{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Daily Paper Cast","title":"ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization","html":"","width":"100%","height":180,"duration":1237,"description":"\n 🤗 Upvotes: 12 | cs.CL\n\n Authors:\n Yinjie Wang, Ling Yang, Guohao Li, Mengdi Wang, Bryon Aragam\n\n Title:\n ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization\n\n Arxiv:\n http://arxiv.org/abs/2502.04306v1\n\n Abstract:\n Recent research has leveraged large language model multi-agent systems for complex problem-solving while trying to reduce the manual effort required to build them, driving the development of automated agent workflow optimization methods. However, existing methods remain inflexible due to representational limitations, a lack of adaptability, and poor scalability when relying on discrete optimization techniques. We address these challenges with ScoreFlow, a simple yet high-performance framework that leverages efficient gradient-based optimization in a continuous space. ScoreFlow incorporates Score-DPO, a novel variant of the direct preference optimization method that accounts for quantitative feedback. Across six benchmarks spanning question answering, coding, and mathematical reasoning, ScoreFlow achieves an 8.2% improvement over existing baselines. Moreover, it empowers smaller models to outperform larger ones with lower inference costs. Project: https://github.com/Gen-Verse/ScoreFlow\n ","thumbnail_url":"https://img.transistorcdn.com/8lOVNnuwhrA3rxrDMv7Osu4j_t1-jORooO6NfGcQhcw/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81Zjg1/YzRhODczMDU4MmE4/OGMwN2FiNDlmYzI2/MDliMi5qcGVn.webp","thumbnail_width":300,"thumbnail_height":300}