# OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations

arXiv: https://arxiv.org/abs/2605.23668 · HTML: https://mlsanity.com/paper/2605.23668/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 22 May 2026.

## Builds on (most cited first, 19 of 19)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent](https://mlsanity.com/paper/2507.02259/) (2025)
- [MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents](https://mlsanity.com/paper/2506.15841/) (2025)
- [Augmenting Language Models with Long-Term Memory](https://mlsanity.com/paper/2306.07174/) (2023)
- [Proactive Human-Machine Conversation with Explicit Conversation Goals](https://mlsanity.com/paper/1906.05572/) (2019)
- [A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestion](https://mlsanity.com/paper/1507.02221/) (2015)
- [A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects](https://mlsanity.com/paper/2305.02750/) (2023)
- [Learning to Attend, Copy, and Generate for Session-Based Query Suggestion](https://mlsanity.com/paper/1708.03418/) (2017)
- [ShareChat: A Dataset of Chatbot Conversations in the Wild](https://mlsanity.com/paper/2512.17843/) (2025)
- [OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion](https://mlsanity.com/paper/2506.06913/) (2025)
- [CTR-Guided Generative Query Suggestion in Conversational Search](https://mlsanity.com/paper/2507.04072/) (2025)
- [From Clicks to Preference: A Multi-stage Alignment Framework for Generative Query Suggestion in Conversational System](https://mlsanity.com/paper/2508.15811/) (2025)
- [LLM-Driven Preference Data Synthesis for Proactive Prediction of the Next User Utterance in Human-Machine Dialogue](https://mlsanity.com/paper/2601.09713/) (2025)

## Built on by (most cited first, 1 of 1)

- [What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems](https://mlsanity.com/paper/2608.07565/) (2026)

## Abstract (arXiv)

Although large language model (LLM) conversational systems process millions of multi-turn dialogues daily, they remain fundamentally reactive: they respond only after the user types a query. A key step toward proactive interaction is next-query prediction, which anticipates the user's subsequent query based solely on the preceding dialogue. Progress on this task is hindered by the lack of dedicated benchmarks and a fundamental efficiency--quality trade-off: naively concatenating full dialogue history incurs linearly growing token consumption, while truncating to the latest turn discards crucial cross-turn context. Our key insight is that accurate prediction does not require re-reading raw history; it suffices to track the user's evolving intent trajectory across topics, unresolved needs, and interest shifts. We propose OnePred, which maintains a recursively updated memory as its sole cross-turn context, bounding the per-turn cost independently of conversation length. We train the model via a two-stage reinforcement learning pipeline that first teaches what to predict, then what to compress, shaping the memory into a prediction-oriented intent chain. To establish a rigorous testbed, we introduce NQP-Bench, spanning three diverse subsets. Experiments demonstrate that OnePred reduces per-turn token consumption by up to 22× compared to full-history inputs while consistently exceeding all baselines in prediction quality, with larger gains on longer conversations. Our code is publicly available at https://github.com/ZBWpro/OnePred.