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

arXiv: https://arxiv.org/abs/2603.03325 · HTML: https://mlsanity.com/paper/2603.03325/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 34 of its 48 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 34)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning](https://mlsanity.com/paper/2503.05379/) (2025)
- [User-LLM: Efficient LLM Contextualization with User Embeddings](https://mlsanity.com/paper/2402.13598/) (2024)
- [Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate](https://mlsanity.com/paper/2501.17703/) (2025)
- [Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents](https://mlsanity.com/paper/2405.16533/) (2024)
- [Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation](https://mlsanity.com/paper/2402.04616/) (2024)
- [ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions](https://mlsanity.com/paper/2505.14668/) (2025)
- [SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction](https://mlsanity.com/paper/2410.09008/) (2024)
- [RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agents](https://mlsanity.com/paper/2308.09904/) (2023)
- [Efficient Reinforcement Learning with Large Language Model Priors](https://mlsanity.com/paper/2410.07927/) (2024)
- [User Embedding Model for Personalized Language Prompting](https://mlsanity.com/paper/2401.04858/) (2024)
- [MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations](https://mlsanity.com/paper/2403.10943/) (2024)
- [Intent Detection in the Age of LLMs](https://mlsanity.com/paper/2410.01627/) (2024)
- [Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents](https://mlsanity.com/paper/2502.04392/) (2025)
- [User Intent Recognition and Satisfaction with Large Language Models: A User Study with ChatGPT](https://mlsanity.com/paper/2402.02136/) (2024)
- [Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking dialogs](https://mlsanity.com/paper/2402.11633/) (2024)
- [Towards Open Intent Discovery for Conversational Text](https://mlsanity.com/paper/1904.08524/) (2019)
- [Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling](https://mlsanity.com/paper/2504.13592/) (2025)
- [Step-DeepResearch Technical Report](https://mlsanity.com/paper/2512.20491/) (2025)
- [Toward Edge General Intelligence with Multiple-Large Language Model (Multi-LLM): Architecture, Trust, and Orchestration](https://mlsanity.com/paper/2507.00672/) (2025)

## Abstract (arXiv)

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.