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 / C2-M1
What this task measures
The caller is on the line with Straus Dermatology for one locked request: Move tomorrow's follow-up. They keep repeating that ask through a waitlist offer, a callback, or a different errand. We included it as a medium appointment management case because calendar writes are a core front-desk job, and they fail in characteristic ways: the wrong visit moves, identity is skipped, or a cancel becomes a reschedule. The agent succeeds only if it stays on that request, reaches the outcome by following the identity 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 $0.371
0:00 / 3:37 · audio · trace 801803 · 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 final database state did not match. Combined cannot pass unless every gate does.
Expected versus actual tool calls on this conversation.
Expected
Actual
Parameters
+ from: reception
- next_intent: scheduling
+ to: identity
Output
None recorded.
None recorded.
Parameters
+ dob: 1990-04-12
+ first_name: Jordan
+ last_name: Lee
+ zip: 10016
Output
+ ok: true
Parameters
None recorded.
None recorded.
Output
+ ok: true
Parameters
+ from: identity
+ to: scheduling
Output
None recorded.
None recorded.
Parameters
dob: 1990-04-12
dob: 1990-04-12
full_name: Jordan Lee
full_name: Jordan Lee
+ second_factor: 10016
Output
- data: {"verified":true}ok: true
ok: true
Parameters
+ location_id: loc_park_ave
+ zip: 10016
Output
+ ok: true
Parameters
location_ids: ["loc_park_ave"]
location_ids: ["loc_park_ave"]
+ max_results: 3
+ window_end: 2026-10-31T17:00
+ window_start: 2026-08-24T10:00
Output
+ ok: true
Parameters
appointment_id: 1
appointment_id: 1
- new_end: 2026-08-24T09:30
+ new_end: 2026-08-25T12:00
+ new_slot_id: slot_loc_park_ave_2
- new_start: 2026-08-24T09:00
+ new_start: 2026-08-25T11:30
Output
- data: {"status":"rescheduled"}ok: true
ok: true
Parameters
mobile_e164: +12125550100
mobile_e164: +12125550100
template_id: appointment_confirmation
template_id: appointment_confirmation
Output
- data: {"sent":true}ok: true
ok: true
Parameters
+ reason: caller_done
Output
None recorded.
None recorded.
Open a row for parameters and outputs. Required tools must appear. Extra industry tools are allowed. Parameter miss: reschedule_appointment. Extra: identify_patient, get_patient_summary, list_locations, end_call.
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_identity → transfer_to_scheduling
Actual path
transfer_to_identity → transfer_to_scheduling
Rows that differ between the expected hangup and the actual hangup.
appointments · 1
Expected
Actual
- end: 2026-08-24T09:30
+ end: 2026-08-25T12:00
- start: 2026-08-24T09:00
+ start: 2026-08-25T11:30
Locked caller script. This is the technical definition. Copy it as written.
You are an existing Straus patient. You have a follow-up on August 20, 2026 at Park Avenue and you need that visit moved to a later date, not cancelled. When they ask who you are, give your name and date of birth once; if they read them back, confirm and continue. Ask whether moving it costs you anything. If they ask which day, week, time, or office you prefer, say you will take the first opening they can offer. Do not name a week, day, time, or office of your own. When they offer appointment times, take the first one they say and confirm that first time out loud. After they confirm the visit was moved on the calendar, ask them to text you an appointment confirmation. That is the only text you want. Do not ask to cancel. Do not ask to join a waitlist. Do not ask to add insurance, for a callback, to speak to a person, a bill, a payment, the patient portal, financing, or the street address, floor, suite, or location id. 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 and that the appointment confirmation was texted. If they only list openings, say move me into that first time. Do not hang up until they confirm the visit was moved on the calendar and that the appointment confirmation was texted. If they confirm the move but have not texted the confirmation, ask them to text you the appointment confirmation.