IntPro: A Proxy Agent for Context-Aware Intent Understanding via Retrieval-conditioned Inference

TL;DR

This work proposes IntPro, a proxy agent that learns to adapt to individual users via retrieval-conditioned intent inference, and designs intent explanations that abstract how contextual signals connect to expressed intents, and store them in an individual intent history library for retrieval.

Abstract

Large language models (LLMs) have become integral to modern Human-AI collaboration workflows, where accurately understanding user intent serves as a crucial step for generating satisfactory responses. Context-aware intent understanding, which involves inferring user intentions from situational environments, is inherently challenging because it requires reasoning over both the immediate context and the user's underlying motivations that drive their behavior. Moreover, existing approaches often treat intent understanding as a static recognition task, overlooking users' accumulated intent patterns that could provide valuable references for more accurate and generalizable understanding. To address this gap, we propose IntPro, a proxy agent that learns to adapt to individual users via retrieval-conditioned intent inference. We design intent explanations that abstract how contextual signals connect to expressed intents, and store them in an individual intent history library for retrieval. We train IntPro through supervised fine-tuning on retrieval-conditioned trajectories and multi-turn Group Relative Policy Optimization (GRPO) with tool-aware reward functions, enabling the agent to learn when to leverage historical intent patterns and when to infer directly. Experiments across three diverse scenarios (Highlight-Intent, MIntRec2.0, and Weibo Post-Sync) demonstrate that IntPro achieves strong intent understanding performance with effective context-aware reasoning capabilities across different scenarios and model types.

Figures (11)

• Figure 1: Current Human-LLM Collaboration (A) VS Human-Proxy-LLM Collaboration with context-aware intent understanding (B).
• Figure 2: Overview of our data construction pipeline for context-aware intent understanding, including intent history library construction and retrieval-conditioned intent inference trajectory generation.
• Figure 3: The whole training pipeline of IntPro includes supervised fine-tuning and GRPO with tool-aware reward function.
• Figure 4: t-SNE Visualization Comparison on MIntRec2.0. (a) Raw human context representations show overlapping clusters with weak intent separation. (b) Intent explanation embeddings exhibit clearer clusters, indicating improved separation.
• Figure 5: Performance of Four Fine-Tuning Strategies (Answer-only, Explanation-based, Reasoning-based, Retrieval-conditioned) across Two Models and Three Datasets.