ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn Dialogue

TL;DR

The paper introduces ACR, a framework that dynamically refactors dialogue context to improve multi-turn dialogue performance of LLMs, reducing drift and token usage.

Contribution

It proposes a novel adaptive context refactoring framework with a self-evolving training paradigm to better manage dialogue history.

Findings

Significantly outperforms existing methods in multi-turn dialogue tasks.

Reduces token consumption while maintaining high performance.

Effectively mitigates contextual inertia and state drift.

Abstract

Large Language Models (LLMs) have shown remarkable performance in multi-turn dialogue. However, in multi-turn dialogue, models still struggle to stay aligned with what has been established earlier, follow dependencies across many turns, and avoid drifting into incorrect facts as the interaction grows longer. Existing approaches primarily focus on extending the context window, introducing external memory, or applying context compression, yet these methods still face limitations such as \textbf{contextual inertia} and \textbf{state drift}. To address these challenges, we propose the \textbf{A}daptive \textbf{C}ontext \textbf{R}efactoring \textbf{(ACR)} Framework, which dynamically monitors and reshapes the interaction history to mitigate contextual inertia and state drift actively. ACR is built on a library of context refactoring operators and a teacher-guided self-evolving training paradigm that learns when to intervene and how to refactor, thereby decoupling context management from the reasoning process. Extensive experiments on multi-turn dialogue demonstrate that our method significantly outperforms existing baselines while reducing token consumption.