{"slug": "fde-gym-the-last-mile-of-ai-delivery", "title": "FDE-Gym: The Last Mile of AI Delivery", "summary": "A new arXiv paper submitted 15 Oct 2026 introduces FDE-Gym, a benchmark of 95 end-to-end delivery tasks drawn from 20 customer scenarios across 18 sectors, built to test forward-deployed engineers' ability to clarify ambiguous requirements and uncover unstated constraints in live systems. Evaluating 13 model configurations from seven providers, the best configuration scored a mean FDE-Gym score of 0.56 and resolved only 14 of the 95 tasks, with discovering unstated constraints identified as the primary bottleneck. Even on the 23 tasks where the best configuration obtained every key fact from stakeholders, it reached a normalized business uplift of 0.8 or above on only 10, revealing a substantial gap between solving well-specified tasks and delivering effective AI systems for real customers.", "body_md": "# Computer Science > Artificial Intelligence\n\n  [Submitted on 15 Oct 2026]\n\n# Title:FDE-Gym: The Last Mile of AI Delivery\n\n[View PDF](http://arxiv.org/pdf/2610.22350v1)\n\n[HTML (experimental)](https://arxiv.org/html/2610.22350v1)\n\nAbstract:Existing agent benchmarks typically evaluate agents on well-specified tasks defined by issue reports, specifications, or task tickets. Real-world customer delivery is different: forward-deployed engineers (FDEs) must clarify ambiguous requirements, work in live systems, and uncover unstated constraints. We introduce FDE-Gym, a benchmark of 95 end-to-end delivery tasks from 20 customer scenarios across 18 sectors, each adapted by industry experts from real-world delivery projects. In simulated customer environments with scripted stakeholders and modifiable customer systems, agents interact with stakeholders and operate on production-like systems to deliver working solutions. FDE-Gym scores a delivery by how much it improves the customer's own success metric, normalized between 0 (unchanged system) and 1 (reference solution), with penalties for stakeholder interactions (messages, trial runs, and waiting time). An online platform lets humans practice FDE skills under the same grading criteria. We evaluate 13 model configurations from seven providers. In the realistic setting, where unstated constraints must be discovered, the best configuration achieves a mean FDE-Gym score of 0.56 and resolves only 14 of the 95 tasks (a score of at least 0.8 with no incident). Discovering unstated constraints is the primary bottleneck: performance drops sharply when models must uncover them without explicit guidance. Yet information discovery alone does not account for the gap: even on the 23 tasks where the best configuration obtains every key fact from stakeholders, it reaches a normalized business uplift of 0.8 or above on only 10. These results reveal a substantial gap between solving well-specified tasks and delivering effective AI systems for real customers.\n    \n\n### Additional Features\n\n### Current browse context:\n\ncs.AI\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/fde-gym-the-last-mile-of-ai-delivery", "canonical_source": "http://arxiv.org/abs/2610.22350v1", "published_at": "2026-10-16 15:20:07+00:00", "updated_at": "2026-10-16 15:48:21.657332+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "large-language-models"], "entities": ["FDE-Gym", "arXiv", "cs.AI"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/fde-gym-the-last-mile-of-ai-delivery", "markdown": "https://wpnews.pro/news/fde-gym-the-last-mile-of-ai-delivery.md", "text": "https://wpnews.pro/news/fde-gym-the-last-mile-of-ai-delivery.txt", "jsonld": "https://wpnews.pro/news/fde-gym-the-last-mile-of-ai-delivery.jsonld"}}