StagedWorkspace让AI智能体能追踪文件版本，在OfficeQA和APEX测试中大幅提升表现，比单一视图强很多。
StagedWorkspace是为知识工作智能体设计的版本化工作空间，解决了智能体在处理代码、文档等数字工件时的版本管理问题。在OfficeQA Pro和APEX-Agents基准测试中，双解析/原生访问方式将OfficeQA Pass@1提高了8.3-12.1分，APEX平均评分提高了4.7-9.2分。SW-AGENT在Gemini 3.1 Pro上获得63.9%的OfficeQA分数，在GPT-5.4 Nano上获得42.1的APEX分数，显著高于同模型的已发布分数。
StagedWorkspace: A Versioned Workspace for Knowledge-Work Agents
AI agents increasingly perform knowledge work (i.e., produce and modify persistent digital artifacts such as code repositories, documents, spreadsheets, slides, reports), yet the parsed views they search, the native files they edit, the changes they review, and the artifacts they submit can refer to different versions of the same work product. We formulate this as a workspace-state contract: every view should be explicitly tied to a version of the evolving workspace state. Coding agents partly address this need through repository contracts for search, diffs, and tests, whereas an analogous contract is less explicit for PDFs, spreadsheets, slides, notebooks, and mixed-format project folders. We propose StagedWorkspace, a versioned workspace for knowledge-work agents. The workspace binds parsed records and review diffs to content hashes of the native files as they change. In fixed-harness ablations on OfficeQA Pro and APEX-Agents, dual parsed/native access has the highest point estimate for every tested model; relative to the more limiting single view, it improves OfficeQA Pass@1 by 8.3-12.1 points and APEX mean rubric score by 4.7-9.2 points. SW-AGENT scores 63.9% with Gemini 3.1 Pro on OfficeQA and 42.1 with GPT-5.4 Nano on APEX, compared with published same-model scores of 29.3% and 25.5, respectively. A paired review-axis ablation on 57 file-editing tasks further finds higher observed scores when diffs are visible. These results identify workspace state as an experimental variable in knowledge-work agents and motivate benchmarks that score evidence, staged edits, and submitted artifacts as explicit state transitions.