{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/360degrea-towards-a-reusable-experience","title":"360$^\\circ$REA: Towards A Reusable Experience Accumulation with 360° Assessment for Multi-Agent System","arxiv_id":"2404.05569","date":"2024-04-08","proceeding":null,"authors":["Shen Gao","Hao Li","Chengrui Huang","Quan Tu","Zhiliang Tian","Minlie Huang","Shuo Shang"],"abstract":"Large language model agents have demonstrated remarkable advancements across various complex tasks. Recent works focus on optimizing the agent team or employing self-reflection to iteratively solve complex tasks. Since these agents are all based on the same LLM, only conducting self-evaluation or removing underperforming agents does not substantively enhance the capability of the agents. We argue that a comprehensive evaluation and accumulating experience from evaluation feedback is an effective approach to improving system performance. In this paper, we propose Reusable Experience Accumulation with 360$^\\circ$ Assessment (360$^\\circ$REA), a hierarchical multi-agent framework inspired by corporate organizational practices. The framework employs a novel 360$^\\circ$ performance assessment method for multi-perspective performance evaluation with fine-grained assessment. To enhance the capability of agents in addressing complex tasks, we introduce dual-level experience pool for agents to accumulate experience through fine-grained assessment. Extensive experiments on complex task datasets demonstrate the effectiveness of 360$^\\circ$REA.","url_abs":"https://arxiv.org/abs/2404.05569v3","url_pdf":"https://arxiv.org/pdf/2404.05569v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"360degrea-towards-a-reusable-experience","repo_url":"https://github.com/LLLQAQFFF/360REA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.05569","atlas_url":"https://app.syntology.ai/?focus=2404.05569","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}