# EnterpriseBench Corecraft: Training Generalizable Agents on High-Fidelity RL Environments

arXiv: https://arxiv.org/abs/2602.16179 · HTML: https://mlsanity.com/paper/2602.16179/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 35 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 30)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents](https://mlsanity.com/paper/2401.13178/) (2024)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks](https://mlsanity.com/paper/2412.14161/) (2024)
- [Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration](https://mlsanity.com/paper/1802.08802/) (2018)
- [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023)
- [Survey on Evaluation of LLM-based Agents](https://mlsanity.com/paper/2503.16416/) (2025)
- [Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback](https://mlsanity.com/paper/2406.09279/) (2024)
- [T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step](https://mlsanity.com/paper/2312.14033/) (2023)
- [The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution](https://mlsanity.com/paper/2510.25726/) (2025)
- [AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following](https://mlsanity.com/paper/2511.10507/) (2025)
- [Measuring Agents in Production](https://mlsanity.com/paper/2512.04123/) (2025)
- [Agent-R1: A Unified and Modular Framework for Agentic Reinforcement Learning](https://mlsanity.com/paper/2511.14460/) (2025)

## Built on by (most cited first, 8 of 8)

- [Auditing Reward Hackability in Code RL Training Environments](https://mlsanity.com/paper/2606.16062/) (2026)
- [ComplexConstraints and Beyond: Expert Rubrics for RLVR](https://mlsanity.com/paper/2606.09118/) (2026)
- [HealthCraft: A Reinforcement Learning Safety Environment for Emergency Medicine](https://mlsanity.com/paper/2605.21496/) (2026)
- [Cross-Benchmark Generalization in Long-Horizon Agents](https://mlsanity.com/paper/2608.00181/) (2026)
- [Post-Training on Office Work Improves Software Engineering: A Behavioral Account of Cross-Domain Transfer](https://mlsanity.com/paper/2608.01604/) (2026)
- [Explain Like I'm 5 or Whatever I Choose: Evaluating the Potential for Interactive Complexity in Language Model Responses](https://mlsanity.com/paper/2606.06788/) (2026)
- [Cross-Benchmark Transfer from RL on Agentic Coding Tasks](https://mlsanity.com/paper/2610.00890/) (2026)
- [DAYJOB: A Benchmark for Long-Horizon Professional Work](https://mlsanity.com/paper/2610.01306/) (2026)

## Abstract (arXiv)

We show that training AI agents on high-fidelity reinforcement learning environments produces capabilities that generalize beyond the training distribution. We introduce CoreCraft, the first environment in EnterpriseBench, Surge AI's suite of agentic RL environments. CoreCraft is a fully operational enterprise simulation of a customer support organization, comprising over 2,500 entities across 14 entity types with 23 unique tools, designed to measure whether AI agents can perform the multi-step, domain-specific work that real jobs demand. Frontier models such as GPT-5.2 and Claude Opus 4.6 solve fewer than 30% of tasks when all expert-authored rubric criteria must be satisfied. Using this environment, we train GLM 4.6 with Group Relative Policy Optimization (GRPO) and adaptive clipping. After a single epoch of training, the model improves from 25.37% to 36.76% task pass rate on held-out evaluation tasks. More importantly, these gains transfer to out-of-distribution benchmarks: +4.5% on BFCL Parallel, +7.4% on Tau2-Bench Retail, and +6.8% on Tool Decathlon (Pass@1). We believe three environment properties are consistent with the observed transfer: task-centric world building that optimizes for diverse, challenging tasks; expert-authored rubrics enabling reliable reward computation; and enterprise workflows that reflect realistic professional patterns. Our results suggest that environment quality, diversity, and realism are key factors enabling generalizable agent capabilities.