（BIOSTIM实验室，医学系Salah Boubnider Constantine 03大学） 纠错

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

Explainable Compliance Detection with Multi-Hop Natural Language Inference on Assurance Case Structure

Fariz Ikhwantri, Dusica Marijan

机构 * Simula Research Laboratory（Simula研究实验室） 纠错

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

MCCoder: Streamlining Motion Control with LLM-Assisted Code Generation and Rigorous Verification

Yin Li, Liangwei Wang, Shiyuan Piao, Boo-Ho Yang, Ziyue Li, Wei Zeng, Fugee Tsung

机构 * Thrust of Data Science and Analytics, The Hong Kong University of Science and Technology (Guangzhou)（数据科学与分析 thrust，香港科学与技术大学（广州）） ； Department of Industrial Engineering and Decision Analytics, The Hong Kong University of Science and Technology（工业工程与决策分析系，香港科学与技术大学） ； MOVENSYS Inc.（MOVENSYS公司） ； University of Cologne（科隆大学） 纠错

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

Comments IEEE CASE 2025 Best Student Paper Finalists

CAVALRY-V: A Large-Scale Generator Framework for Adversarial Attacks on Video MLLMs

Jiaming Zhang, Rui Hu, Qing Guo, Wei Yang Bryan Lim

机构 * Nanyang Technological University（南洋理工大学） ； Beijing Jiaotong University（北京交通大学） ； A*STAR Project Page（A*STAR项目页面） 纠错

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

Agentic Medical Knowledge Graphs Enhance Medical Question Answering: Bridging the Gap Between LLMs and Evolving Medical Knowledge

Mohammad Reza Rezaei, Reza Saadati Fard, Jayson L. Parker, Rahul G. Krishnan, Milad Lankarany

机构 * University of Toronto（多伦多大学） ； Vector Institute（向量研究所） ； Worcester Polytechnic Institute（沃思菲技术学院） 纠错

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

Reasoner Outperforms: Generative Stance Detection with Rationalization for Social Media

Jiaqing Yuan, Ruijie Xi, Munindar P. Singh

机构 * North Carolina State University（北卡罗来纳州立大学） 纠错

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

Comments Accepted by ACM Hypertext 2025