EnvSimBench: A Benchmark for Evaluating and Improving LLM-Based Environment Simulation

TL;DR

EnvSimBench is a comprehensive benchmark designed to evaluate and enhance the ability of LLMs to accurately simulate environments, addressing hallucinations and inconsistencies that hinder scalable AI agent training.

Contribution

It introduces the first formal EnvSim Ability metric, a diverse benchmark dataset, and a constraint-driven pipeline to improve LLM-based environment simulation fidelity and efficiency.

Findings

All state-of-the-art LLMs struggle with multi-state updates, achieving high accuracy only on invariant states.

The proposed pipeline reduces hallucinations and increases environment synthesis yield by 6.8%.

The approach cuts simulation costs by over 90%.

Abstract

Scalable AI agents training relies on interactive environments that faithfully simulate the consequences of agent actions. Manually crafted environments are expensive to build, brittle to extend, and fundamentally limited in diversity. A promising direction is to replace manually crafted environments with LLM-simulated counterparts. However, this paradigm hinges on an unexamined core assumption: LLMs can accurately simulate environmental feedback. In practice, LLM-simulated environments suffer from hallucinations, logical inconsistencies, and silent state drift failures that corrupt agent reward signals and compound the construction costs that the paradigm was designed to eliminate. To address this gap, we propose EnvSimBench with four contributions: 1) We provide the first formal definition and operationalization of Environment Simulation Ability (EnvSim Ability) as a quantifiable research objective. 2) We construct EnvSimBench, a rigorous benchmark covering 400 samples across 167 diverse environments, equipped with verifiable labels and fine-grained difficulty stratification along three axes. 3) Systematic evaluations reveal that all state-of-the-art language models suffer from a universal state change cliff: they achieve near-perfect accuracy on tasks when the environment state remains invariant, yet fail catastrophically when multiple states need simultaneous updates. This finding exposes EnvSim Ability as a critical yet largely unaddressed capability gap. 4) We design a constraint-driven simulation pipeline that substantially reduces hallucination, boosts environment synthesis yield by 6.8%, and cuts costs by over 90%. Overall, EnvSimBench serves as both a diagnostic framework and a practical optimization path for reliable LLM-based environment simulation, establishing a foundation for scalable agent training. Code and data are available at https://github.com/cookieApril/EnvSimBench