Metraipolis › archive › dc_fa9c04b752c3
DuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration — arXiv:2610.11299
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11299
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T05:47:35.172Z
- SHA-256 of the archived text
f6f9b3442ceb26ece69da3bc350ce2cbe877ee3735058fe4ecf611e36638940e- Stable URL of this page
https://metraipolis.com/documento/dc_fa9c04b752c3
How to cite
DuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration — arXiv:2610.11299 — arXiv (en), https://arxiv.org/abs/2610.11299 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa9c04b752c3 (Metraipolis archive dc_fa9c04b752c3, sha256 f6f9b3442ceb26ece69da3bc350ce2cbe877ee3735058fe4ecf611e36638940e)
BibTeX
@misc{dcfa9c04b752c3,
title = {DuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration — arXiv:2610.11299},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11299},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa9c04b752c3; sha256 f6f9b3442ceb26ece69da3bc350ce2cbe877ee3735058fe4ecf611e36638940e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11299. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Voice agents are converging on a collaboration pattern: a full-duplex interaction model stays on the live channel as the entry to the conversation, while search, reasoning, and coding are handled through asynchronous delegation. A duplex model supports continuous listening and speaking, but complex reasoning and tool use may exceed its capabilities. A coding agent can plan and execute extended tasks, but its sequential interface is a poor fit for live conversation. Combining them requires a harness that coordinates task acceptance, progress, cancellation, replacement, and result delivery while keeping the conversation responsive. Existing harnesses often rely on coupled heuristics, making them difficult to improve systematically from evidence. We present DuplexAgent, a full-duplex collaboration system whose harness expresses this workflow as six editable modules, and Duplex-Harness-RSI, a closed loop that revises them from interaction traces. A simulator automatically generates timed test conversations, runs the system, and produces failure traces that identify the collaboration modules requiring repair. Reasoning LLMs and coding agents in the delegation pool also serve the improvement loop: the Exam Planner selects the next tests from observed weaknesses and the repair archive, and the Harness Editor proposes targeted module changes. The capabilities that serve the user thus also improve the system's coordination. Experiments on intelligence, agentic, and duplex benchmarks show that DuplexAgent combines continuous interaction with difficult reasoning and complex task execution, achieving stronger spoken-knowledge and executable-tool scores than the compared delegated systems while maintaining strong interruption response. A harness ablation further shows that this modular, verifiable loop outperforms the initial harness and repeated editing that lacks its diagnosis and repair archive. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Sound (cs.SD). Pagina del lavoro: https://arxiv.org/abs/2610.11299 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T05:47:00.607Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).