Summarizing deeply nested discussion threads requires handling interleaved replies, quotes, and overlapping topics, which standard LLM summarizers struggle to capture reliably. We introduce ThreadSumm, a multi-stage LLM framework that treats thread summarization as a hierarchical reasoning problem over explicit aspect and content unit representations. Our method first performs content planning via LLM-based extraction of discourse aspects and Atomic Content Units, then applies sentence ordering to construct thread-aware sequences that surface multiple viewpoints rather than a single linear strand. On top of these interpretable units, ThreadSumm employs a Tree of Thoughts search that generates and scores multiple paragraph candidates, jointly optimizing coherence and coverage within a unified search space. With this multi-proposal and iterative refinement design, we show improved performance in generating logically structured summaries compared to existing baselines, while achieving higher aspect retention and opinion coverage in nested discussions.
@article{arxiv.2604.17648,
title = {ThreadSumm: Summarization of Nested Discourse Threads Using Tree of Thoughts},
author = {Olubusayo Olabisi and Ekata Mitra and Ameeta Agrawal},
journal= {arXiv preprint arXiv:2604.17648},
year = {2026}
}