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.
Healthcare / C3-M4
What this task measures
The caller is on the line with Straus Dermatology for one locked request: UnitedHealthcare on an existing Brooklyn Heights chart. They keep repeating that ask through a waitlist offer, a callback, or a different errand. We included it as a medium coverage and benefits case because carrier answers have to stay tied to one office and one plan, naming that location and that carrier. The agent succeeds only if it stays on that request, reaches the outcome by taking the coverage desk path, 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 $0.615
0:00 / 8:08 · audio · trace 801876 · click a span to play, drag to scrub, scroll to pan
Audio
Speech Audio
Agent Audio
Handoffs
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
+ from: reception
+ to: coverage
Output
None recorded.
None recorded.
Parameters
+ location_id: loc_brooklyn_heights
Output
+ ok: true
Parameters
carrier: unitedhealthcare
carrier: unitedhealthcare
location_id: loc_brooklyn_heights
location_id: loc_brooklyn_heights
+ provider_id: prov_chen
Output
- data: {"accepted":true}ok: true
ok: true
Open a row for parameters and outputs. Required tools must appear. Extra industry tools are allowed. Extra: list_locations.
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
transfer_to_coverage
Actual path
transfer_to_coverage
The actual hangup matches the expected hangup.
Locked caller script. This is the technical definition. Copy it as written.
You are an existing Straus patient. Ask whether they still take UnitedHealthcare at the Brooklyn Heights office specifically, not a yes for the whole practice. Stay until they have looked that up for Brooklyn Heights. If they ask for your name and date of birth, answer once and confirm if they read it back. If they say acceptance depends on the provider, or they name Doctor Chen, Doctor Ruiz, or Doctor Patel, tell them you do not have a provider yet and you still need that office-level yes or no; do not pick a provider and do not agree to wait until you book. If they offer a callback instead of a lookup, decline and stay on that office question. Once they have given you a yes or no that names that office, thank them and end the call. Do not ask to book, reschedule, or cancel. Do not ask to add or change insurance. Do not ask for a callback, to speak to a person, a bill, a payment, the patient portal, a waitlist, a text, financing, or the street, floor, or suite. A spoken yes for the whole practice is not enough. Stay until they have looked up whether that office takes UnitedHealthcare; a guess without a lookup is not enough. Do not ask them to text you an appointment confirmation.