R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning (2026 · 7 citations)
LLMs with strong reasoning skills still hallucinate on knowledge-heavy questions. Prompt-driven multi-step RAG pipelines also tend to choose poorly when and what to retrieve, and they keep reasoning and retrieval only loosely connected.
CheckRLM: Effective Knowledge–Thought Coherence Checking in Retrieval-Augmented Reasoning (2026)
Reasoning Language Models (RLMs) such as OpenAI-o1 and DeepSeek-R1 produce long chains of thought. On knowledge-intensive questions, a single wrong fact early in the chain can spread to later steps and corrupt the final answer, a problem known as error accumulation. CheckRLM addresses this with Retrieval-Augmented…

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

Disentangled Contrastive Hypergraph Learning for Next POI Recommendation ↗International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · no summary yetYantong Lai et al.2024 · 56 citations
R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement LearningFindings of the Association for Computational LinguisticsQingfei Zhao, Ruobing Wang, Dingling Xu, et al.2026 · 7 citations
CheckRLM: Effective Knowledge–Thought Coherence Checking in Retrieval-Augmented ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Dingling Xu, Ruobing Wang, Qingfei Zhao, et al.2026

Co-authors here

11 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 8 times (of the 149,439 papers whose bibliographies we read); 3 citing papers with a page here →.

Updated 2 November 2026