# ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training

arXiv: https://arxiv.org/abs/2602.06820 · HTML: https://mlsanity.com/paper/2602.06820/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 32 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 25 of 25)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [ToolACE: Winning the Points of LLM Function Calling](https://mlsanity.com/paper/2409.00920/) (2024)
- [APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay](https://mlsanity.com/paper/2504.03601/) (2025)
- [Feedback Loops With Language Models Drive In-Context Reward Hacking](https://mlsanity.com/paper/2402.06627/) (2024)
- [ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay](https://mlsanity.com/paper/2505.16282/) (2025)
- [EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis](https://mlsanity.com/paper/2601.05808/) (2026)
- [Simulating Environments with Reasoning Models for Agent Training](https://mlsanity.com/paper/2511.01824/) (2025)
- [Towards General Agentic Intelligence via Environment Scaling](https://mlsanity.com/paper/2509.13311/) (2025)
- [Scaling Agent Learning via Experience Synthesis](https://mlsanity.com/paper/2511.03773/) (2025)
- [EvilGenie: A Reward Hacking Benchmark](https://mlsanity.com/paper/2511.21654/) (2025)
- [Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments](https://mlsanity.com/paper/2508.08791/) (2025)
- [ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web](https://mlsanity.com/paper/2601.08276/) (2026)

## Built on by (most cited first, 30 of 32)

- [Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence](https://mlsanity.com/paper/2604.18292/) (2026)
- [Qwen-AgentWorld: Language World Models for General Agents](https://mlsanity.com/paper/2606.24597/) (2026)
- [Recursive Synthesis for Long-Horizon Terminal Tasks](https://mlsanity.com/paper/2608.05466/) (2026)
- [SETA: Scaling Environments for Terminal Agents](https://mlsanity.com/paper/2607.10891/) (2026)
- [SPADE: Self-Play in Adaptive Synthetic Executable Environments](https://mlsanity.com/paper/2608.19197/) (2026)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments](https://mlsanity.com/paper/2605.27209/) (2026)
- [Bridging the Agent-World Gap: Text World Models for LLM-based Agents](https://mlsanity.com/paper/2606.09032/) (2026)
- [SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation](https://mlsanity.com/paper/2607.05943/) (2026)
- [Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence](https://mlsanity.com/paper/2608.31075/) (2026)
- [TRACE: Capability-Targeted Agentic Training](https://mlsanity.com/paper/2604.05336/) (2026)
- [What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents](https://mlsanity.com/paper/2608.27260/) (2026)
- [RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents](https://mlsanity.com/paper/2606.19047/) (2026)
- [EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning](https://mlsanity.com/paper/2608.06197/) (2026)
- [Apodex 1.1: Scaling Agentic Intelligence for Complex Work](https://mlsanity.com/paper/2608.23283/) (2026)
- [AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories](https://mlsanity.com/paper/2609.05837/) (2026)
- [EnvCraft: Synthesizing Executable Environments in Agentic RL for Claw-like Agent](https://mlsanity.com/paper/2609.05576/) (2026)
- [AgentOmnia: Scaling Agentic Models for Full-Scenario Applications](https://mlsanity.com/paper/2607.23124/) (2026)
- [Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks](https://mlsanity.com/paper/2609.08404/) (2026)
- [Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms](https://mlsanity.com/paper/2609.27321/) (2026)
- [CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning](https://mlsanity.com/paper/2609.32750/) (2026)
- [CompoWorld: Compositional Environment Scaling for General Agents](https://mlsanity.com/paper/2609.33665/) (2026)
- [WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents](https://mlsanity.com/paper/2609.36887/) (2026)
- [Scaling Verifiable Environments for Long-horizon Work Agents](https://mlsanity.com/paper/2610.04906/) (2026)
- [ClawLoop: Self-Improving Agents via Harness-Native Training Loop](https://mlsanity.com/paper/2610.14118/) (2026)
- [AutoEnvScaling: Automating the Data Flywheel with Terminal Agents](https://mlsanity.com/paper/2610.14163/) (2026)
- [ProgAgent: Learning Tool Orchestration through Programmatic Training](https://mlsanity.com/paper/2610.14774/) (2026)
- [Recursive Environment Scaling for General Long-Horizon Agents](https://mlsanity.com/paper/2610.16397/) (2026)
- [EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents](https://mlsanity.com/paper/2610.16523/) (2026)
- [Agent-Reflex: Teaching Language Agents to Act Reflectively](https://mlsanity.com/paper/2610.17953/) (2026)

## Abstract (arXiv)

Training generalist agents capable of adapting to diverse scenarios requires interactive environments for self-exploration. However, interactive environments remain critically scarce, and existing synthesis methods suffer from significant limitations regarding environmental diversity and scalability. To address these challenges, we introduce ScaleEnv, a framework that constructs fully interactive environments and verifiable tasks entirely from scratch. Specifically, ScaleEnv ensures environment reliability through procedural testing, and guarantees task completeness and solvability via tool dependency graph expansion and executable action verification. By enabling agents to learn through exploration within ScaleEnv, we demonstrate significant performance improvements on unseen, multi-turn tool-use benchmarks such as τ2-Bench and VitaBench, highlighting strong generalization capabilities. Furthermore, we investigate the relationship between increasing number of domains and model generalization performance, providing empirical evidence that scaling environmental diversity is critical for robust agent learning.