mlsanityData to 14 Oct 2026

A State-Update Prompting Strategy for Efficient and Robust Multi-turn Dialogue

arXiv 2509.17766 ↗First posted 22 Sep 2025cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) struggle with information forgetting and inefficiency in long-horizon, multi-turn dialogues. To address this, we propose a training-free prompt engineering method, the State-Update Multi-turn Dialogue Strategy. It utilizes "State Reconstruction" and "History Remind" mechanisms to effectively manage dialogue history. Our strategy shows strong performance across multiple multi-hop QA datasets. For instance, on the HotpotQA dataset, it improves the core information filtering score by 32.6%, leading to a 14.1% increase in the downstream QA score, while also reducing inference time by 73.1% and token consumption by 59.4%. Ablation studies confirm the pivotal roles of both components. Our work offers an effective solution for optimizing LLMs in long-range interactions, providing new insights for developing more robust Agents.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 23 references that are in the map. First posted on arXiv 22 Sep 2025.

Builds on

21 of 23 references.

References · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2024Qwen2.5 Technical Reportcited by 4,942
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  9. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  10. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  11. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  12. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
9 more
  1. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  2. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  3. 2023Active Retrieval Augmented Generationcited by 516
  4. 2025LLMs Get Lost In Multi-Turn Conversationcited by 429
  5. 2019QASC: A Dataset for Question Answering via Sentence Compositioncited by 252
  6. 2022Dense Text Retrieval based on Pretrained Language Models: A Surveycited by 136
  7. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 123
  8. 2015A Neural Network Approach to Context-Sensitive Generation of Conversational Responsescited by 98
  9. 2024Inference Scaling for Long-Context Retrieval Augmented Generationcited by 65

Built on by

Not cited yet.