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 / C1-H4
What this task measures
The caller is on the line with Straus Dermatology for one locked request: Hours, parking, UnitedHealthcare, then a Brooklyn Heights booking. They keep repeating that ask through a waitlist offer, a callback, or a different errand. We included it as a hard new patient access case because first-contact dermatology work is scored on holding a narrow office question through booking offers, waitlists, and extra yeses. The agent succeeds only if it stays on that request, reaches the outcome by following the coverage desk then scheduling path, and leaves the record exactly as this case requires: the right row written or cleared, and nothing extra.
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 $0.128
0:00 / 1:27 · audio · trace 801736 · 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
Fail
This sample fails because tools and handoff path and final database state did not match. Combined cannot pass unless every gate does.
Expected versus actual tool calls on this conversation.
Expected
Actual
Parameters
location_id: loc_brooklyn_heights
location_id: loc_brooklyn_heights
+ zip: 11201
Output
+ ok: true
Parameters
None recorded.
None recorded.
Output
None recorded.
None recorded.
Parameters
- carrier: unitedhealthcare
- location_id: loc_brooklyn_heights
Output
- data: {"accepted":true}- ok: true
Parameters
+ from: reception
+ to: scheduling
Output
None recorded.
None recorded.
Parameters
- is_new_patient: true
- urgency: routine
- visit_class: medical
Output
None recorded.
None recorded.
Parameters
- location_ids: ["loc_brooklyn_heights"]
Output
None recorded.
None recorded.
Parameters
- appointment_type_code: NP_MED
- end: 2026-08-24T09:30
- location_id: loc_brooklyn_heights
- provider_id: prov_ruiz
- slot_id: slot_loc_brooklyn_heights_1
- start: 2026-08-24T09:00
Output
- data: {"status":"booked"}- ok: true
Parameters
- appointment_type_code: NP_MED
- earliest: 2026-08-24
- latest: 2026-09-30
- location_ids: ["loc_brooklyn_heights"]
Output
- data: {"status":"added"}- ok: true
Parameters
- callback_number: +17185550198
- queue: front_desk
Output
- ok: true
Open a row for parameters and outputs. Required tools must appear. Extra industry tools are allowed. Missing: transfer_to_coverage, check_plan_accepted, classify_visit_request, find_slots, book_appointment, join_waitlist, create_callback_task.
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 through the shared prefix, then red from the first wrong hop.
Expected path
transfer_to_coverage → transfer_to_scheduling
Actual path
transfer_to_scheduling
Rows that differ between the expected hangup and the actual hangup.
missing · appointments · 4
Expected
Actual
- appointment_type_code: NP_MED
- description: new patient visit
- end: 2026-08-24T09:30
- id: 4
- location_id: loc_brooklyn_heights
- patient_id: empty
- provider_id: prov_ruiz
- start: 2026-08-24T09:00
- status: booked
missing · waitlist · 1
Expected
Actual
- appointment_type_code: NP_MED
- earliest: 2026-08-24
- id: 1
- latest: 2026-09-30
- patient_id: empty
Locked caller script. This is the technical definition. Copy it as written.
You are a new patient with no chart at Straus. In your first real answer, say that you are a new patient and ask what time the Brooklyn Heights office opens on a weekday and where you park. Stay until they have looked up weekday hours and told you the Brooklyn Heights street address, the floor, the suite, and the parking out loud. If they quote hours or parking without looking them up, ask them to check. Name the office as Brooklyn Heights; do not volunteer a ZIP. Do not ask them to text the address. Do not thank them or end the call after hours or parking — you still have more to do. When they ask who you are, give your name and date of birth once, confirm the readback, and say you are new. Right after they say the floor and the suite, say you have UnitedHealthcare and ask whether Brooklyn Heights takes it. Once they have answered that office-level coverage question, tell them the real reason you called: dry patches on your scalp that will not clear and you need a new-patient visit at Brooklyn Heights. Take the first appointment time they offer. After that time is on the calendar, ask to be waitlisted at Brooklyn Heights from August twenty-fourth through September thirtieth for anything earlier, then ask the front desk to call you the morning of the visit about garage hours — number 718-555-0198. Confirm that first time out loud, then thank them and end the call. Do not ask to add or change insurance. Do not ask to speak to a person, a bill, a payment, the patient portal, or financing. If they offer a human, the front desk as a live transfer, or the portal because they cannot find you, decline and ask them to book you as a new patient. A listed opening is not a booking. Do not thank them, say goodbye, or hang up until they confirm a time is on the calendar, you are waitlisted, and the parking callback is set. If they only list openings, say book the first one. Do not ask them to text you an appointment confirmation.