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.
Legal / C5-H1
What this task measures
The caller is on the line with Halverson & Reed for one locked request: Medical malpractice booked in Florida. They keep repeating that ask through a callback offer, a message left for someone else, or advice on a different matter. We included it as a hard fees and booking case because fee disclosure and a two-step evaluation booking are the commercial close of intake, and they have to be spoken from the firm’s own figures. The agent succeeds only if it stays on that request, reaches the outcome by following the conflict screening then intake 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 $0.532
0:00 / 5:56 · audio · trace 804055 · 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
+ full_name: Amina Okoro
+ phone: 3055550181
Output
+ ok: true
Parameters
+ from: reception
+ to: screening
Output
None recorded.
None recorded.
Parameters
opposing_party: Palmetto Surgical Group
opposing_party: Palmetto Surgical Group
Output
+ ok: true
Parameters
practice_area: medical_malpractice
practice_area: medical_malpractice
Output
+ ok: true
Parameters
practice_area: medical_malpractice
practice_area: medical_malpractice
state: FL
state: FL
Output
+ ok: true
Parameters
incident_date: 2026-07-10
incident_date: 2026-07-10
practice_area: medical_malpractice
practice_area: medical_malpractice
state: FL
state: FL
Output
+ ok: true
Parameters
+ from: screening
+ to: intake
Output
None recorded.
None recorded.
Parameters
incident_date: 2026-07-10
incident_date: 2026-07-10
practice_area: medical_malpractice
practice_area: medical_malpractice
state: FL
state: FL
- summary: Nerve injury after surgery.
+ summary: Caller reports possible nerve injury after a procedure at Palmetto Surgical Group in Florida and has had nerve pain and numbness since the procedure. Caller wants to proceed with intake for evaluation.
Output
+ ok: true
Parameters
- channel: email
+ channel: sms
Output
+ ok: true
Parameters
+ provider: Palmetto Surgical Group
Output
+ ok: true
Parameters
+ from: intake
+ to: scheduling
Output
None recorded.
None recorded.
Parameters
+ earliest_date: 2026-08-23
practice_area: medical_malpractice
practice_area: medical_malpractice
state: FL
state: FL
Output
+ ok: true
Parameters
practice_area: medical_malpractice
practice_area: medical_malpractice
+ slot_id: s_120
Output
+ ok: true
Parameters
+ confirmation_token: HR-EVAL-3092
Output
+ ok: true
Open a row for parameters and outputs. Required tools must appear. Extra industry tools are allowed. Parameter miss: record_intake, send_intake_packet. Extra: lookup_caller, request_records_authorization.
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_screening → transfer_to_intake → transfer_to_scheduling
Actual path
transfer_to_screening → transfer_to_intake → transfer_to_scheduling
Rows that differ between the expected hangup and the actual hangup.
extra · documents · 1
Expected
Actual
+ caller_id: c_new
+ id: 1
+ kind: intake_packet
extra · documents · 2
Expected
Actual
+ caller_id: c_new
+ id: 2
+ kind: records_authorization
missing · documents · {"caller_id": "c_new", "kind": "intake_packet", "target": "email"}
Expected
Actual
- caller_id: c_new
- kind: intake_packet
intakes · 1
Expected
Actual
- summary: Nerve injury after surgery.
+ summary: Caller reports possible nerve injury after a procedure at Palmetto Surgical Group in Florida and has had nerve pain and numbness since the procedure. Caller wants to proceed with intake for evaluation.
Locked caller script. This is the technical definition. Copy it as written.
Open with exactly: "I think a surgeon at Palmetto Surgical Group nicked a nerve during my procedure in Florida." When asked who this would be against, say exactly: "It's Palmetto Surgical Group." When asked when, say exactly: "It was July tenth, twenty twenty six." If asked whether to send the packet by email or text, say exactly: "Email is fine." Take the first appointment time offered. When read back, say exactly: "Yes, that's right, go ahead and book it." Do not ask for a staff member. Stay until they confirm the intake is on the file, the packet is sent, and the appointment is booked. A spoken "we'll take care of it" without those writes is not enough. Once told the appointment is booked, say exactly: "Thank you, that's all I needed." and end the call.
