HuggingFace Daily Papers（社区热门论文）· HuggingFace Daily Papers（社区热门论文）·· 6 天前AI 评分35
GraphForge：用图锚定工作区合成训练工作型智能体
AI 导读
GraphForge 是一个基于证据图的工作型智能体训练数据合成框架，从职业种子出发为每个种子组装真实文件工作区，并基于文件关系构建证据图，使任务描述与评分标准都由该图派生、每条标准锚定到可验证的文件。
正文
Authors:Qisheng Su, Hanchen Wang, Guanru Zhu, Huicheng Jiang, Qiuyinzhe Zhang, Kou Shi, Zhen Fang, Ziao Zhang, Qingnan Ren, Zehui Chen, Tao Gui, Feng Zhao
Abstract:Working agents need to read diverse files, coordinate tools, and produce deliverables. Training such agents requires tasks built on many real files with verifiable results, but few pipelines exist to synthesize this kind of data. Existing pipelines either generate files with models, which lack realism and diversity, or build tasks on real files without task-specific verifiers, leaving result quality unchecked. We introduce GraphForge, an evidence-graph based framework that grounds both the task and its verification in real files. Starting from occupation-grounded seeds for controlled diversity, GraphForge assembles a workspace of real files for each seed and builds an evidence graph over their relations. Since the task statement and rubrics are both derived from this graph, task requirements are backed by the workspace files and each criterion is anchored to the files needed to verify it. An initial rollout further tests executability, and a revision agent repairs the task and rubrics against the original files before trajectories are collected. Fine-tuning Qwen3.6-27B on 2,169 GraphForge trajectories brings GDPVal to 1445.7 (+65.7) under OpenHands, and Workspace-Bench-Lite and SpreadsheetBench II to 63.7 (+7.7) and 24.0 (+13.7) under Claude Code. Rejection fine-tuning on the SFT model's own rollouts, with candidates selected by the evidence-anchored rubrics, yields further improvements on all three benchmarks, suggesting that the rubrics provide a useful selection signal. The data and models are available.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2609.38923 [cs.CL] |
| (or arXiv:2609.38923v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.38923 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Qisheng Su [view email]
[v1]
Wed, 30 Sep 2026 04:07:17 UTC (340 KB)
来源：HuggingFace Daily Papers（社区热门论文） · arxiv.org