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 / C5-H4
What this task measures
The caller is on the line with Straus Dermatology for one locked request: Windermere balance, visit charge, then CareCredit and a link. They keep repeating that ask through a waitlist offer, a callback, or a different errand. We included it as a hard billing and payments case because balances and payment links have to come from the chart, at the amount on file. The agent succeeds only if it stays on that request, reaches the outcome by following the identity then billing 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 $0.391
0:00 / 5:38 · audio · trace 801976 · 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 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: billing
+ to: identity
Output
None recorded.
None recorded.
Parameters
+ dob: 1995-09-08
+ first_name: Alice
+ last_name: Romano
+ zip: 34786
Output
+ ok: true
Parameters
+ from: identity
+ to: billing
Output
None recorded.
None recorded.
Parameters
dob: 1995-09-08
dob: 1995-09-08
full_name: Alice Romano
full_name: Alice Romano
+ second_factor: 34786
Output
- data: {"verified":true}ok: true
ok: true
Parameters
None recorded.
None recorded.
Output
ok: true
ok: true
Parameters
None recorded.
None recorded.
Output
- data: {"balance_cents":32000}ok: true
ok: true
Parameters
- line_item_id: li_visit
Output
- ok: true
Parameters
+ amount_cents: 32000
Output
ok: true
ok: true
Parameters
+ amount_cents: 32000
mobile_e164: +14075550155
mobile_e164: +14075550155
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. Missing: explain_charge. Extra: identify_patient, 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_billing
Actual path
transfer_to_identity → transfer_to_billing
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. You got a bill for a few hundred dollars from the Windermere office and you cannot pay the whole thing this month. Answer their identity questions once, confirm the readback, then stay on the bill. Ask what you owe and why the visit charge is there. After you hear the amount and the explanation, say you cannot pay it all at once and ask whether there is a payment plan. Accept the financing they offer and ask for the payment link to be texted to you. Then thank them and end the call. Do not ask to book, reschedule, or cancel. Do not ask for a callback or to speak to a person. Do not ask about a waitlist, the patient portal, insurance, or the street, floor, or suite. Do not ask for any text other than the payment link. Stay until they have explained the visit charge, looked up a payment plan or financing in their system, then texted the payment link. A spoken 'we have plans' without a lookup is not enough. Do not ask them to text you an appointment confirmation.