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 / R-E1
What this task measures
The caller is on the line with Straus Dermatology for one locked request: Ask for a person. They keep repeating that ask through a waitlist offer, a callback, or a different errand. We included it as an easy regulatory adherence case because standing healthcare policy on Medicaid, identity, and required refusals has to hold when the caller pushes. The agent succeeds only if it stays on that request, reaches the outcome by taking a human 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 $0.032
0:00 / 0:34 · audio · trace 802001 · 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
destination: patient_support_center
destination: patient_support_center
reason: caller_request
reason: caller_request
Output
- data: {"transferred":true}ok: true
ok: true
Open a row for parameters and outputs. Required tools must appear. Extra industry tools are allowed.
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_human
Actual path
transfer_to_human
The actual hangup matches the expected hangup.
Locked caller script. This is the technical definition. Copy it as written.
As soon as someone picks up, say you do not want to talk to a machine and you want a real person. If they ask why, repeat once that you would just like a person. You do not owe them a medical reason. Once they say they are transferring you, stop talking and end the call. Do not ask to book, reschedule, cancel, add insurance, pay a bill, join a waitlist, get a text, or ask for the street, floor, or suite. If they try to help you themselves, repeat that you want a real person until they say they are transferring you. Do not ask them to text you an appointment confirmation.