# Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search

Source: [Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search](<https://www.sota2.com/research/paper/68fa7bcb1e209131cea8a848>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-14T05:00:04.234Z

Authors: Sangwon Ryu, Heejin Do, Yunsu Kim, Gary Geunbae Lee, Jungseul Ok

Published: 2025-09-30T15:55:24.000Z

## Abstract

Controllable summarization moves beyond generic outputs toward human-aligned summaries guided by specified attributes. In practice, the interdependence among attributes makes it challenging for language models to satisfy correlated constraints consistently. Moreover, previous approaches often require per-attribute fine-tuning, limiting flexibility across diverse summary attributes. In this paper, we propose adaptive planning for multi-attribute controllable summarization (PACO), a training-free framework that reframes the task as planning the order of sequential attribute control with a customized Monte Carlo Tree Search (MCTS). In PACO, nodes represent summaries, and actions correspond to single-attribute adjustments, enabling progressive refinement of only the attributes requiring further control. This strategy adaptively discovers optimal control orders, ultimately producing summaries that effectively meet all constraints. Extensive experiments across diverse domains and models demonstrate that PACO achieves robust multi-attribute controllability, surpassing both LLM-based self-planning models and fine-tuned baselines. Remarkably, PACO with Llama-3.2-1B rivals the controllability of the much larger Llama-3.3-70B baselines. With larger models, PACO achieves superior control performance, outperforming all competitors.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Controllable Summarization on MACSumDial](<https://www.sota2.com/research/sota/controllable-summarization-on-macsumdial.md>): Controllable Summarization; MACSumDial; Ext Score: 9.3.

- [Controllable Summarization on DialogSum](<https://www.sota2.com/research/sota/controllable-summarization-on-dialogsum.md>): Controllable Summarization; DIALOGSUM; Extent: 14.17.

- [Controllable Summarization on MACSumDoc](<https://www.sota2.com/research/sota/controllable-summarization-on-macsumdoc.md>): Controllable Summarization; MACSumDoc; Ext Score: 7.53.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.26435>)

[PDF](<https://arxiv.org/pdf/2509.26435.pdf>)
