{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/autowebglm-bootstrap-and-reinforce-a-large","title":"AutoWebGLM: A Large Language Model-based Web Navigating Agent","arxiv_id":"2404.03648","date":"2024-04-04","proceeding":null,"authors":["Hanyu Lai","Xiao Liu","Iat Long Iong","Shuntian Yao","Yuxuan Chen","Pengbo Shen","Hao Yu","Hanchen Zhang","Xiaohan Zhang","Yuxiao Dong","Jie Tang"],"abstract":"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}.","url_abs":"https://arxiv.org/abs/2404.03648v2","url_pdf":"https://arxiv.org/pdf/2404.03648v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"autowebglm-bootstrap-and-reinforce-a-large","repo_url":"https://github.com/thudm/autowebglm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.03648","atlas_url":"https://app.syntology.ai/?focus=2404.03648","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03648"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thudm/autowebglm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"37ecf4aff9fcd163","entry":"get_dom_list","repo":"thudm/autowebglm","repo_kind":"official","path":"miniwob++/miniwob_tools/utils.py","file_url":"https://github.com/thudm/autowebglm/blob/HEAD/miniwob%2B%2B/miniwob_tools/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"37ecf4aff9fcd163"}},{"code_sha256_prefix":"e5df06a0578279f5","entry":"print_html_object","repo":"thudm/autowebglm","repo_kind":"official","path":"miniwob++/html_tools/utils.py","file_url":"https://github.com/thudm/autowebglm/blob/HEAD/miniwob%2B%2B/html_tools/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e5df06a0578279f5"}},{"code_sha256_prefix":"a7429f25bfea2585","entry":"process_dom_list","repo":"thudm/autowebglm","repo_kind":"official","path":"miniwob++/miniwob_tools/utils.py","file_url":"https://github.com/thudm/autowebglm/blob/HEAD/miniwob%2B%2B/miniwob_tools/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a7429f25bfea2585"}},{"code_sha256_prefix":"624000cbde7aed7d","entry":"update_dom_list","repo":"thudm/autowebglm","repo_kind":"official","path":"miniwob++/miniwob_tools/utils.py","file_url":"https://github.com/thudm/autowebglm/blob/HEAD/miniwob%2B%2B/miniwob_tools/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"624000cbde7aed7d"}},{"code_sha256_prefix":"59ad9b9b71ef36c1","entry":"action2str","repo":"thudm/autowebglm","repo_kind":"official","path":"webarena/browser_env/actions.py","file_url":"https://github.com/thudm/autowebglm/blob/HEAD/webarena/browser_env/actions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59ad9b9b71ef36c1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}