paper-with-me

홈 › Papers

WebWalker: Benchmarking LLMs in Web Traversal

2025-01-13 · Jialong Wu, Wenbiao Yin, Yong Jiang, Zhenglin Wang, Zekun Xi, Runnan Fang, Linhai Zhang, Yulan He, Deyu Zhou, Pengjun Xie, Fei Huang

Retrieval-augmented generation (RAG) demonstrates remarkable performance across tasks in open-domain question-answering. However, traditional search engines may retrieve shallow content, limiting the ability of LLMs to handle complex, multi-layered information. To address it, we introduce WebWalkerQA, a benchmark designed to assess the ability of LLMs to perform web traversal. It evaluates the capacity of LLMs to traverse a website's subpages to extract high-quality data systematically. We propose WebWalker, which is a multi-agent framework that mimics human-like web navigation through an explore-critic paradigm. Extensive experimental results show that WebWalkerQA is challenging and demonstrates the effectiveness of RAG combined with WebWalker, through the horizontal and vertical integration in real-world scenarios.

📄 PDF Abstract BibTeX arXiv:2501.07572

Code (2)

alibaba-nlp/webwalker 공식 구현
alibaba-nlp/webagent

Tasks

BenchmarkingOpen-Domain Question AnsweringQuestion AnsweringRAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
WordPiece 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Adam 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

See and Remember: A Multimodal Agent for Web Traversal

2026-03-03 · Xinjun Wang, Shengyao Wang, Aimin Zhou, Hao Hao arxiv

Autonomous web navigation requires agents to perceive complex visual environments and maintain long-term context, yet current Large Language Model (LLM) based agents often struggle with spatial disorientation and navigat…

Visual Grounding

Can LLMs perform structured graph reasoning?

2024-02-02 · Palaash Agrawal, Shavak Vasania, Cheston Tan

Pretrained Large Language Models (LLMs) have demonstrated various reasoning capabilities through language-based prompts alone, particularly in unstructured task settings (tasks purely based on language semantics). Howeve…

BenchmarkingNavigatevalid

Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs

2024-07-31 · Elan Markowitz, Anil Ramakrishna, Jwala Dhamala, Ninareh Mehrabi 외

Knowledge graphs (KGs) complement Large Language Models (LLMs) by providing reliable, structured, domain-specific, and up-to-date external knowledge. However, KGs and LLMs are often developed separately and must be integ…

Knowledge GraphsQuestion Answering

RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals

2025-05-21 · Xuanliang Zhang, Dingzirui Wang, Keyan Xu, Qingfu Zhu 외

The table reasoning task, crucial for efficient data acquisition, aims to answer questions based on the given table. Recently, reasoning large language models (RLLMs) with Long Chain-of-Thought (Long CoT) significantly e…

Knowledge Graph Prompting for Multi-Document Question Answering

2023-08-22 · Yu Wang, Nedim Lipka, Ryan A. Rossi, Alexa Siu 외

The `pre-train, prompt, predict' paradigm of large language models (LLMs) has achieved remarkable success in open-domain question answering (OD-QA). However, few works explore this paradigm in the scenario of multi-docum…

graph constructionOpen-Domain Question AnsweringQuestion AnsweringRetrieval