AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Careful Queries, Credible Results: Teaching RAG Models Advanced Web Search Tools with Reinforcement Learning

Yuqin Dai, Shuo Yang, Guoqing Wang, Yong Deng, Zhanwei Zhang, Jun Yin, Pengyu Zeng, Zhenzhe Ying, Changhua Meng, Can Yi, Yuchen Zhou, Weiqiang Wang and 1 more

AAAI 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Source-restricting Reward (SR) to base RL training (ablation)WebFilter (Qwen2.5-7B-Instruct) · 2WikiACC_R: 55.2 -> 59.7Improved
add Source-restricting Reward (SR) to base RL training (ablation)WebFilter (Qwen2.5-7B-Instruct) · TriviaQAACC_L: 82.6 -> 86.0Improved
add Source-restricting Reward (SR) (ablation)WebFilter · advanced operator usage in queriesfraction of queries with advanced operators: less than 10% -> more than 75%Improved
add Retrieval-precision Reward (RR) on top of SR (ablation)WebFilter · BamboogleACC_R: 64.6 -> 73.1Improved
add Retrieval-precision Reward (RR) on top of SR (ablation)WebFilter · BamboogleACC_L: 65.2 -> 74.3Improved
add Retrieval-precision Reward (RR) on top of SR (ablation)WebFilter · HotpotQAACC_R: 50.6 -> 55.1Improved
add Retrieval-precision Reward (RR) on top of SR (ablation)WebFilter · NQACC_R: 41.4 -> 40.1Hurt
add Retrieval-precision Reward (RR) on top of SR (ablation)WebFilter · TriviaQAACC_R: 79.0 -> 77.5Hurt
add Source-restricting Reward (SR) to base (ablation)WebFilter · BamboogleACC_R: 64.9 -> 64.6No clear effect
use WebFilter instead of DeepResearcher on MuSiQueWebFilter · MuSiQueACC_R: 27.1 -> 24.5Hurt
train with RL over web search with advanced operatorsWebFilter · HotpotQAACC_R: 52.8 -> 55.1Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy