EMNLP Findings2025
Divide, Optimize, Merge: Scalable Fine-Grained Generative Optimization for LLM Agents
Jiale Liu, Yifan Zeng, Shaokun Zhang, Chi Zhang, Malte Højmark-Bertelsen, Marie Normann Gadeberg, Huazheng Wang, Qingyun Wu
Abstract
LLM-based optimization has shown remarkable potential in improving agentic systems. However, the conventional approach of prompting LLM-based generative optimizer with the trajectories on the whole training dataset in a single pass becomes untenable as datasets grow, leading to context window overflow and degraded pattern recognition. To address these challenges, we propose Fine-grained Generative Optimization (FGO), a scalable framework that divides large optimization tasks into manageable subsets, performs targeted optimizations, and systematically combines optimized components through progressive merging. Evaluation across ALFWorld, Logistic-sQA, and GAIA benchmarks demonstrates that FGO outperforms conventional approach by 1.6-8.6% while reducing average prompt token consumption by 56.3%. Our framework provides a practical solution for scaling up LLMbased generative optimization of increasingly sophisticated agentic systems. Further analysis demonstrates that FGO achieves the most consistent performance gain in all training dataset sizes, showcasing its scalability and efficiency.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Self-Refine: Iterative Refinement with Self-Feedback
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Language Models are Few-Shot Learners
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Self-Refine: Iterative Refinement with Self-Feedback cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Reflexion: language agents with verbal reinforcement learning cites Self-Refine: Iterative Refinement with Self-Feedback
- Reflexion: language agents with verbal reinforcement learning cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds on43
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
- Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran et al.NeurIPS 2023 · 5,068 citations
- Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan et al.NeurIPS 2023 · 4,972 citations
Related papers
- PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based SamplingYongchao Chen, Jacob Arkin, Yilun Hao, Yang Zhang et al.EMNLP 2024 · 6 citations
- TaskCraft: Automated Generation of Agentic TasksDingfeng Shi, Jingyi Cao, Qianben Chen, Weichen Sun et al.ICLR 2026 · 49 citations
- FLAIRR-TS - Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time SeriesGunjan Jalori, Preetika Verma, Sercan Ö. ArikEMNLP Findings 2025 · 1 citation
- SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm IntelligenceYao Zhang, Chenyang Lin, Shijie Tang, Haokun Chen et al.EMNLP 2025 · 2 citations
- STARK: Strategic Team of Agents for Refining KernelsJuncheng Dong, Yang Yang, Tao Liu, Yang Wang et al.ICLR 2026 · 26 citations
