# Incremental Summarization for Customer Support via Progressive Note-Taking and Agent Feedback

arXiv: https://arxiv.org/abs/2510.06677 · HTML: https://mlsanity.com/paper/2510.06677/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 8 Oct 2025.

## Builds on (most cited first, 13 of 13)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data](https://mlsanity.com/paper/1911.00359/) (2019)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [DialogSum: A Real-Life Scenario Dialogue Summarization Dataset](https://mlsanity.com/paper/2105.06762/) (2021)
- [CSDS: A Fine-Grained Chinese Dataset for Customer Service Dialogue Summarization](https://mlsanity.com/paper/2108.13139/) (2021)
- [Improving Factual Consistency of Abstractive Summarization on Customer Feedback](https://mlsanity.com/paper/2106.16188/) (2021)
- [Conversational Agents and Children: Let Children Learn](https://mlsanity.com/paper/2302.12043/) (2023)

## Built on by (most cited first, 4 of 4)

- [State Contamination in Memory-Augmented LLM Agents](https://mlsanity.com/paper/2605.16746/) (2026)
- [Mandol: An Agglomerative Agent Memory System for Long-Term Conversations](https://mlsanity.com/paper/2606.29778/) (2026)
- [Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization](https://mlsanity.com/paper/2608.09043/) (2026)
- [From Monolithic Blending to Agentic Orchestration: Dynamic Response for Conversational Assistants at Scale](https://mlsanity.com/paper/2609.05758/) (2026)

## Abstract (arXiv)

We introduce an incremental summarization system for customer support agents that intelligently determines when to generate concise bullet notes during conversations, reducing agents' context-switching effort and redundant review. Our approach combines a fine-tuned Mixtral-8x7B model for continuous note generation with a DeBERTa-based classifier to filter trivial content. Agent edits refine the online notes generation and regularly inform offline model retraining, closing the agent edits feedback loop. Deployed in production, our system achieved a 3% reduction in case handling time compared to bulk summarization (with reductions of up to 9% in highly complex cases), alongside high agent satisfaction ratings from surveys. These results demonstrate that incremental summarization with continuous feedback effectively enhances summary quality and agent productivity at scale.