# Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling

arXiv: https://arxiv.org/abs/2504.13592 · HTML: https://mlsanity.com/paper/2504.13592/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 18 Apr 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 10 of 10)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines](https://mlsanity.com/paper/2007.12720/) (2020)
- [AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls](https://mlsanity.com/paper/2402.04253/) (2024)
- [What Makes a Reward Model a Good Teacher? An Optimization Perspective](https://mlsanity.com/paper/2503.15477/) (2025)
- [Exploring Zero and Few-shot Techniques for Intent Classification](https://mlsanity.com/paper/2305.07157/) (2023)
- [DARD: A Multi-Agent Approach for Task-Oriented Dialog Systems](https://mlsanity.com/paper/2411.00427/) (2024)

## Built on by (most cited first, 12 of 12)

- [VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding](https://mlsanity.com/paper/2505.01481/) (2025)
- [On Predictability of Reinforcement Learning Dynamics for Large Language Models](https://mlsanity.com/paper/2510.00553/) (2025)
- [Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards](https://mlsanity.com/paper/2505.02686/) (2025)
- [Deep Learning Approaches for Multimodal Intent Recognition: A Survey](https://mlsanity.com/paper/2507.22934/) (2025)
- [Learning to Reason for Hallucination Span Detection](https://mlsanity.com/paper/2510.02173/) (2025)
- [Empowering LLMs in Task-Oriented Dialogues: A Domain-Independent Multi-Agent Framework and Fine-Tuning Strategy](https://mlsanity.com/paper/2505.14299/) (2025)
- [ToolSample: Dual Dynamic Sampling Methods with Curriculum Learning for RL-based Tool Learning](https://mlsanity.com/paper/2509.14718/) (2025)
- [E3-Rewrite: Learning to Rewrite SQL for Executability, Equivalence,and Efficiency](https://mlsanity.com/paper/2508.09023/) (2025)
- [Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking](https://mlsanity.com/paper/2509.06472/) (2025)
- [IntPro: A Proxy Agent for Context-Aware Intent Understanding via Retrieval-conditioned Inference](https://mlsanity.com/paper/2603.03325/) (2026)
- [Don't Wait to Reply: Towards Responsive yet Thoughtful Dialogue through Proactive Thinking](https://mlsanity.com/paper/2607.03093/) (2026)
- [PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation](https://mlsanity.com/paper/2610.11167/) (2026)

## Abstract (arXiv)

Intent detection, a critical component in task-oriented dialogue (TOD) systems, faces significant challenges in adapting to the rapid influx of integrable tools with complex interrelationships. Existing approaches, such as zero-shot reformulations and LLM-based dynamic recognition, struggle with performance degradation when encountering unseen intents, leading to erroneous task routing. To enhance the model's generalization performance on unseen tasks, we employ Reinforcement Learning (RL) combined with a Reward-based Curriculum Sampling (RCS) during Group Relative Policy Optimization (GRPO) training in intent detection tasks. Experiments demonstrate that RL-trained models substantially outperform supervised fine-tuning (SFT) baselines in generalization. Besides, the introduction of the RCS, significantly bolsters the effectiveness of RL in intent detection by focusing the model on challenging cases during training. Moreover, incorporating Chain-of-Thought (COT) processes in RL notably improves generalization in complex intent detection tasks, underscoring the importance of thought in challenging scenarios. This work advances the generalization of intent detection tasks, offering practical insights for deploying adaptable dialogue systems.