← Back to all news
arXiv AI By Quan Xiao, Mingda Liu, Gaowen Liu, Katsuki Fujisawa, Tianyi Chen

BRIDGE: Bilevel Retrieval-Credit-Aware Agentic Reinforcement Learning

Read the original on arXiv AI →

The paper introduces BRIDGE, a bilevel optimization framework that jointly trains a large language model (LLM) and a retriever for agentic reinforcement learning (ARL). It demonstrates that adapting the retriever before the policy yields better rewards, and that BRIDGE outperforms existing methods on seven open‑domain QA benchmarks and medical QA tasks, achieving significant gains in accuracy and reasoning quality.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computation and Language
Aug 25

GTA-RAG: Graph-Trajectory-Augmented Reinforcement Learning for Multi-Turn Retrieval-Augmented Reasoning

arXiv:2608.22479v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) enables LLMs to access external knowledge for answering knowledge-intensive questions. For complex multi-hop quest...

By Jun Chen, Yongchao Liu, Pengyu Qiu, Jiajun Zheng, Juelu Zhang, Yujie Zeng, Qin Zhang, Ziyue Qiao, Xiao Luo
llmsragagentsreinforcement-learningbenchmarks
More like this →
arXiv AI
Jul 14

To Answer or to Abstain: Mitigating Search-Agent Hallucinations via Abstention-Aware Reinforcement Learning

arXiv:2607. 10738v1 Announce Type: cross Abstract: Recent advances in equipping Large Language Models (LLMs) with search tools and outcome-reward reinforcement learning (RL) have achieved new state-of-the-art results on open-domain QA tasks.

By Fengji Zhang, Tianyu Fan, Yuxiang Zheng, Xinyao Niu, Chengen Huang, Jacky Keung, Bei Chen
llmsagentsreinforcement-learningbenchmarkssafety
More like this →
Hugging Face Trending Papers
Jul 12

To Answer or to Abstain: Mitigating Search-Agent Hallucinations via Abstention-Aware Reinforcement Learning

Recent advances in equipping Large Language Models (LLMs) with search tools and outcome-reward reinforcement learning (RL) have achieved new state-of-the-art results on open-domain QA tasks. However, we argue that current training paradigms harbor a critical vulnerability: they predominantly reward correct answers but fail to penalize fabricated ones when retrieval fails, thereby implicitly exacerbating hallucinations.

llmsagentsreinforcement-learningbenchmarkssafety
More like this →
arXiv Machine Learning
Aug 12

SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task

arXiv:2607. 24850v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have enabled search agents to autonomously tackle complex tasks across extended search and reasoning horizons.

By Lang Mei, Xiaohan Yu, Chong Chen, Liyan Liu, Xiangnan Chen, Jinchao Ma, Chao Feng, Li Huang, Siyu Mo, Sichen Kang, Yunkun Xu, Zhihan Yang, Zhujun Xue, Jingren Zhang, Qing He, Yingdi Huang, Hao Jiang, Ziao Ma, Zewei Pan, Minhao Sun, Zhuo Tao, Jinzhao Xiao, Gangtao Xin, Huanyao Zhang, Wenjian Zhang, Jiangshan Zhang, Guojie Zhu, Fangzhou Zou, Jiaxin Mao, Wentao Zhang
llmsagentsreinforcement-learningfine-tuningbenchmarks
More like this →
arXiv AI
Jun 3

UR$^2$: Unify RAG and Reasoning through Reinforcement Learning

arXiv:2508. 06165v5 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown strong capabilities through two complementary paradigms: Retrieval-Augmented Generation (RAG) for knowledge grounding and Reinforcement Learning from Verifiable Rewards (RLVR) for complex reasoning.

By Weitao Li, Boran Xiang, Xiaolong Wang, Zhinan Gou, Weizhi Ma, Yang Liu
llmsragreinforcement-learningbenchmarks
More like this →