RL for RAG

RAG: Retrieval-Augmented Generation · RL: Reinforcement Learning

Follow this topic Ask about this topic

Latest papers

14 papers1 paper in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

Copying Is Not Grounding: Training Faithful Long-Form RAG with Authored-Sentence Credit
Oct 13, 2026Hoang Pham, Duc Anh Vu, Duy Tung Doan +2RL for RAG RAG Citation Faithfulness
Nanyang Technological University · Viettel AI, Viettel Group · VinUniversity
BRIDGE: Bilevel Retrieval-Credit-Aware Agentic Reinforcement Learning
Sep 29, 2026Quan Xiao, Mingda Liu, Gaowen Liu +2Reinforcement Learning Agentic RAG
Department of Electrical and Computer Engineering, Cornell University · Institute of Integrated Research, Institute of Science Tokyo · Cisco Research
Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG
Sep 4, 2026Shuyu Guo, Shuo Zhang, Zhaochun RenRetrieval-Augmented Generation LLM Inference Acceleration
Shandong University Qingdao, China · Bloomberg London, United Kingdom · Leiden University Leiden, The Netherlands
PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation
Aug 31, 2026MinKeon Kim, Namjun Lee, Jaekwang KimRetrieval-Augmented Generation Retrieval-Augmented Reasoning
Department of Applied Artificial Intelligence, Convergence Program for Social Innovation, Sungkyunkwan University, Seoul, South Korea
GTA-RAG: Graph-Trajectory-Augmented Reinforcement Learning for Multi-Turn Retrieval-Augmented Reasoning
Aug 23, 2026Jun Chen, Yongchao Liu, Pengyu Qiu +6Multi-Hop QA Agentic RAG
1Shenzhen University, Shenzhen, China · 2Great Bay University, Dongguan, China · 3Ant Group, Hangzhou, China +1
Harness-G: A Graph-Structured Harness for Search Agents
Jul 30, 2026Yanning Hou, Haoyuan Chen, Sihang Zhou +7RL for LLM Agents Credit Assignment in RL
National University of Defense Technology · Changsha, China
Understanding the Behaviors of Environment-aware Information Retrieval
Jun 15, 2026Ruifeng Yuan, Chaohao Yuan, David Dai +4Retrieval-Augmented Generation Reinforcement Learning
1Fudan University · 2Alibaba DAMO Academy · 3Chinese University of Hong Kong +2
CRITIC-R1: Learning Structured Critics for Retrieval-Augmented Generation
May 28, 2026Wenhan Xiao, Ziwei Zhang, Chuanyue Yu +4LLM Self-Correction Retrieval-Augmented Generation
Nankai University · Beihang University · Guangxi Normal University
Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL
May 14, 2026Jianbo Zhu, Xing Fang, Jing Wang +5Semantic ID Recommendation E-Commerce Search
Taobao & Tmall Group of Alibaba Hangzhou, China
CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generation
Apr 28, 2026Rui Qi, Fengran Mo, Sijin Lu +3Retrieval-Augmented Generation RL for RAG
School of Computer Science and Technology, Beijing Jiaotong University Beijing, China · RALI, Université de Montréal Montréal, Québec, Canada
AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
Apr 19, 2026Jingbo Sun, Wenyue Chong, Songjun Tu +7Agentic Retrieval Agentic RAG
SKL-MAIS, Institute of Automation, Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences +1
OThink-SRR1: Search, Refine and Reasoning with Reinforced Learning for Large Language Models
Mar 27, 2026Haijian Liang, Zenghao Niu, Junjie Wu +3RL for RAG Agentic RAG
Shenzhen University · OPPO Research Institute
APEX-Searcher: Refining Credit Assignment with Subgoaling for Agentic Retrieval-Augmented Generation
Mar 14, 2026Kun Chen, Qingchao Kong, Zhao Feifei +1Agentic RAG RL for RAG
University of Chinese Academy of Sciences · MAIS, Institute of Automation, Chinese Academy of Sciences · Wenge Technology Co., Ltd
Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training
Feb 26, 2026Tianle Xia, Ming Xu, Lingxiang Hu +7RL for RAG Agentic RAG
Tencent

Oct 13, 2026J/K move · Enter open · S save

Copying Is Not Grounding: Training Faithful Long-Form RAG with Authored-Sentence Credit

Hoang Pham, Duc Anh Vu, Duy Tung Doan, Cong-Duy T Nguyen+1

Nanyang Technological University · Viettel AI, Viettel Group · VinUniversity

RL for RAG RAG Citation Faithfulness LLM Grounding Retrieval-Augmented Generation Reward Hacking

Open paper AskPDF arXiv

In search engines and assistants, long-form RAG answers can mislead readers with claims their sources do not support. Faithfulness rewards, the share of supported sentences, train models toward fewer such claims. We show that these rewards are hacked by copying. A sentence copied from the passages is supported almost by construction, so trained models learn to copy rather than ground what they write. Common defenses only move the hack: a KL or copy penalty leaves copying in place or trades it for shorter, emptier answers and refusals. GRPO, the standard RL algorithm, makes it worse by giving every sentence its answer's advantage, reinforcing copied and grounded sentences alike. We propose Authored-Sentence Credit (ASC) , which fixes both by moving GRPO's reward and advantage from the answer to the sentence level. The reward credits only sentences that are authored rather than copied, say more than the question, and are supported by the passages. The advantage compares each sentence with every sentence sampled for the question, so one that earns no credit ranks last and is never reinforced. Across four models and two in-domain, three held-out corpora, only ASC lowers the error rate of authored sentences and writes more supported ones in every setting, by 38% and 46% at the median under held-out evaluators, giving readers more grounded information. It takes none of these shortcuts, and two LLM judges comparing whole answers prefer no baseline to the base model but rate ASC's answers on par with it. We conclude that a faithfulness reward should credit what a model writes, not what it copies.