Bluejay / Labs
Open navigation

Working paper / 2026

MIVAS

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.

GitHub repository ↗

Clone the repository, pair a model harness with an industry task suite, and reproduce the evaluation environment.

Customer Support / R-H4

R-H4: Scam report, then the Bellwether return window

hardRegulatory adherence· Rosalind Baptiste

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.

Performance

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

0:000:100:200:300:400:501:001:101:201:301:401:502:002:102:202:302:402:503:003:103:203:303:403:504:004:104:204:304:404:505:005:105:205:30
0:00

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.

This sample fails because tools and final database state did not match. Combined cannot pass unless every gate does.

1. Tools

Expected versus actual tool calls on this conversation.

Expected

Actual

  • transfer_to_fraudtransfer_to_fraudto=fraud · from=receptionhit

    Parameters

     
    + from: reception
     
    + to: fraud

    Output

    None recorded.

    None recorded.

  • check_subscription_chargephone=541-555-0133 · amount=399.99check_subscription_charge[email protected] · phone=504-555-0133 · amount=399.99mismatch

    Parameters

      amount: 399.99
      amount: 399.99
    - phone: 541-555-0133
    + phone: 504-555-0133

    Output

     
    + error_code: NO_SUCH_CHARGE
     
    + ok: false
  • check_outbound_contactphone=541-555-0133 · [email protected]check_outbound_contact[email protected] · phone=504-555-0133mismatch

    Parameters

    - phone: 541-555-0133
    + phone: 504-555-0133

    Output

     
    + error_code: NO_OUTBOUND_CONTACT
     
    + ok: false
  • report_scam_contactphone=541-555-0133 · [email protected] · channel=emailreport_scam_contact[email protected] · phone=504-555-0133 · amount=399.99mismatch

    Parameters

      amount: 399.99
      amount: 399.99
      channel: email
      channel: email
      claimed_brand: TechCrew
      claimed_brand: TechCrew
      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
  • transfer_to_verificationtransfer_to_verificationto=verification · from=fraudhit

    Parameters

     
    + from: fraud
     
    + to: verification

    Output

    None recorded.

    None recorded.

  • identify_customeridentify_customerphone=504-555-0133 · full_name= · order_number=hit

    Parameters

     
     
     
     
     
    + phone: 504-555-0133

    Output

     
    + ok: true
  • verify_identitypostal_code=97401 · card_last4=7719verify_identitycard_last4=7719 · postal_code=97401hit

    Parameters

      card_last4: 7719
      card_last4: 7719
      postal_code: 97401
      postal_code: 97401

    Output

     
    + ok: true
  • get_customer_summaryget_customer_summaryhit

    Parameters

    None recorded.

    None recorded.

    Output

     
    + ok: true
  • transfer_to_returnstransfer_to_returnsto=returns · from=verificationhit

    Parameters

     
    + from: verification
     
    + to: returns

    Output

    None recorded.

    None recorded.

  • get_orderorder_number=KE-4431775get_orderorder_number=KE-4431775hit

    Parameters

      order_number: KE-4431775
      order_number: KE-4431775

    Output

     
    + ok: true
  • check_return_eligibilityorder_number=KE-4431775check_return_eligibilitysku=SKU-BWM-0450 · opened=true · order_number=KE-4431775hit

    Parameters

     
    + opened: true
      order_number: KE-4431775
      order_number: KE-4431775
     
    + sku: SKU-BWM-0450

    Output

     
    + ok: true
  • transfer_to_ordersto=orders · from=returnsextra

    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.

2. Handoff path

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

3. Final database state

The final-database gate failed, and no row-level difference was recorded between the expected hangup and the actual hangup.

Scores across model harnesses

Model harnesspass@1pass5Runs

Task definition

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.

Caller traits

full_name
Rosalind Baptiste
phone
541-555-0133
postal_code
97401
card_last4
7719
order_number
KE-4431775