{"ID":2865327,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.22315","arxiv_id":"2509.22315","title":"PRIME: Planning and Retrieval-Integrated Memory for Enhanced Reasoning","abstract":"Inspired by the dual-process theory of human cognition from \\textit{Thinking, Fast and Slow}, we introduce \\textbf{PRIME} (Planning and Retrieval-Integrated Memory for Enhanced Reasoning), a multi-agent reasoning framework that dynamically integrates \\textbf{System 1} (fast, intuitive thinking) and \\textbf{System 2} (slow, deliberate thinking). PRIME first employs a Quick Thinking Agent (System 1) to generate a rapid answer; if uncertainty is detected, it then triggers a structured System 2 reasoning pipeline composed of specialized agents for \\textit{planning}, \\textit{hypothesis generation}, \\textit{retrieval}, \\textit{information integration}, and \\textit{decision-making}. This multi-agent design faithfully mimics human cognitive processes and enhances both efficiency and accuracy. Experimental results with LLaMA 3 models demonstrate that PRIME enables open-source LLMs to perform competitively with state-of-the-art closed-source models like GPT-4 and GPT-4o on benchmarks requiring multi-hop and knowledge-grounded reasoning. This research establishes PRIME as a scalable solution for improving LLMs in domains requiring complex, knowledge-intensive reasoning.","short_abstract":"Inspired by the dual-process theory of human cognition from \\textit{Thinking, Fast and Slow}, we introduce \\textbf{PRIME} (Planning and Retrieval-Integrated Memory for Enhanced Reasoning), a multi-agent reasoning framework that dynamically integrates \\textbf{System 1} (fast, intuitive thinking) and \\textbf{System 2} (s...","url_abs":"https://arxiv.org/abs/2509.22315","url_pdf":"https://arxiv.org/pdf/2509.22315v3","authors":"[\"Hieu Tran\",\"Zonghai Yao\",\"Nguyen Luong Tran\",\"Zhichao Yang\",\"Feiyun Ouyang\",\"Shuo Han\",\"Razieh Rahimi\",\"Hong Yu\"]","published":"2025-09-26T13:16:36Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false}