AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale

• URL: http://arxiv.org/abs/2608.20634v1
• Date: Fri, 21 Aug 2026 00:15:45 GMT
• Title: AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale
• Abstract summary: We introduce AgentMercury, a framework for synthesizing executable environments from high-level business scenarios.<n>We construct 4,783 executable environments spanning 14 industries and 50 countries, and use them as training substrates for reinforcement learning.<n>We show that fine-tuning Qwen3.5-35B-A3B on construction traces increases executable authoring success from 3.3% to 83.3% on held-out business scenarios.
• Score: 6.489568846701505
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Agents learn to act through interaction with environments, yet the environments used for training are often manually constructed or synthesized around predefined tasks and benchmarks. This task-centric paradigm makes it difficult to scale environments that reflect realistic and evolving workflows where diverse tasks can naturally emerge from the underlying world. We introduce AgentMercury, a scalable framework for synthesizing executable environments from high-level business scenarios. Rather than constructing an environment for a specific task, AgentMercury first instantiates a persistent world with entities, services, tools, state, and executable cross-service invariants, from which diverse tasks and interaction trajectories can subsequently emerge. We construct 4,783 executable environments spanning 14 industries and 50 countries, and use them as training substrates for reinforcement learning. Despite being generated without targeting the evaluation benchmarks, policies trained on these business-oriented environments improve substantially on both enterprise workflows and out-of-domain benchmarks spanning reasoning, coding, scientific computing, and tool use. In our experiments, Qwen3.5-4B improves from 12.3 to 15.7 on EnterpriseOps-GYM and from 45.9 to 56.0 on AIME26 after training on AgentMercury environments. We further show that the construction process itself can be learned: fine-tuning Qwen3.5-35B-A3B on construction traces increases executable-world authoring success from 3.3% to 83.3% on held-out business scenarios. These results show that scenario-grounded environments can provide useful and generalizable learning signals beyond benchmark-specific training, while their construction can itself become a learnable capability.

Related papers

• State2State: Environment-Derived Mid-Training for LLM Agents [67.08889234341996]
  We study an environment learning paradigm in which agents acquire interaction and manipulation capabilities solely through environment interaction.<n>We propose State2State, an environment-derived mid-training method that converts explored environment states into training objectives.<n> Experiments on ALFWorld and ScienceWorld show that State2State improves agent performance as a standalone environment-learning stage in most settings.
  arXiv  Detail & Related papers  (2026-08-05T15:02:41Z)
• Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization [93.59040719904154]
  This paper introduces RACES (textbfRecursive textbfAutomated textbfComposition for textbfEnvironment textbfScaling), a framework that conceptualizes verifiable environments as composable building blocks.<n> RACES is implemented with 300 individual environments and defines a set of composition operators that induce diverse reasoning patterns.
  arXiv  Detail & Related papers  (2026-06-10T17:39:41Z)
• Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence [122.8626256816085]
  textbfAgent-World is a self-evolving training arena for advancing general agent intelligence through scalable environments.<n>Agent-World-8B and 14B consistently outperforms strong proprietary models and environment scaling baselines.
  arXiv  Detail & Related papers  (2026-04-20T14:01:10Z)
• TRACE: Capability-Targeted Agentic Training [11.088296897059157]
  We introduce TRACE, an end-to-end system for environment-specific agent self-improvement.<n>TRACE contrasts successful and failed trajectories to identify lacking capabilities.<n>It synthesizes a targeted training environment for each that rewards whether the capability was exercised.<n>It trains a LoRA adapter via RL on each synthetic environment, routing to the relevant adapter at inference.
  arXiv  Detail & Related papers  (2026-04-07T02:22:44Z)
• EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings [8.341628877927244]
  We introduce EnterpriseOps-Gym, a benchmark designed to evaluate agentic planning in realistic enterprise settings.<n>Within this environment, agents are evaluated on 1,150 expert-curated tasks across eight mission-critical verticals.<n>Our evaluation of 14 frontier models reveals critical limitations in state-of-the-art models.
  arXiv  Detail & Related papers  (2026-03-13T21:09:39Z)
• EnterpriseBench Corecraft: Training Generalizable Agents on High-Fidelity RL Environments [0.10934862523101825]
  We show that training AI agents on high-fidelity reinforcement learning environments produces capabilities that generalize beyond the training distribution.<n>We introduce CoreCraft, the first environment in EnterpriseBench, Surge AI's suite of agentic RL environments.
  arXiv  Detail & Related papers  (2026-02-18T04:35:46Z)
• Autonomous Continual Learning of Computer-Use Agents for Environment Adaptation [57.65688895630163]
  We introduce ACuRL, an Autonomous Curriculum Reinforcement Learning framework that continually adapts agents to specific environments with zero human data.<n>Our method effectively enables both intra-environment and cross-environment continual learning, yielding 4-22% performance gains without forgetting existing environments.
  arXiv  Detail & Related papers  (2026-02-10T23:06:02Z)
• 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)
• 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)
• WebArena: A Realistic Web Environment for Building Autonomous Agents [92.3291458543633]
  We build an environment for language-guided agents that is highly realistic and reproducible. We focus on agents that perform tasks on the web, and create an environment with fully functional websites from four common domains. We release a set of benchmark tasks focusing on evaluating the functional correctness of task completions.
  arXiv  Detail & Related papers  (2023-07-25T22:59:32Z)

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.