# When should I search more: Adaptive Complex Query Optimization with Reinforcement Learning

arXiv: https://arxiv.org/abs/2601.21208 · HTML: https://mlsanity.com/paper/2601.21208/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)

## Builds on (most cited first, 25 of 25)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries](https://mlsanity.com/paper/2401.15391/) (2024)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [Unsupervised Question Decomposition for Question Answering](https://mlsanity.com/paper/2002.09758/) (2020)
- [TopiOCQA: Open-domain Conversational Question Answering with Topic Switching](https://mlsanity.com/paper/2110.00768/) (2021)
- [Few-Shot Generative Conversational Query Rewriting](https://mlsanity.com/paper/2006.05009/) (2020)
- [Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search](https://mlsanity.com/paper/2303.06573/) (2023)
- [Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks](https://mlsanity.com/paper/2304.14732/) (2023)
- [Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations](https://mlsanity.com/paper/2102.10073/) (2021)
- [RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback](https://mlsanity.com/paper/2403.06840/) (2024)
- [Query expansion techniques for information retrieval: A survey](https://mlsanity.com/paper/1708.00247/) (2017)
- [CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search](https://mlsanity.com/paper/2406.05013/) (2024)
- [Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversation](https://mlsanity.com/paper/2402.11827/) (2024)
- [IterCQR: Iterative Conversational Query Reformulation with Retrieval Guidance](https://mlsanity.com/paper/2311.09820/) (2023)
- [A Comparison of Question Rewriting Methods for Conversational Passage Retrieval](https://mlsanity.com/paper/2101.07382/) (2021)
- [Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers](https://mlsanity.com/paper/2406.10991/) (2024)
- [AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment](https://mlsanity.com/paper/2407.01965/) (2024)
- [Synergistic Interplay between Search and Large Language Models for Information Retrieval](https://mlsanity.com/paper/2305.07402/) (2023)

## Abstract (arXiv)

Query optimization is a crucial component for the efficacy of Retrieval-Augmented Generation (RAG) systems. While reinforcement learning (RL)-based agentic and reasoning methods have recently emerged as a promising direction on query optimization, most existing approaches focus on the expansion and abstraction of a single query. However, complex user queries are prevalent in real-world scenarios, often requiring multiple parallel and sequential search strategies to handle disambiguation and decomposition. Directly applying RL to these complex cases introduces significant hurdles. Determining the optimal number of sub-queries and effectively re-ranking and merging retrieved documents vastly expands the search space and complicates reward design, frequently leading to training instability. To address these challenges, we propose a novel RL framework called Adaptive Complex Query Optimization (ACQO). Our framework is designed to adaptively determine when and how to expand the search process. It features two core components: an Adaptive Query Reformulation (AQR) module that dynamically decides when to decompose a query into multiple sub-queries, and a Rank-Score Fusion (RSF) module that ensures robust result aggregation and provides stable reward signals for the learning agent. To mitigate training instabilities, we adopt a Curriculum Reinforcement Learning (CRL) approach, which stabilizes the training process by progressively introducing more challenging queries through a two-stage strategy. Our comprehensive experiments demonstrate that ACQO achieves state-of-the-art performance on three complex query benchmarks, significantly outperforming established baselines. The framework also showcases improved computational efficiency and broad compatibility with different retrieval architectures, establishing it as a powerful and generalizable solution for next-generation RAG systems.