Metraipolis › archive › dc_0d2fed7d7791
ReSUM: Reasoning-Driven Multi-Agent Framework for Query-Focused Summarization — arXiv:2611.09349
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09349
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:33:33.715Z
- SHA-256 of the archived text
4f37dd60c951dc29d6ba4dd1c97f4664adc765b2bb9e83e68d1d054362b17d71- Stable URL of this page
https://metraipolis.com/documento/dc_0d2fed7d7791
How to cite
ReSUM: Reasoning-Driven Multi-Agent Framework for Query-Focused Summarization — arXiv:2611.09349 — arXiv (en), https://arxiv.org/abs/2611.09349 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0d2fed7d7791 (Metraipolis archive dc_0d2fed7d7791, sha256 4f37dd60c951dc29d6ba4dd1c97f4664adc765b2bb9e83e68d1d054362b17d71)
BibTeX
@misc{dc0d2fed7d7791,
title = {ReSUM: Reasoning-Driven Multi-Agent Framework for Query-Focused Summarization — arXiv:2611.09349},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09349},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0d2fed7d7791; sha256 4f37dd60c951dc29d6ba4dd1c97f4664adc765b2bb9e83e68d1d054362b17d71},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09349. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLMs excel at language tasks, but long-meeting QFS remains difficult due to complex speaker dynamics, sparse key information, and limited data. Meetings involve disfluencies, long transcripts and complex discourse. QFS have high risk of information omission, hallucination, even for advanced models such as GPT-4-mini and Gemini. Existing end-to-end methods compress retrieval, evidence extraction, and summary generation into a single pass, failing to handle the complex reasoning required for targeted meeting summaries. We propose ReSUM, a modular multi-LLM framework coordinated by a planner that orchestrates retrieval and summarization agents. By distilling teacher reasoning into query- and plan-conditioned retrievers and summarizers, ReSUM enhances long-context robustness, minimizes irrelevant exploration, and generates more faithful and comprehensive query-focused summaries. Experiments show consistent gains on query-focused meeting summarization benchmarks. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2611.09349 — 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 2026-11-09T22:30:32.057Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).