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 / C1-M4
What this task measures
The caller is on the line with Halverson & Reed for one locked request: New auto accident screening checks. 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 medium reception and routing case because intake has to wait until the caller is classified; messages, wrong numbers, and represented parties are everyday reception work. The agent succeeds only if it stays on that request, reaches the outcome by taking the conflict screening path, and leaves the record untouched: no appointment, ticket, or note the caller never asked for.
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 $0.146
0:00 / 1:27 · audio · trace 803846 · 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: Harriet Voss
+ full_name: Harriet Moss
+ phone: 5035550281
Output
+ ok: true
Parameters
+ from: reception
+ to: screening
Output
None recorded.
None recorded.
Parameters
- opposing_party: Pellham Transit
+ opposing_party: Pelham Transit
Output
+ ok: true
Parameters
practice_area: auto_accident
practice_area: auto_accident
Output
+ ok: true
Parameters
practice_area: auto_accident
practice_area: auto_accident
state: WA
state: WA
Output
+ ok: true
Parameters
- incident_date: 2026-06-08
+ incident_date: 2020-06-08
practice_area: auto_accident
practice_area: auto_accident
state: WA
state: WA
Output
+ ok: true
Parameters
+ reason_code: deadline_review
Output
+ ok: true
Open a row for parameters and outputs. Required tools must appear. Extra industry tools are allowed. Parameter miss: lookup_caller, check_conflict, calculate_filing_deadline. Extra: escalate_to_human.
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
Actual path
transfer_to_screening
Rows that differ between the expected hangup and the actual hangup.
extra · escalations · 1
Expected
Actual
+ caller_id: c_new
+ id: 1
+ reason_code: deadline_review
Locked caller script. This is the technical definition. Copy it as written.
Open with exactly: "I was in a car accident in Washington and I need a lawyer." This is a new matter of yours. You have not called this firm before. When asked who this would be against, say exactly: "It's Pellham Transit." When asked which state this happened in or where it took place, say exactly: "In Washington." When asked when, say exactly: "It was June eighth, twenty twenty six." Give your name and number if asked. Do not ask for a staff member. Stay until they confirm they have checked the other side, that they handle car accidents, that they are licensed in Washington, and the filing deadline. A spoken promise that they will take the matter, without those checks, is not enough. If they start taking a written account or offer an appointment, say exactly: "That's all I needed today. Thank you." and end the call. Once they have confirmed the other side is clear, they handle car accidents in Washington, and they have given the filing deadline, say exactly: "Thank you, that's all I needed." and end the call.
