paper-with-me

홈 › Papers

Reinforcement Fine-Tuning for History-Aware Dense Retriever in RAG

2026-02-03 · Yicheng Zhang, Zhen Qin, Zhaomin Wu, Wenqi Zhang, Shuiguang Deng arxiv

Retrieval-augmented generation (RAG) enables large language models (LLMs) to produce evidence-based responses, and its performance hinges on the matching between the retriever and LLMs. Retriever optimization has emerged as an efficient alternative to fine-tuning LLMs. However, existing solutions suffer from objective mismatch between retriever optimization and the goal of RAG pipeline. Reinforcement learning (RL) provides a promising solution to address this limitation, yet applying RL to retriever optimization introduces two fundamental challenges: 1) the deterministic retrieval is incompatible with RL formulations, and 2) state aliasing arises from query-only retrieval in multi-hop reasoning. To address these challenges, we replace deterministic retrieval with stochastic sampling and formulate RAG as a Markov decision process, making retriever optimizable by RL. Further, we incorporate retrieval history into the state at each retrieval step to mitigate state aliasing. Extensive experiments across diverse RAG pipelines, datasets, and retriever scales demonstrate consistent improvements of our approach in RAG performance.

📄 PDF Abstract BibTeX arXiv:2602.03645

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

History-Aware Conversational Dense Retrieval

2024-01-30 · Fengran Mo, Chen Qu, Kelong Mao, Tianyu Zhu 외

Conversational search facilitates complex information retrieval by enabling multi-turn interactions between users and the system. Supporting such interactions requires a comprehensive understanding of the conversational …

Conversational SearchInformation RetrievalRetrieval

STARE-VLA: Progressive Stage-Aware Reinforcement for Fine-Tuning Vision-Language-Action Models

2025-12-04 · Feng Xu, Guangyao Zhai, Xin Kong, Tingzhong Fu 외 arxiv

Recent advances in Vision-Language-Action (VLA) models, powered by large language models and reinforcement learning-based fine-tuning, have shown remarkable progress in robotic manipulation. Existing methods often treat …

Reinforcement Learning

A Framework for History-Aware Hyperparameter Optimisation in Reinforcement Learning

2023-03-09 · Juan Marcelo Parra-Ullauri, Chen Zhen, Antonio García-Domínguez, Nelly Bencomo 외

A Reinforcement Learning (RL) system depends on a set of initial conditions (hyperparameters) that affect the system's performance. However, defining a good choice of hyperparameters is a challenging problem. Hyperparame…

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)

GUI-Rise: Structured Reasoning and History Summarization for GUI Navigation

2025-10-31 · Tao Liu, Chongyu Wang, Rongjie Li, Yingchen Yu 외 arxiv

While Multimodal Large Language Models (MLLMs) have advanced GUI navigation agents, current approaches face limitations in cross-domain generalization and effective history utilization. We present a reasoning-enhanced fr…

Reinforcement LearningDomain Generalization

Closed-Loop CO2 Storage Control With History-Based Reinforcement Learning and Latent Model-Based Adaptation

2026-05-04 · Sofianos Panagiotis Fotias, Vassilis Gaganis arxiv

Closed-loop management of geological CO2 storage requires control policies that adapt to uncertain reservoir behavior while relying on observations that are realistically available during operation. This work formulates …

Reinforcement Learning