cs.CLFeb 10, 2026

IntPro: Context-Aware Intent Inference via Selective Retrieval from User History

Authors: Guanming Liu, Meng Wu, Peng Zhang, Yu Zhang, Yubo Shu, Xianliang Huang, Kainan Tu, Ning Gu, 

Organizations: Fudan University, China · Lenovo Group Ltd, China

Abstract

Accurately understanding user intent in context is essential for large language models (LLMs) to provide effective assistance. However, observed behavior may support multiple plausible intents, making the current context alone insufficient for identifying the user's underlying goal. A user's interaction history may contain recurring context-to-intent patterns that help disambiguate the current intent. Leveraging such historical patterns requires deciding whether to invoke retrieval for the current context and, if so, forming queries that express plausible intents rather than relying on contextual similarity alone. We present IntPro, a proxy agent that learns to either infer intent directly from the current context or generate candidate intent explanations to retrieve intent-aligned records from the user's history. We design intent explanations as a shared intent-oriented natural-language form that expresses the observed action, its functional goal, and a cue-to-intent rationale. Label-conditioned explanations represent historical records, while candidate explanations generated from the current context serve as retrieval queries in the same form. IntPro first learns direct and retrieval-conditioned inference through Direct-and-Retrieval supervised fine-tuning (SFT). IntPro then uses multi-turn GRPO with a retrieval-decision reward to jointly optimize intent prediction and selective retrieval mechanism. Experiments across three scenarios and three model backbones demonstrate that IntPro consistently improves context-aware intent inference.

Figures & tables

Explore similar work

CardsList
  1. Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering

    May 12, 2026Maryam Amirizaniani, Benjamin Charles Germain Lee, Jevin West +1RL for Language ModelsLLM Personalization

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

    May 22, 2026Jiangwang Chen, Bowen Zhang, Zixin Song +4Long-Term Conversational MemoryEfficient Language Model Inference

  3. IntentGrasp: A Comprehensive Benchmark for Intent Understanding

    May 7, 2026Yuwei Yin, Chuyuan Li, Giuseppe CareniniLLM EvaluationIntent Classification