{"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/agent-as-a-judge-evaluate-agents-with-agents","title":"Agent-as-a-Judge: Evaluate Agents with Agents","arxiv_id":"2410.10934","date":"2024-10-14","proceeding":null,"authors":["Mingchen Zhuge","Changsheng Zhao","Dylan Ashley","Wenyi Wang","Dmitrii Khizbullin","Yunyang Xiong","Zechun Liu","Ernie Chang","Raghuraman Krishnamoorthi","Yuandong Tian","Yangyang Shi","Vikas Chandra","Jürgen Schmidhuber"],"abstract":"Contemporary evaluation techniques are inadequate for agentic systems. These approaches either focus exclusively on final outcomes -- ignoring the step-by-step nature of agentic systems, or require excessive manual labour. To address this, we introduce the Agent-as-a-Judge framework, wherein agentic systems are used to evaluate agentic systems. This is an organic extension of the LLM-as-a-Judge framework, incorporating agentic features that enable intermediate feedback for the entire task-solving process. We apply the Agent-as-a-Judge to the task of code generation. To overcome issues with existing benchmarks and provide a proof-of-concept testbed for Agent-as-a-Judge, we present DevAI, a new benchmark of 55 realistic automated AI development tasks. It includes rich manual annotations, like a total of 365 hierarchical user requirements. We benchmark three of the popular agentic systems using Agent-as-a-Judge and find it dramatically outperforms LLM-as-a-Judge and is as reliable as our human evaluation baseline. Altogether, we believe that Agent-as-a-Judge marks a concrete step forward for modern agentic systems -- by providing rich and reliable reward signals necessary for dynamic and scalable self-improvement.","url_abs":"https://arxiv.org/abs/2410.10934v2","url_pdf":"https://arxiv.org/pdf/2410.10934v2.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":"agent-as-a-judge-evaluate-agents-with-agents","repo_url":"https://github.com/metauto-ai/agent-as-a-judge","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[{"slug":"devai","name":"DevAI","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2410.10934","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}