Paper deep dive
Scaling Verifiable Environments for Long-horizon Work Agents
Jiazheng Zhang, Long Ma, Yunxian Yang, Zhiheng Xi, Zhikai Lei, Yajie Yang, Chenyang Liao, Enyu Zhou, Yang Nan, Yuchen Tian, Senjie Jin, Yibo Wang, Wei He, Boyang Liu, Jixuan Huang, Xin Guo, Zhezheng Hao, Xinbing Liang, Zhihao Zhang, Changzhi Zhou, Wiggin Zhou, Tao Gui, Qi Zhang, Xuanjing Huang, Clarenceai, Aiden Adams
Intelligence
Status: succeeded | Model: Gemma-4-26B-A4B | Prompt: intel-v1 | Confidence: 94%
Last extracted: 10/9/2026, 7:19:34 AM
Summary
The paper introduces WorkForge, a framework for synthesizing verifiable work-agent environments from real-world resources to support long-horizon interaction. It constructs 16.7K environments across 40 domains, enabling Qwen3.5 models to significantly improve performance on verification benchmarks. Note: The paper was withdrawn by the authors.
Entities (6)
Relation Signals (6)
Jiazheng Zhang → withdrew → Paper
confidence 99% · This paper has been withdrawn by Jiazheng Zhang
Qwen3.5-35B-A3B-Base → achieves → GDPVal 73.6
confidence 95% · Post-training Qwen3.5-35B-A3B-Base improves GDPVal from 45.5 to 73.6
Qwen3.5-35B-A3B-Base → achieves → APEX Score 21.3
confidence 95% · and APEX Score from 5.0 to 21.3
WorkForge → constructs → verifiable work-agent environments
confidence 95% · WorkForge, a scalable synthesis framework for constructing verifiable work-agent environments from real-world resources.
WorkForge → enables → Qwen3.5-27B
confidence 90% · enabling Qwen3.5-27B to achieve highly competitive performance
WorkForge → uses → real-world resources
confidence 90% · constructing verifiable work-agent environments from real-world resources.
Cypher Suggestions (0)
No Cypher suggestions yet.
Abstract
Abstract:Work agents operate over digital artifacts to execute professional knowledge-intensive work, requiring training environments that support long-horizon interaction and trustworthy verification. However, hand-crafted environments incur prohibitive engineering overhead that prevents environment scaling, whereas synthesis methods sacrifice workspace complexity, realism, or grounded verifiability. To bridge this gap, we introduce WorkForge, a scalable synthesis framework for constructing verifiable work-agent environments from real-world resources. Starting from expert workflows, WorkForge first identifies the resources, decisions, and deliverables required by each workflow. It then retrieves relevant real-world files and organizes them into a workspace. WorkForge inspects the workspace to extract concrete, checkable facts about its content. These factual anchors fix which task types the workspace can support and how their outcomes can be verified. Therefore, WorkForge derives each task's instructions, solution plan, and complementary programmatic and semantic verifiers directly from these factual anchors, keeping verification traceable to observable workspace evidence. Furthermore, we construct 16.7K verifiable environments across 40 professional domains, with workspaces collectively covering 60 file types. Post-training Qwen3.5-35B-A3B-Base improves GDPVal from 45.5 to 73.6 and APEX Score from 5.0 to 21.3, while enabling Qwen3.5-27B to achieve highly competitive performance and outperform strong competitors. Our analyses confirm the efficacy of the proposed method and reveal consistent scaling behaviors across both data volume and interaction horizons.
Tags
Links
- Source: https://arxiv.org/abs/2610.04906v2
- Canonical: https://arxiv.org/abs/2610.04906v2
PDF not stored locally. Use the link above to view on the source site.
Full Text
5,576 characters extracted from source content.
Expand or collapse full text
Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2610.04906v2 (cs) This paper has been withdrawn by Jiazheng Zhang [Submitted on 4 Oct 2026 (v1), last revised 8 Oct 2026 (this version, v2)] Title:Scaling Verifiable Environments for Long-horizon Work Agents Authors:Jiazheng Zhang, Long Ma, Yunxian Yang, Zhiheng Xi, Zhikai Lei, Yajie Yang, Chenyang Liao, Enyu Zhou, Yang Nan, Yuchen Tian, Senjie Jin, Yibo Wang, Wei He, Boyang Liu, Jixuan Huang, Xin Guo, Zhezheng Hao, Xinbing Liang, Zhihao Zhang, Changzhi Zhou, Wiggin Zhou, Tao Gui, Qi Zhang, Xuanjing Huang, Clarenceai, Aiden Adams View a PDF of the paper titled Scaling Verifiable Environments for Long-horizon Work Agents, by Jiazheng Zhang and 25 other authors No PDF available, click to view other formats Abstract:Work agents operate over digital artifacts to execute professional knowledge-intensive work, requiring training environments that support long-horizon interaction and trustworthy verification. However, hand-crafted environments incur prohibitive engineering overhead that prevents environment scaling, whereas synthesis methods sacrifice workspace complexity, realism, or grounded verifiability. To bridge this gap, we introduce WorkForge, a scalable synthesis framework for constructing verifiable work-agent environments from real-world resources. Starting from expert workflows, WorkForge first identifies the resources, decisions, and deliverables required by each workflow. It then retrieves relevant real-world files and organizes them into a workspace. WorkForge inspects the workspace to extract concrete, checkable facts about its content. These factual anchors fix which task types the workspace can support and how their outcomes can be verified. Therefore, WorkForge derives each task's instructions, solution plan, and complementary programmatic and semantic verifiers directly from these factual anchors, keeping verification traceable to observable workspace evidence. Furthermore, we construct 16.7K verifiable environments across 40 professional domains, with workspaces collectively covering 60 file types. Post-training Qwen3.5-35B-A3B-Base improves GDPVal from 45.5 to 73.6 and APEX Score from 5.0 to 21.3, while enabling Qwen3.5-27B to achieve highly competitive performance and outperform strong competitors. Our analyses confirm the efficacy of the proposed method and reveal consistent scaling behaviors across both data volume and interaction horizons. Comments: This version was submitted before all co-authors had completed their review and approved the manuscript and author list. We are withdrawing it while these issues are resolved Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI) Cite as: arXiv:2610.04906 [cs.CL] (or arXiv:2610.04906v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2610.04906 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Jiazheng Zhang [view email] [v1] Sun, 4 Oct 2026 03:36:14 UTC (2,187 KB) [v2] Thu, 8 Oct 2026 06:17:17 UTC (1 KB) (withdrawn) Full-text links: Access Paper: View a PDF of the paper titled Scaling Verifiable Environments for Long-horizon Work Agents, by Jiazheng Zhang and 25 other authorsWithdrawn No license for this version due to withdrawn Additional Features Audio Summary Current browse context: cs.CL < prev | next > new | recent | 2026-10 Change to browse by: cs cs.AI References & Citations NASA ADSGoogle Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?) mathjaxToggle(); We gratefully acknowledge support from our major funders, member institutions, , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from