app.build: A Production Framework for Scaling Agentic Prompt-to-App Generation with Environment Scaffolding

• URL: http://arxiv.org/abs/2509.03310v1
• Date: Wed, 03 Sep 2025 13:41:45 GMT
• Title: app.build: A Production Framework for Scaling Agentic Prompt-to-App Generation with Environment Scaffolding
• Authors: Evgenii Kniazev, Arseny Kravchenko, Igor Rekun, James Broadhead, Nikita Shamgunov, Pranav Sah, Pratik Nichite, Ivan Yamshchikov,
• Abstract summary: We present app.build, an open-source framework that improves LLM-based application generation through systematic validation and structured environments.<n>Our approach combines multi-layered validation pipelines, stack-specific orchestration, and model-agnostic architecture, implemented across three reference stacks.<n>We demonstrate that comprehensive validation achieves 73.3% viability rate with 30% reaching perfect quality scores, while open-weights models achieve 80.8% of closed-model performance when provided structured environments.
• Score: 0.09198412216120845
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We present app.build (https://github.com/appdotbuild/agent/), an open-source framework that improves LLM-based application generation through systematic validation and structured environments. Our approach combines multi-layered validation pipelines, stack-specific orchestration, and model-agnostic architecture, implemented across three reference stacks. Through evaluation on 30 generation tasks, we demonstrate that comprehensive validation achieves 73.3% viability rate with 30% reaching perfect quality scores, while open-weights models achieve 80.8% of closed-model performance when provided structured environments. The open-source framework has been adopted by the community, with over 3,000 applications generated to date. This work demonstrates that scaling reliable AI agents requires scaling environments, not just models -- providing empirical insights and complete reference implementations for production-oriented agent systems.

