paper-with-me

홈 › Papers

AutoWebGLM: A Large Language Model-based Web Navigating Agent

2024-04-04 · Hanyu Lai, Xiao Liu, Iat Long Iong, Shuntian Yao, Yuxuan Chen, Pengbo Shen, Hao Yu, Hanchen Zhang, Xiaohan Zhang, Yuxiao Dong, Jie Tang

Large language models (LLMs) have fueled many intelligent web agents, but most existing ones perform far from satisfying in real-world web navigation tasks due to three factors: (1) the complexity of HTML text data (2) versatility of actions on webpages, and (3) task difficulty due to the open-domain nature of the web. In light of these challenges, we develop the open AutoWebGLM based on ChatGLM3-6B. AutoWebGLM can serve as a powerful automated web navigation agent that outperform GPT-4. Inspired by human browsing patterns, we first design an HTML simplification algorithm to represent webpages with vital information preserved succinctly. We then employ a hybrid human-AI method to build web browsing data for curriculum training. Finally, we bootstrap the model by reinforcement learning and rejection sampling to further facilitate webpage comprehension, browser operations, and efficient task decomposition by itself. For comprehensive evaluation, we establish a bilingual benchmark -- AutoWebBench -- for real-world web navigation tasks. We evaluate AutoWebGLM across diverse web navigation benchmarks, demonstrating its potential to tackle challenging tasks in real environments. Related code, model, and data are released at \url{https://github.com/THUDM/AutoWebGLM}.

📄 PDF Abstract BibTeX arXiv:2404.03648

Code (1)

thudm/autowebglm 공식 구현

Tasks

Decision MakingLanguage ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음
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…
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning

2024-11-04 · Zehan Qi, Xiao Liu, Iat Long Iong, Hanyu Lai 외

Large language models (LLMs) have shown remarkable potential as autonomous agents, particularly in web-based tasks. However, existing LLM web agents heavily rely on expensive proprietary LLM APIs, while open LLMs lack th…

Does Peer Observation Help? Vision-Sharing Collaboration for Vision-Language Navigation

2026-03-21 · Qunchao Jin, Yiliao Song, Qi Wu arxiv

Vision-Language Navigation (VLN) systems are fundamentally constrained by partial observability, as an agent can only accumulate knowledge from locations it has personally visited. As multiple robots increasingly coexist…

Vision-Language Navigation

RMM: A Recursive Mental Model for Dialogue Navigation

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Homero Roman Roman, Yonatan Bisk, Jesse Thomason, Asli Celikyilmaz 외

Language-guided robots must be able to both ask humans questions and understand answers. Much existing work focuses only on the latter. In this paper, we go beyond instruction following and introduce a two-agent task whe…

Answer GenerationInstruction Followingmodel

RMM: A Recursive Mental Model for Dialog Navigation

2020-05-02 · Homero Roman Roman, Yonatan Bisk, Jesse Thomason, Asli Celikyilmaz 외

Language-guided robots must be able to both ask humans questions and understand answers. Much existing work focuses only on the latter. In this paper, we go beyond instruction following and introduce a two-agent task whe…

Answer GenerationInstruction Followingmodel

UrbanNav: Learning Language-Guided Urban Navigation from Web-Scale Human Trajectories

2025-12-10 · Yanghong Mei, Yirong Yang, Longteng Guo, Qunbo Wang 외 arxiv

Navigating complex urban environments using natural language instructions poses significant challenges for embodied agents, including noisy language instructions, ambiguous spatial references, diverse landmarks, and dyna…

Spatial ReasoningVisual Navigation