Lune

ACL Findings2026

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

Jiawei Shen, Jia Zhu, Hanghui Guo, Weijie Shi, Yue Cui, Qingyu Niu, Guoqing Ma, Jingjiang Liu, Yidan Liang, Yilin Wang, Shimin Di, Jiajie Xu

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 contextual inertia and state drift. To address these challenges, we propose the Adaptive Context Refactoring (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 teacherguided 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. Our code is available at https://github. com/ClannadKno/multi-turn.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on20

  1. Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
  2. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
  3. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessTri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra et al.NeurIPS 2022 · 5,493 citations
  4. HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language ModelsBernal Jimenez Gutierrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga et al.NeurIPS 2024 · 395 citations
  5. MemoryBank: Enhancing Large Language Models with Long-Term MemoryWanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye et al.AAAI 2024 · 394 citations

Related papers

  1. Sculptor: Empowering LLMs with Cognitive Agency via Active Context ManagementMo Li, L.H. Xu, Qitai Tan, Long Ma et al.ICLR 2026 · 20 citations
  2. ARC: Active and Reflection-driven Context Management for Long-Horizon Information Seeking AgentsYilun Yao, Shan Huang, Elsie Dai, Zhewen Tan et al.ACL Findings 2026
  3. U-Fold: Dynamic Intent-Aware Context Folding for User-Centric AgentsJin Su, Runnan Fang, Yeqiu Li, Xiaobin Wang et al.ACL Findings 2026
  4. Agentic Conversational Search with Contextualized Reasoning via Reinforcement LearningFengran Mo, Yifan Gao, Sha Li, Hansi Zeng et al.ACL Findings 2026
  5. PACE: Predictive Adaptive Context Extraction for Long-Horizon LLM AgentsLei Wei, Xiao Peng, TT, Guannan Zhang et al.ACL 2026
Dusk over the sea between two cliffs drawn in fine vertical lines