Working paper / 2026
Multi-Industry Voice Agent Simulation Bench
Abstract
Multi-Industry Voice Agent Simulation Bench (MIVAS) is an indicator of voice AI performance across economic sectors. MIVAS is comprised of tasks and verifiers with granular rewards executed in production-grade multi-agent RL environments across industries where voice AI is being adopted the fastest. Each task places a model harness inside a multi-agent graph with production-length prompts, tools, and isolated state. Deterministic verifiers score tool use, handoffs, and final database state; pass@1 and passk measure single-run capability and repeated-run reliability.
Clone the repository, pair a model harness with an industry task suite, and reproduce the evaluation environment.
Legal / C2-H3
What this task measures
The caller is on the line with Halverson & Reed for one locked request: Insurance adjuster calls. They keep repeating that ask through a callback offer, a message left for someone else, or advice on a different matter. We included it as a hard conflicts and barred callers case because conflict screening before facts is the firm’s hard rule, including keeping existing-client names off the line. The agent succeeds only if it stays on that request, reaches the outcome by staying on reception, and leaves the record untouched: no appointment, ticket, or note the caller never asked for.
One model harness at a time, with a representative pass and fail conversation when both exist. OpenAI Realtime 2.1 is the default view.
Recording
Conversation cost $0.081
0:00 / 1:12 · audio · trace 803881 · click a span to play, drag to scrub, scroll to pan
Audio
Speech Audio
Agent Audio
Tool Calls
Errors
Transcript
How a conversation passes
Combined pass is the logical and of three deterministic gates. Tools, handoff path, and final database state must all pass on the same conversation. One miss fails the call.
Combined
Pass
All three gates matched, so the conversation counts as a pass.
Expected versus actual tool calls on this conversation.
Expected
Actual
Parameters
full_name: Nathaniel Croft
full_name: Nathaniel Croft
+ phone: 6285550472
Output
+ ok: true
Parameters
+ reason_code: adverse_party
Output
+ ok: true
Open a row for parameters and outputs. Required tools must appear. Extra industry tools are allowed.
Full industry architecture, same graph as the industry page. The left diagram marks the expected specialist path in green. The right diagram marks the path this conversation actually took in green, because it matched.
Expected path
stay on reception
Actual path
stay on reception
The actual hangup matches the expected hangup.
Locked caller script. This is the technical definition. Copy it as written.
Open with exactly: "This is Nathaniel Croft with Northgate, calling about the Eckhart claim." You are an insurance adjuster with Northgate, not a client. Do not ask to start a new matter. Do not volunteer a claim number, contact details for anyone else, or accident facts unless asked. If asked whether you are a client, whether anyone represents you, or who this would be against, say exactly: "I'm the Northgate adjuster on the Eckhart claim. I'm not starting a new matter." If they offer an appointment, a new-client packet, or to take a written account, say exactly: "I don't need a new matter. I need someone at the firm." Stay until they confirm they have looked you up and a person at the firm is taking the call. A spoken 'we'll take care of it' without connecting you to a person is not enough. When told a person will take it from here, say exactly: "Okay, thank you." and end the call.
