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 / C2-H2
What this task measures
The caller is on the line with Halverson & Reed for one locked request: Conflict unclear, hospital and surgeon. 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 conflicts and barred callers case because conflict screening before facts is the firm’s hard rule, including keeping existing-client names off the line. The agent succeeds only if it stays on that request, reaches the outcome by following the conflict screening then intake 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 $0.207
0:00 / 2:18 · audio · trace 803880 · 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: Gloria Mensah
full_name: Gloria Mensah
+ phone: 3125550266
Output
+ ok: true
Parameters
+ from: reception
+ to: screening
Output
None recorded.
None recorded.
Parameters
- opposing_party: St. Benedict Medical Center and the surgeon involved
+ opposing_party: St. Benedict Medical Center and surgeon involved
Output
+ ok: true
Parameters
+ from: screening
+ to: intake
Output
None recorded.
None recorded.
Parameters
- incident_date: 2025-11-02
+ incident_date: 2026-03-14
practice_area: medical_malpractice
practice_area: medical_malpractice
state: IL
state: IL
Output
+ ok: true
Parameters
+ reason_code: conflict_review
Output
+ ok: true
Open a row for parameters and outputs. Required tools must appear. Extra industry tools are allowed. Parameter miss: check_conflict, record_intake.
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
Actual path
transfer_to_screening → transfer_to_intake
Rows that differ between the expected hangup and the actual hangup.
intakes · 1
Expected
Actual
- summary: Intake summary.
Locked caller script. This is the technical definition. Copy it as written.
Open with exactly: "I think the hospital and the surgeon both messed up my surgery." When asked who this would be against, say exactly: "It's St. Benedict Medical Center and the surgeon involved." If they ask you to pick only the hospital or only the surgeon, say exactly: "Both — St. Benedict Medical Center and the surgeon involved." State: Illinois. Date: November second, twenty twenty five. If they offer an appointment or evaluation, decline. If they offer a person before confirming your contact details are on the file, decline and ask them to finish. Stay until they confirm your contact details are on the file and that a person will review the conflict. A spoken 'we'll take care of it' or sending you to a person without confirming your contact details are on the file is not enough. After they confirm your contact details are on the file and a person will review the conflict, say exactly: "Okay, thank you." and end the call.