Related papers

• Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning [62.499592503950026]
  Large language model (LLM) have empowered autonomous agents to perform complex tasks that require multi-turn interactions with tools and environments.<n>We propose Agent World Model (AWM), a fully synthetic environment generation pipeline.<n>We scale to 1,000 environments covering everyday scenarios, in which agents can interact with rich toolsets.
  arXiv  Detail & Related papers  (2026-02-10T18:55:41Z)
• SWE-Universe: Scale Real-World Verifiable Environments to Millions [84.63665266236963]
  SWE-Universe is a framework for automatically constructing real-world software engineering (SWE) verifiable environments from GitHub pull requests (PRs)<n>We propose a building agent powered by an efficient custom-trained model to overcome the prevalent challenges of automatic building.<n>We demonstrate the profound value of our environments through large-scale agentic mid-training and reinforcement learning.
  arXiv  Detail & Related papers  (2026-02-02T17:20:30Z)
• A Lightweight Modular Framework for Constructing Autonomous Agents Driven by Large Language Models: Design, Implementation, and Applications in AgentForge [1.932555230783329]
  Lightweight, open-source Python framework designed to democratize the construction of LLM-driven autonomous agents.<n>AgentForge introduces three key innovations: (1) a composable skill abstraction that enables fine-grained task decomposition with formally defined input-output contracts, (2) a unified backend interface supporting seamless switching between cloud-based APIs and local inference engines, and (3) a declarative YAML-based configuration system that separates agent logic from implementation details.
  arXiv  Detail & Related papers  (2026-01-19T20:33:26Z)
• Semantic Caching and Intent-Driven Context Optimization for Multi-Agent Natural Language to Code Systems [0.0]
  We present a production-optimized multi-agent system designed to translate natural language queries into executable Python code for structured data analytics.<n>Unlike systems that rely on expensive frontier models, our approach achieves high accuracy and cost efficiency through three key innovations.<n>We describe the architecture, present empirical results from production deployment, and discuss practical considerations for deploying LLM-based analytics systems at scale.
  arXiv  Detail & Related papers  (2026-01-16T11:32:20Z)
• ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development [72.4729759618632]
  We introduce ABC-Bench, a benchmark to evaluate agentic backend coding within a realistic, executable workflow.<n>We curated 224 practical tasks spanning 8 languages and 19 frameworks from open-source repositories.<n>Our evaluation reveals that even state-of-the-art models struggle to deliver reliable performance on these holistic tasks.
  arXiv  Detail & Related papers  (2026-01-16T08:23:52Z)
• Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem [90.17610617854247]
  We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimize the production pipeline for agentic model.<n>ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering.<n>We release ROME, an open-source agent grounded by ALE and trained on over one million trajectories.
  arXiv  Detail & Related papers  (2025-12-31T14:03:39Z)
• SCUBA: Salesforce Computer Use Benchmark [63.66753028386581]
  SCUBA is a benchmark designed to evaluate computer-use agents on customer relationship management ( CRM) within the Salesforce platform.<n> SCUBA contains 300 task instances derived from real user interviews, spanning three primary personas, platform administrators, sales representatives, and service agents.<n>We benchmark a diverse set of agents under both zero-shot and demonstration-augmented settings.
  arXiv  Detail & Related papers  (2025-09-30T16:48:49Z)
• Scalable Engine and the Performance of Different LLM Models in a SLURM based HPC architecture [3.746889836344766]
  This work elaborates on a High performance computing architecture based on Simple Linux Utility for Resource Management (SLURM)<n> Dynamic resource scheduling and seamless integration of containerized have been leveraged to manage CPU, GPU, and memory efficiently in multi-node clusters.<n>The obtained results pave ways for significantly more efficient, responsive, and fault-tolerant LLM inference on large-scale HPC infrastructures.
  arXiv  Detail & Related papers  (2025-08-25T09:11:27Z)
• OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks [52.87238755666243]
  We present OmniEAR, a framework for evaluating how language models reason about physical interactions, tool usage, and multi-agent coordination in embodied tasks.<n>We model continuous physical properties and complex spatial relationships across 1,500 scenarios spanning household and industrial domains.<n>Our systematic evaluation reveals severe performance degradation when models must reason from constraints.
  arXiv  Detail & Related papers  (2025-08-07T17:54:15Z)
• LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools? [50.60770039016318]
  We present LiveMCPBench, the first comprehensive benchmark for benchmarking Model Context Protocol (MCP) agents.<n>LiveMCPBench consists of 95 real-world tasks grounded in the MCP ecosystem.<n>Our evaluation covers 10 leading models, with the best-performing model reaching a 78.95% success rate.
  arXiv  Detail & Related papers  (2025-08-03T14:36:42Z)
• MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models [76.72220653705679]
  We introduce MCPEval, an open-source framework that automates end-to-end task generation and deep evaluation of intelligent agents.<n> MCPEval standardizes metrics, seamlessly integrates with native agent tools, and eliminates manual effort in building evaluation pipelines.<n> Empirical results across five real-world domains show its effectiveness in revealing nuanced, domain-specific performance.
  arXiv  Detail & Related papers  (2025-07-17T05:46:27Z)
• SetupBench: Assessing Software Engineering Agents' Ability to Bootstrap Development Environments [2.184775414778289]
  We introduce setupbench, a benchmark that isolates the environment-bootstrap skill.<n>Our tasks span seven language ecosystems, five database engines, and multi-service orchestration scenarios.<n>We find low success rates across task categories, with particular challenges in repository setup (38.9-57.4%) and local database configuration (20.0-53.3%)
  arXiv  Detail & Related papers  (2025-07-11T22:45:07Z)
• Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky [0.0]
  Large language models (LLMs) are increasingly tasked with invoking enterprise APIs, yet they routinely falter when near-duplicate tools vie for the same user intent.<n>We introduce DiaFORGE, a disambiguation-centric, three-stage pipeline that synthesizes persona-driven, multi-turn dialogues.<n>On our benchmark DiaBENCH, models trained with DiaFORGE raise tool-invocation success by 27 pp over GPT-4o and by 49 pp over Claude-3.5-Sonnet, both under optimized prompting.
  arXiv  Detail & Related papers  (2025-07-04T06:49:02Z)
• An Integrated Platform for LEED Certification Automation Using Computer Vision and LLM-RAG [0.0]
  This paper presents an automated platform designed to streamline key aspects of LEED certification.<n>The platform integrates a PySide6-based user interface, a review Manager for process orchestration, and multiple analysis engines for credit compliance, energy modeling via EnergyPlus, and location-based evaluation.
  arXiv  Detail & Related papers  (2025-06-01T08:05:35Z)
• CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents [49.68117560675367]
  Crab is the first benchmark framework designed to support cross-environment tasks.<n>Our framework supports multiple devices and can be easily extended to any environment with a Python interface.<n>The experimental results demonstrate that the single agent with GPT-4o achieves the best completion ratio of 38.01%.
  arXiv  Detail & Related papers  (2024-07-01T17:55:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.