RAG-R1: Incentivizing the Search and Reasoning Capabilities of LLMs through Multi-query Parallelism

Documenti analoghi

• ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning
  di: Zhao, Shu, et al.
  Pubblicazione: (2025)
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
  di: Song, Huatong, et al.
  Pubblicazione: (2025)
• DistRAG: Towards Distance-Based Spatial Reasoning in LLMs
  di: Schneider, Nicole R, et al.
  Pubblicazione: (2025)
• FeB4RAG: Evaluating Federated Search in the Context of Retrieval Augmented Generation
  di: Wang, Shuai, et al.
  Pubblicazione: (2024)
• From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents
  di: Zhang, Weizhi, et al.
  Pubblicazione: (2025)