DocOS: Towards Proactive Document-Guided Actions in GUI Agents
The paper introduces DocOS, a benchmark aimed at enhancing the capabilities of GUI agents through proactive document-guided actions. This approach allows agents to autonomously search for relevant documentation to solve complex tasks. The study highlights the challenges agents face in locating information and executing precise actions based on retrieved instructions.
- ▪DocOS is designed to assess document-guided problem solving in interactive environments.
- ▪The proposed method enables GUI agents to search for documentation to resolve long-tailed tasks.
- ▪Experiments reveal that agents struggle with locating relevant information and grounding instructions into actions.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.18048 |
| Publication time | Tue, 19 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-19T04:04:57.272Z |
| Last seen | 2026-05-19T04:04:57.272Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 0NFQxRQhr3aw |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.18048 (cs) [Submitted on 18 May 2026] Title:DocOS: Towards Proactive Document-Guided Actions in GUI Agents Authors:Jingjing Liu, Ziye Huang, Zihao Cheng, Zeming Liu, Jiahong Wu, Yuhang Guo, Kehai Chen, Yunhong Wang, Haifeng Wang View a PDF of the paper titled DocOS: Towards Proactive Document-Guided Actions in GUI Agents, by Jingjing Liu and 8 other authors View PDF HTML (experimental) Abstract:While Graphical User Interface (GUI) agents have shown promising performance in automated device interaction, they primarily depend on static parametric knowledge from pre-training or instruction tuning.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
