ACL Findings2026
Supplement Generation Training for Enhancing Agentic Task Performance
Young Min Cho, Daniele Bonadiman, Divya Bhargavi, Tamer Alkhouli, Salvatore Romeo, Dongwei Jiang, Khushbu Pahwa, Yubin Ge, Etsuko Ishii, Monica Sunkara, Yi Zhang
Abstract
Training large foundation models for agentic tasks is increasingly impractical due to the high computational costs, long iteration cycles, and rapid obsolescence as new models are continuously released. Instead of post-training massive models for every new task or domain, we propose Supplement Generation Training (SGT), a more efficient and sustainable strategy. SGT trains a smaller LLM to generate useful supplemental text that, when appended to the original input, helps the larger LLM solve the task more effectively. These lightweight models can dynamically adapt supplements to task requirements, improving performance without modifying the underlying large models. This approach decouples task-specific optimization from large foundation models and enables more flexible, cost-effective deployment of LLMpowered agents in real-world applications.
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
Builds on15
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Improving Factuality and Reasoning in Language Models through Multiagent DebateYilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum et al.ICML 2024 · 1,562 citations
- DS-1000: A Natural and Reliable Benchmark for Data Science Code GenerationYuhang Lai, Chengxi Li, Yiming Wang, Tianyi Zhang et al.ICML 2023 · 504 citations
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement LearningLakshya A. Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems et al.ICLR 2026 · 466 citations
- Large Language Models are Human-Level Prompt EngineersYongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster et al.ICLR 2023 · 297 citations
Related papers
- Offline Training of Language Model Agents with Functions as Learnable WeightsShaokun Zhang, Jieyu Zhang, Jiale Liu, Linxin Song et al.ICML 2024 · 41 citations
- LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM AgentsTaro Yano, Yoichi Ishibashi, Masafumi OyamadaEMNLP 2025
- Divide, Optimize, Merge: Scalable Fine-Grained Generative Optimization for LLM AgentsJiale Liu, Yifan Zeng, Shaokun Zhang, Chi Zhang et al.EMNLP Findings 2025
- Scaling Agents via Continual Pre-trainingLiangcai Su, Zhen Zhang, Guangyu Li, Zhuo Chen et al.ICLR 2026 · 46 citations
- Task Oriented In-Domain Data AugmentationXiao Liang, Xinyu Hu, Simiao Zuo, Yeyun Gong et al.EMNLP 2024 · 1 citation
