Explanipedia

Conceptual design report of the Super Tau-Charm Facility: the accelerator Open

L. An, Shizhong An, Ligong Bian, I. Boyko, Marina Chadeeva , et al. · 2025

Electron–positron colliders operating in the GeV center-of-mass range, or tau-charm energy region, have been proved to enable competitive frontier research due to several unique features. With the progress of high-energy physics in the las…

InspectCoder: Dynamic Analysis-Enabled Self Repair through interactive LLM-Debugger Collaboration Open

Yunkun Wang, Yue Zhang, Guochang Li, Zhi Chen, Binhua Li , et al. · 2025

Large Language Models (LLMs) frequently generate buggy code with complex logic errors that are challenging to diagnose. While existing LLM-based self-repair approaches conduct intensive static semantic analysis or reply on superficial exec…

Scaling Generalist Data-Analytic Agents Open

Shuofei Qiao, Yanqiu Zhao, Zhisong Qiu, Xiaobin Wang, Jintian Zhang , et al. · 2025

Data-analytic agents are emerging as a key catalyst for automated scientific discovery and for the vision of Innovating AI. Current approaches, however, rely heavily on prompt engineering over proprietary models, while open-source models s…

GSID: Generative Semantic Indexing for E-Commerce Product Understanding Open

Haiyang Yang, Qingguo Xie, Qinghe Zhang, Liyu Chen, Huike Zou , et al. · 2025

Structured representation of product information is a major bottleneck for the efficiency of e-commerce platforms, especially in second-hand ecommerce platforms. Currently, most product information are organized based on manually curated p…

PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awareness Open

Huacan Chai, Z. Cao, Mengran Ran, Yingxuan Yang, Jianghao Lin , et al. · 2025

Large language models (LLMs) have achieved impressive success in single-turn function calling, yet real-world applications such as travel planning or multi-stage data analysis typically unfold across multi-turn conversations. In these sett…

Towards General Agentic Intelligence via Environment Scaling Open

Runnan Fang, Shan Cai, Baixuan Li, Jialong Wu, Guangyu Li , et al. · 2025

Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-calling intelligence, which needs agents to develop these ca…

WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents Open

Zile Qiao, Guoxin Chen, Xuanzhong Chen, Donglei Yu, Wenbiao Yin , et al. · 2025

Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we introduce WebResearcher, a novel framework for building such …

CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis Open

Xinyu Zhang, Pei Zhang, Shuang Luo, Jialong Tang, Yu Wan , et al. · 2025

Cultural competence, defined as the ability to understand and adapt to multicultural contexts, is increasingly vital for large language models (LLMs) in global environments. While several cultural benchmarks exist to assess LLMs' cultural …

WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent Open

Xinyu Geng, Peng Xia, Zhen Zhang, Xinyu Wang, Qiuchen Wang , et al. · 2025

Web agents such as Deep Research have demonstrated superhuman cognitive abilities, capable of solving highly challenging information-seeking problems. However, most research remains primarily text-centric, overlooking visual information in…

TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence Open

Guiyang Hou, Xing Gao, Yuchuan Wu, Xiang Huang, Wenqi Zhang , et al. · 2025

Recently, Large Language Models (LLMs) have made significant progress in IQ-related domains that require careful thinking, such as mathematics and coding. However, enhancing LLMs' cognitive development in social domains, particularly from …

ChARM: Character-based Act-adaptive Reward Modeling for Advanced Role-Playing Language Agents Open

Feiteng Fang, Ting-En Lin, Yuchuan Wu, Xiong Liu, Xiang Huang , et al. · 2025

Role-Playing Language Agents (RPLAs) aim to simulate characters for realistic and engaging human-computer interactions. However, traditional reward models often struggle with scalability and adapting to subjective conversational preference…

Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning Patterns Open

Xiang Li, Haiyang Yu, Xinghua Zhang, Shizhu He, Fei Huang , et al. · 2025

Process Reward Models (PRMs) are crucial in complex reasoning and problem-solving tasks (e.g., LLM agents with long-horizon decision-making) by verifying the correctness of each intermediate reasoning step. In real-world scenarios, LLMs ma…

Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation Open

Junyang Wang, Haiyang Xu, Xi Zhang, Ming Yan, Ji Zhang , et al. · 2025

The exponential rise in mobile device usage necessitates streamlined automation for effective task management, yet many AI frameworks fall short due to inadequate operational expertise. While manually written knowledge can bridge this gap,…

Qwen3 Technical Report Open

An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui , et al. · 2025

In this work, we present Qwen3, the latest version of the Qwen model family. Qwen3 comprises a series of large language models (LLMs) designed to advance performance, efficiency, and multilingual capabilities. The Qwen3 series includes mod…

WritingBench: A Comprehensive Benchmark for Generative Writing Open

Yuning Wu, Mei Jiang, Ming Yan, Chenliang Li, Shaopeng Lai , et al. · 2025

Recent advancements in large language models (LLMs) have significantly enhanced text generation capabilities, yet evaluating their performance in generative writing remains a challenge. Existing benchmarks primarily focus on generic text g…

Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference Open

Zhuo Chen, Xinyu Wang, Yong Jiang, Zhen Zhang, Xinyu Geng , et al. · 2025

Despite the advancements made in Vision Large Language Models (VLLMs), like text Large Language Models (LLMs), they have limitations in addressing questions that require real-time information or are knowledge-intensive. Indiscriminately ad…

Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation Open

Junyang Wang, Haiyang Xu, Xi Zhang, Ming Yan, Ji Zhang , et al. · 2025

The exponential rise in mobile device usage necessitates streamlined automation for effective task management, yet many AI frameworks fall short due to inadequate operational expertise. While manually written knowledge can bridge this gap,…

Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation Open

Chenyang Huang, Fei Huang, Zaixiang Zheng, Osmar R. Zai͏̈ane, Hao Zhou , et al. · 2025

Multilingual neural machine translation (MNMT) aims at using one single model for multiple translation directions. Recent work applies non-autoregressive Transformers to improve the efficiency of MNMT, but requires expensive knowledge dist…

Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks Open

Zhenhailong Wang, Haiyang Xu, Junyang Wang, Xi Zhang, Ming Yan , et al. · 2025

Smartphones have become indispensable in modern life, yet navigating complex tasks on mobile devices often remains frustrating. Recent advancements in large multimodal model (LMM)-based mobile agents have demonstrated the ability to percei…

OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis Open

Run Luo, Ting-En Lin, Haonan Zhang, Yuchuan Wu, Xiong Liu , et al. · 2025

Recent advancements in omnimodal learning have significantly improved understanding and generation across images, text, and speech, yet these developments remain predominantly confined to proprietary models. The lack of high-quality omnimo…

CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis Open

Xinyu Zhang, Pei Zhang, Shuang Luo, Jialong Tang, Yu Wan , et al. · 2025

GSID: Generative Semantic Indexing for E-Commerce Product Understanding Open

Haiyang Yang, Qingguo Xie, Qinghe Zhang, Yu Chen, Huike Zou , et al. · 2025

ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questions Open

Jingheng Ye, Yong Jiang, Xiaobin Wang, Yinghui Li, Yangning Li , et al. · 2025

NOVA-63: Native Omni-lingual Versatile Assessments of 63 Disciplines Open

Jinyang Zhang, Kexin Yang, Yu Wan, Muyang Ye, Baosong Yang , et al. · 2025

Dimensionality Reduction and Classification Based on Enhanced Graph and Hypergraph Joint Discriminative Learning Open

Junhua Li, Hongchun Qu, Fei Huang · 2025

mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding Open

Anwen Hu, Haiyang Xu, Liang Zhang, Jiabo Ye, Ming Yan , et al. · 2025

KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models Open

Zhen Zhang, Xinyu Wang, Yong Jiang, Zile Qiao, Zhuo Chen , et al. · 2025

Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference Open

Zhuo Chen, Xinyu Wang, Yong Jiang, Zhen Zhang, Xinyu Geng , et al. · 2025

DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling Open

Su Chen, Zile Qiao, Bo Wang, Guoxin Chen, Yingyan Hou , et al. · 2025

Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling Open

Zile Qiao, Wei Ye, Yong Jiang, Tong Mo, Pengjun Xie , et al. · 2025

Fei Huang YOU? Author Swipe