# Segment-level Tree Search for Long Meeting Document Summarization

arXiv: https://arxiv.org/abs/2606.08445 · HTML: https://mlsanity.com/paper/2606.08445/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 7 Jun 2026.

## Builds on (most cited first, 24 of 24)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models](https://mlsanity.com/paper/1610.02424/) (2016)
- [Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://mlsanity.com/paper/2210.07197/) (2022)
- [QuestEval: Summarization Asks for Fact-based Evaluation](https://mlsanity.com/paper/2103.12693/) (2021)
- [Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents](https://mlsanity.com/paper/2110.10150/) (2021)
- [Exploring Neural Models for Query-Focused Summarization](https://mlsanity.com/paper/2112.07637/) (2021)
- [CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning](https://mlsanity.com/paper/2112.08713/) (2021)
- [DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization](https://mlsanity.com/paper/2110.08168/) (2021)
- [Abstractive Meeting Summarization: A Survey](https://mlsanity.com/paper/2208.04163/) (2022)
- [What's under the hood: Investigating Automatic Metrics on Meeting Summarization](https://mlsanity.com/paper/2404.11124/) (2024)
- [Context-Aware Hierarchical Merging for Long Document Summarization](https://mlsanity.com/paper/2502.00977/) (2025)
- [Key-Element-Informed sLLM Tuning for Document Summarization](https://mlsanity.com/paper/2406.04625/) (2024)
- [Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning](https://mlsanity.com/paper/2406.00303/) (2024)
- [Incorporating Question Answering-Based Signals into Abstractive Summarization via Salient Span Selection](https://mlsanity.com/paper/2111.07935/) (2021)
- [Towards Understanding Omission in Dialogue Summarization](https://mlsanity.com/paper/2211.07145/) (2022)
- [Multi-Facet Blending for Faceted Query-by-Example Retrieval](https://mlsanity.com/paper/2412.01443/) (2024)
- [Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search](https://mlsanity.com/paper/2509.26435/) (2025)

## Abstract (arXiv)

Meeting documents are challenging to summarize due to their length and complex conversational structure. Existing approaches typically adopt multi-stage pipelines that extract information prior to summarization; however, these approaches often suffer from cumulative error propagation without intermediate validation, a limitation further amplified by short and low-quality reference summaries. We propose segment-level summarization via Monte Carlo Tree Search (S3), a training-free framework that constructs a final summary by composing segment-level summary candidates. S3 partitions a long document into segments and generates multiple summary candidates per segment, forming nodes of a search tree. The best-scoring combination is selected via self-reward-guided tree search and refined into the final output. Despite using a 7B model, S3 achieves performance comparable to larger 72B models while producing length-appropriate summaries.