# Personalized Abstractive Summarization by Tri-agent Generation Pipeline

arXiv: https://arxiv.org/abs/2305.02483 · HTML: https://mlsanity.com/paper/2305.02483/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 4 May 2023.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization](https://mlsanity.com/paper/2210.01241/) (2022)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [Annotating and Modeling Fine-grained Factuality in Summarization](https://mlsanity.com/paper/2104.04302/) (2021)
- [Encode, Tag, Realize: High-Precision Text Editing](https://mlsanity.com/paper/1909.01187/) (2019)
- [LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2105.08206/) (2021)
- [On Improving Summarization Factual Consistency from Natural Language Feedback](https://mlsanity.com/paper/2212.09968/) (2022)
- [Text Editing by Command](https://mlsanity.com/paper/2010.12826/) (2020)
- [Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization](https://mlsanity.com/paper/2208.09770/) (2022)
- [Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits](https://mlsanity.com/paper/2301.00355/) (2023)

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

- [Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing](https://mlsanity.com/paper/2502.20592/) (2025)
- [The Current State of Summarization](https://mlsanity.com/paper/2305.04853/) (2023)
- [GRAVITY: A Framework for Personalized Text Generation via Profile-Grounded Synthetic Preferences](https://mlsanity.com/paper/2510.11952/) (2025)
- [Diversity Augmentation of Dynamic User Preference Data for Boosting Personalized Text Summarizers](https://mlsanity.com/paper/2510.10082/) (2025)

## Abstract (arXiv)

Tailoring outputs from large language models, like ChatGPT, to implicit user preferences remains a challenge despite their impressive generative capabilities. In this paper, we propose a tri-agent generation pipeline comprising a generator, an instructor, and an editor to enhance output personalization. The generator produces an initial output, the instructor automatically generates editing instructions based on user preferences, and the editor refines the output to align with those preferences. The inference-only large language model (ChatGPT) serves as both the generator and editor, with a smaller model acting as the instructor to guide output generation. We train the instructor using editor-steered reinforcement learning, leveraging feedback from a large-scale editor model to optimize instruction generation. Experimental results on two abstractive summarization datasets demonstrate the effectiveness of our approach in generating outputs that better meet user expectations. Code is available at urlhttps://github.com/Wendy-Xiao/chatgpteditingsumm