We lifted 5 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| thudm/autowebglm | canonical | 4 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| get_dom_list | Ran | thudm/autowebglm/miniwob++/miniwob_tools/utils.py code served (permissive licence) · get_code("37ecf4aff9fcd163") |
| print_html_object | Ran | thudm/autowebglm/miniwob++/html_tools/utils.py code served (permissive licence) · get_code("e5df06a0578279f5") |
| process_dom_list | Ran | thudm/autowebglm/miniwob++/miniwob_tools/utils.py code served (permissive licence) · get_code("a7429f25bfea2585") |
| update_dom_list | Ran | thudm/autowebglm/miniwob++/miniwob_tools/utils.py code served (permissive licence) · get_code("624000cbde7aed7d") |
| action2str | Not yet run | thudm/autowebglm/webarena/browser_env/actions.py code served (permissive licence) · get_code("59ad9b9b71ef36c1") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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}.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2404.03648")
get_code_for_paper("2404.03648")
have("2404.03648")
Connect an agent — have() is free.