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-H3
What this task measures
The caller is on the line with Straus Dermatology for one locked request: New Cigna card and a follow-up booking. They keep repeating that ask through a waitlist offer, a callback, or a different errand. We included it as a hard 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 following the identity then 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 $0.456
0:00 / 5:03 · audio · trace 801854 · 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
+ from: reception
- next_intent: coverage
+ to: identity
Output
None recorded.
None recorded.
Parameters
None recorded.
None recorded.
Output
None recorded.
None recorded.
Parameters
None recorded.
None recorded.
Output
None recorded.
None recorded.
Parameters
+ dob: 1990-04-12
+ first_name: Jordan
+ last_name: Li
+ zip: 10016
Output
+ ok: true
Parameters
dob: 1990-04-12
dob: 1990-04-12
- full_name: Jordan Lee
+ full_name: Jordan Li
+ second_factor: 10016
Output
- data: {"verified":true}+ error_code: NO_MATCH
- ok: true
+ ok: false
Parameters
- carrier: cigna
- member_id: C445566778
Output
- ok: true
Parameters
- location_id: loc_park_ave
Output
None recorded.
None recorded.
Parameters
- location_ids: ["loc_park_ave"]
Output
None recorded.
None recorded.
Parameters
- appointment_type_code: MED_FOLLOWUP
- end: 2026-08-24T09:30
- location_id: loc_park_ave
- provider_id: prov_chen
- slot_id: slot_loc_park_ave_1
- start: 2026-08-24T09:00
Output
- data: {"status":"booked"}- ok: true
Parameters
+ dob: 1990-04-12
+ full_name: Jordan Li
+ second_factor: 10016
Output
+ error_code: NO_MATCH
+ ok: false
Parameters
+ dob: 1990-04-12
+ full_name: Jordan Li
+ second_factor: 10016
Output
+ error_code: NO_MATCH
+ ok: false
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: verify_identity. Missing: transfer_to_coverage, transfer_to_scheduling, capture_insurance_update, list_locations, find_slots, book_appointment. Extra: identify_patient, verify_identity, verify_identity, 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 through the shared prefix, then red from the first wrong hop.
Expected path
transfer_to_identity → transfer_to_coverage → transfer_to_scheduling
Actual path
transfer_to_identity
Rows that differ between the expected hangup and the actual hangup.
missing · appointments · 4
Expected
Actual
- appointment_type_code: MED_FOLLOWUP
- description: follow-up visit
- end: 2026-08-24T09:30
- id: 4
- location_id: loc_park_ave
- patient_id: pat_jordan_lee
- provider_id: prov_chen
- start: 2026-08-24T09:00
- status: booked
Locked caller script. This is the technical definition. Copy it as written.
You are an existing Straus patient. You have two jobs, in this order. First, answer their identity questions once. After they verify you, do not repeat your name and date of birth. Tell them you have a new Cigna card to put on file, give the new carrier and member ID, and confirm the ID if they read it back. You do not have a group number. Second, you already have a follow-up on August 20 at Park Avenue; leave that one on the books. You still need a new additional follow-up booked at Park Avenue, not a move of August 20. If they offer to move, change, or cancel the visit you already have, say leave that one and book a new one. Before you take a time, ask for the Park Avenue street address, floor, and suite so you know where to go. If they ask what day or time works, say the first available time at Park Avenue is fine. Take the first new appointment time they offer. Do not ask for a different day, time, or office, and do not suggest any date of your own. Confirm that first new time out loud, then thank them and end the call. Do not ask for a callback, to speak to a person, a payment, the patient portal, a waitlist, a text, or financing. Do not ask to cancel or reschedule the visit you already have. 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. If they only list openings, say book the first one. Stay until they confirm the new card is saved on the chart. A spoken 'we'll update it' or a callback is not enough — ask them to save it now. After any 'we will update it,' ask whether it is on your chart now. Do not ask them to text you an appointment confirmation.