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 / T4-H1
What this task measures
The caller is on the line with Kestrel Electronics for one locked request: Cancel Plus after one save offer. They keep repeating that ask through a callback offer, a different ticket, or an unrequested fix. We included it as a hard membership case because status, a prorated upgrade, and a cancellation that offers at most one save are the membership desk in miniature. The agent succeeds only if it stays on that request, reaches the outcome by following the verification then membership 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 $0.267
0:00 / 3:08 · audio · trace 813364 · 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 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: verification
Output
None recorded.
None recorded.
Parameters
+ full_name: Unknown
+ order_number: Unknown
+ phone: Unknown
Output
+ ok: true
Parameters
+ full_name: Selena Cortez
+ phone: 5415500171
Output
+ ok: true
Parameters
card_last4: 1156
card_last4: 1156
postal_code: 97035
postal_code: 97035
Output
+ ok: true
Parameters
None recorded.
None recorded.
Output
+ ok: true
Parameters
+ from: verification
+ to: membership
Output
None recorded.
None recorded.
Parameters
None recorded.
None recorded.
Output
+ ok: true
Parameters
+ confirmation_token: KE-CXL-7708
proration_acknowledged: true
proration_acknowledged: true
Output
+ ok: true
Open a row for parameters and outputs. Required tools must appear. Extra industry tools are allowed. Extra: identify_customer.
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_verification → transfer_to_membership
Actual path
transfer_to_verification → transfer_to_membership
Rows that differ between the expected hangup and the actual hangup.
customers · cust_selina
Expected
Actual
- auto_renew: 1
+ auto_renew: 0
- membership_paid_cents: 2999
+ membership_paid_cents: 0
- membership_start: 2026-02-15
- tier: plus
+ tier: standard
extra · holds · KE-CXL-7708
Expected
Actual
+ customer_id: cust_selina
+ kind: cancel
+ summary: Cancelling Kestrel Plus refunds $14.99 back to the card ending 1156, which is the 6 unused whole months of the $29.99 paid. It ends today, and they'd lose 60-day returns, member pricing, free two-day shipping and 1% back.
+ token: KE-CXL-7708
extra · membership_changes · 1
Expected
Actual
+ amount_cents: 1499
+ customer_id: cust_selina
+ id: 1
Locked caller script. This is the technical definition. Copy it as written.
Open with exactly: "Cancel my Kestrel Plus membership today." Give identity when asked. If they make one save offer, say exactly: "No, please cancel it." Do not accept a second save pitch, a store visit, a letter, or a callback. Confirm after they read back the $14.99 refund for 6 unused months, ending today. 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.
