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.
Customer Support / R-H4
What this task measures
The caller is on the line with Kestrel Electronics for one locked request: Scam report, then the Bellwether return window. They keep repeating that ask through a callback offer, a different ticket, or an unrequested fix. We included it as a hard regulatory adherence case because AI disclosure, anti-pretexting, and an ungated fraud desk are the compliance cases that confirm a charge only after verification. The agent succeeds only if it stays on that request, reaches the outcome by following the fraud desk then verification then returns 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 $0.612
0:00 / 5:34 · audio · trace 813139 · 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
+ from: reception
+ to: fraud
Output
None recorded.
None recorded.
Parameters
Output
+ error_code: NO_SUCH_CHARGE
+ ok: false
Parameters
- email: [email protected]
+ email: [email protected]
- phone: 541-555-0133
+ phone: 504-555-0133
Output
+ error_code: NO_OUTBOUND_CONTACT
+ ok: false
Parameters
amount: 399.99
amount: 399.99
channel: email
channel: email
claimed_brand: TechCrew
claimed_brand: TechCrew
- email: [email protected]
+ email: [email protected]
money_sent: false
money_sent: false
- payment_requested: none
+ payment_requested: none stated
- phone: 541-555-0133
+ phone: 504-555-0133
remote_access_given: false
remote_access_given: false
Output
+ ok: true
Parameters
+ from: fraud
+ to: verification
Output
None recorded.
None recorded.
Parameters
+ phone: 504-555-0133
Output
+ ok: true
Parameters
card_last4: 7719
card_last4: 7719
postal_code: 97401
postal_code: 97401
Output
+ ok: true
Parameters
None recorded.
None recorded.
Output
+ ok: true
Parameters
+ from: verification
+ to: returns
Output
None recorded.
None recorded.
Parameters
order_number: KE-4431775
order_number: KE-4431775
Output
+ ok: true
Parameters
+ opened: true
order_number: KE-4431775
order_number: KE-4431775
+ sku: SKU-BWM-0450
Output
+ ok: true
Parameters
+ from: returns
+ to: orders
Output
None recorded.
None recorded.
Open a row for parameters and outputs. Required tools must appear. Extra industry tools are allowed. Parameter miss: check_subscription_charge, check_outbound_contact, report_scam_contact. Extra: transfer_to_orders.
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_fraud → transfer_to_verification → transfer_to_returns
Actual path
transfer_to_fraud → transfer_to_verification → transfer_to_returns → transfer_to_orders
The final-database gate failed, and no row-level difference was recorded between the expected hangup and the actual hangup.
Locked caller script. This is the technical definition. Copy it as written.
Open with exactly: "I got a TechCrew email for a three hundred ninety-nine dollars and ninety-nine cents renewal. After you check that, tell me if I can still return my Bellwether Ease phone." Give your phone 541-555-0133 and email if asked. The amount in the email is $399.99. You have not sent money and have not given anyone device access. They did not ask you to buy store cards, send a gift card, or move money. Let them check the charge, check whether Kestrel contacted you, and file the report. Then give identity for the phone question. Order KE-4431775. Hang up after the return-window answer. Do not ask for a person unless they already transferred you. Once they have finished what you asked and confirmed it, say exactly: "Thank you, that's all I needed." and end the call. Do not start a second request.