# SimVerity: When Does Simulated Agent Success Survive Physical Deployment?

arXiv: https://arxiv.org/abs/2608.25067 · HTML: https://mlsanity.com/paper/2608.25067/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [An Illusion of Progress? Assessing the Current State of Web Agents](https://mlsanity.com/paper/2504.01382/) (2025)
- [WorldGym: World Model as An Environment for Policy Evaluation](https://mlsanity.com/paper/2506.00613/) (2025)
- [MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control](https://mlsanity.com/paper/2410.17520/) (2024)
- [Formal Scenario-Based Testing of Autonomous Vehicles: From Simulation to the Real World](https://mlsanity.com/paper/2003.07739/) (2020)
- [Mind the Gap! A Study on the Transferability of Virtual vs Physical-world Testing of Autonomous Driving Systems](https://mlsanity.com/paper/2112.11255/) (2021)
- [Rethinking Sim2Real: Lower Fidelity Simulation Leads to Higher Sim2Real Transfer in Navigation](https://mlsanity.com/paper/2207.10821/) (2022)
- [Can Offline Testing of Deep Neural Networks Replace Their Online Testing?](https://mlsanity.com/paper/2101.11118/) (2021)
- [HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devices](https://mlsanity.com/paper/2505.19628/) (2025)
- [SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM Agents](https://mlsanity.com/paper/2509.24282/) (2025)
- [BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks](https://mlsanity.com/paper/2604.24955/) (2026)
- [SAGE: Smart home Agent with Grounded Execution](https://mlsanity.com/paper/2311.00772/) (2023)
- [Predicting LLM Safety Before Release by Simulating Deployment](https://mlsanity.com/paper/2607.07184/) (2026)
- [A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs](https://mlsanity.com/paper/2505.23816/) (2025)
- [How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation under the One-Time-Pad-Based Framework](https://mlsanity.com/paper/2507.19219/) (2025)
- [When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents](https://mlsanity.com/paper/2605.11928/) (2026)
- [AgentSense: Virtual Sensor Data Generation Using LLM Agents in Simulated Home Environments](https://mlsanity.com/paper/2506.11773/) (2025)
- [SMH-Bench: Benchmarking LLM Agents for Environment-Grounded Reasoning and Action in Smart Homes](https://mlsanity.com/paper/2606.01912/) (2026)
- [Confirmation bias: A challenge for scalable oversight](https://mlsanity.com/paper/2507.19486/) (2025)
- [S5-HES Agent: Society 5.0-driven Agentic Framework to Democratize Smart Home Environment Simulation](https://mlsanity.com/paper/2603.01554/) (2026)
- [HomeFlow: A Data Flywheel for Smart Home Agent Training with Verifiable Simulation](https://mlsanity.com/paper/2606.01230/) (2026)
- [Validate the Dream Before You Trust Its Verdict: Admissibility for World-Model Simulators](https://mlsanity.com/paper/2607.07196/) (2026)
- [The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective](https://mlsanity.com/paper/2606.07017/) (2026)

## Abstract (arXiv)

Simulated evaluation is widely used to benchmark AI agents, yet how much evidence a simulated pass provides about physical deployment has not been systematically quantified. We present SimVerity, a verdict-transfer assurance framework: it replays matched scenarios on target smart home deployments and cross-validates agent execution against independently qualified physical witnesses. Our evaluation highlights that deployment success is a real-world process, not a static property in simulation: completion, reported state, observable effect, and settled outcome diverged within the same execution. Although an advanced simulator cleared all 240 light trials, a camera caught 42 sub-second failures invisible to settled-state checks. False clearance was predictable: a risk profile learned from measured trials and locked before evaluation predicted failures on a path it never physically measured, beating a property-blind baseline in all eleven held-out sessions across two cohorts. Agent auditability was also measurable: switching one agent loop's model-client/serving configuration raised its scenario-matching share from 52-88% to 100%. Finally, a second qualified simulator added no independent cross-check: it never disagreed on any overlapping case, and only physical measurement exposed their shared blind spots. SimVerity turns verdict transfer into an explicit decision: clear, abstain, or escalate before deployment.