# ThreadSumm: Summarization of Nested Discourse Threads Using Tree of Thoughts

arXiv: https://arxiv.org/abs/2604.17648 · HTML: https://mlsanity.com/paper/2604.17648/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 11 of its 29 references that are in the map.
- First posted on arXiv 19 Apr 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 11 of 11)

- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Asking and Answering Questions to Evaluate the Factual Consistency of Summaries](https://mlsanity.com/paper/2004.04228/) (2020)
- [Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation](https://mlsanity.com/paper/2212.07981/) (2022)
- [BooookScore: A systematic exploration of book-length summarization in the era of LLMs](https://mlsanity.com/paper/2310.00785/) (2023)
- [EmailSum: Abstractive Email Thread Summarization](https://mlsanity.com/paper/2107.14691/) (2021)
- [Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization](https://mlsanity.com/paper/2501.00888/) (2025)
- [NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization](https://mlsanity.com/paper/2505.24575/) (2025)
- [Understanding Position Bias Effects on Fairness in Social Multi-Document Summarization](https://mlsanity.com/paper/2405.01790/) (2024)
- [MODABS: Multi-Objective Learning for Dynamic Aspect-Based Summarization](https://mlsanity.com/paper/2406.03479/) (2024)
- [Needling Through the Threads: A Visualization Tool for Navigating Threaded Online Discussions](https://mlsanity.com/paper/2506.11276/) (2025)
- [Input Order Shapes LLM Semantic Alignment in Multi-Document Summarization](https://mlsanity.com/paper/2512.02665/) (2025)

## Abstract (arXiv)

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.