Metraipolis › archive › dc_7f926ea7eb87
Live Assistant: Learning Whether, When, and Whom to Assist in Real-World Live Social Streams — arXiv:2609.27303
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27303
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T10:52:12.965Z
- SHA-256 of the archived text
be494310745c5bc8732c9c59ac2785d352f3587b1f958d20978d8383a6b7e7bc- Stable URL of this page
https://metraipolis.com/documento/dc_7f926ea7eb87
How to cite
Live Assistant: Learning Whether, When, and Whom to Assist in Real-World Live Social Streams — arXiv:2609.27303 — arXiv (en), https://arxiv.org/abs/2609.27303 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f926ea7eb87 (Metraipolis archive dc_7f926ea7eb87, sha256 be494310745c5bc8732c9c59ac2785d352f3587b1f958d20978d8383a6b7e7bc)
BibTeX
@misc{dc7f926ea7eb87,
title = {Live Assistant: Learning Whether, When, and Whom to Assist in Real-World Live Social Streams — arXiv:2609.27303},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27303},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f926ea7eb87; sha256 be494310745c5bc8732c9c59ac2785d352f3587b1f958d20978d8383a6b7e7bc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27303. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Livestreams are long-lasting interactive environments where audiovisual content, viewer activity, host behavior, and platform signals evolve together, creating assistance needs that emerge from the stream itself. We introduce \liveassistant, a framework for mixed-initiative, role-conditioned assistance that formulates livestream interaction as four coupled decisions: \textbf{whether to act, when to act, whom to address, and what to communicate}. At each 10-second interval, one autoregressive policy consumes native audio and video with synchronized comments, gifts, viewer dynamics, and room metadata, then selects \textsc{OBS}, \textsc{MEM}, or \textsc{ANS}. \textsc{OBS} remains silent, \textsc{MEM} records a private semantic update, and \textsc{ANS} specifies a recipient, task, and grounded message. To support this task, we build a trajectory engine that reconstructs real livestream sessions into structured causal supervision, yielding over 320 hours of optimization trajectories and a human-reviewed benchmark of 275 clips and 13,812 decision intervals. We train the policy with Marker-Aware Multiturn Supervised Fine-Tuning (MA-MSFT), which strengthens sparse structured decisions, followed by Streaming Multiturn GSPO (SM-GSPO), which optimizes self-generated trajectories with turn- and trajectory-level credit. On the held-out benchmark, \liveassistant reaches 71.14 state accuracy, 72.67 recipient accuracy, and 58.41 task accuracy, with consistent gains over representative streaming and general multimodal baselines. Together, the formulation, benchmark, and training framework establish livestream assistance as selective participation in a shared social stream.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.27303 — 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 2026-10-08T10:06:16.723Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).