OpenAlex ·
Jarvis: Coordination Deserves a Brain of Its Own in Agentic Interactive Models
- Published
- Source
- OpenAlex
- Published in
- arXiv (Cornell University)
- DOI
- 10.48550/arxiv.2610.23804
- Original
- Read it at the publisher
- Topics
Abstract
Interactive models increasingly hand complex reasoning and tool use to a slow brain in the background, leaving a realtime front model free to sustain full-duplex dialogue. Yet the user may refine, cancel or replace a request while its task runs, so a plan or result that made sense a moment ago goes stale. Each new utterance must therefore be read against the work in flight, but the front model follows only the conversation and the back end sees only its own task. Coordination deserves a brain of its own, one that sees both. We introduce Jarvis, a coordination harness where models judge and code enforces. Its typed decision model, JEV, reads each turn against the live tasks and picks among operations built from a versioned task record. Code checks every choice against the current state before applying it, so no decision can act on a task version the user has replaced. Jarvis also rechecks plans before they execute and results before they are spoken, and counts an answer as delivered only once the user has heard it in full. We build two instances of this design. Jarvis-Audio runs unchanged on three full-duplex speech models. Jarvis-Omni adds vision and rechecks the evidence behind an answer before and during playback, since a scene can change while nobody speaks. With the front model and back end held fixed, replacing Qwen Audio Agent with Jarvis raises tau-Voice task success more than sixfold, from 29 to 192 of 278 tasks, and the gains hold on every benchmark and front model. Against published systems, Jarvis-Audio reaches 69% Pass1 on Full-Duplex-Bench v3 with an open 9B front model, versus 60% for GPT-Realtime. These results suggest that how the two brains are coordinated matters as much as how strong they are.
The authors’ abstract, as arXiv lists it. arXiv’s listings, abstracts included, are free for anyone to reuse.
Read it on ReadSearch
Each opens after you create an account, and brings you back to this paper.
More in Artificial Intelligence
Between Spoilers and Guesswork: Avoiding Over-Specification in Coding Benchmarks
Screening LLM Judges Without Ground Truth: A Preliminary Evaluation of an AI Dental Hygiene Coach
StoBasket: Joint Upsell and Cross-Sell Optimization for Contribution Margin
What Matters for NVFP4 Training? A Comparative Study of Low-Precision Pretraining Recipes
When Can You Trust an Agent's Own Verifier? Stress-Testing Counterfactual Rationale Verification Under Search Pressure and Oracle Access
Get the few papers worth your time in Artificial Intelligence every morning.
ReadSearch reads the new papers in your field each day and brings you the few worth reading, each with its key finding in a sentence.