# Strategy Accumulation and Guided Execution for Automated LLM Fine-Tuning

arXiv: https://arxiv.org/abs/2609.22257 · HTML: https://mlsanity.com/paper/2609.22257/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 45 of its 54 references that are in the map.
- First posted on arXiv 6 Sep 2026.

## Builds on (most cited first, 30 of 45)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [BOHB: Robust and Efficient Hyperparameter Optimization at Scale](https://mlsanity.com/paper/1807.01774/) (2018)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge](https://mlsanity.com/paper/2303.14070/) (2023)
- [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026)
- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [Generalizing Verifiable Instruction Following](https://mlsanity.com/paper/2507.02833/) (2025)
- [JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models](https://mlsanity.com/paper/2311.05997/) (2023)
- [Large Language Models to Enhance Bayesian Optimization](https://mlsanity.com/paper/2402.03921/) (2024)
- [DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning](https://mlsanity.com/paper/2402.17453/) (2024)
- [ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation](https://mlsanity.com/paper/2306.02022/) (2023)
- [LawBench: Benchmarking Legal Knowledge of Large Language Models](https://mlsanity.com/paper/2309.16289/) (2023)
- [AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML](https://mlsanity.com/paper/2410.02958/) (2024)

## Abstract (arXiv)

Producing task-specific large language models requires discovering effective training strategies through experimentation. Automated fine-tuning systems have made this experimentation feasible with far less manual effort. However, these systems are stateless: each search discards its discovered strategies, dataset insights, and hyperparameter findings once it ends. Every new task must then repeat this costly search from a cold start. To address this, we propose Strategy Accumulation and Guided Execution (SAGE), a two-stage framework that makes automated fine-tuning search cumulative. In the first stage, a multi-agent pipeline performs Monte Carlo Tree Search-based exploration. A parallel Distillation Agent extracts task-specific exploration records and confidence-scored cross-task insights, which together constitute a structured experience repository. In the second stage, SAGE retrieves relevant experience from this repository and selects what applies to guide training on the new task. We evaluate SAGE on nine unseen tasks spanning both single- and cross-category settings. In single-round execution, SAGE's accumulated experience raises the average relative improvement over baseline from 3.2% to 15.6%, a 12.4-percentage-point gain over the same pipeline without it. These results show that persistent strategy experience provides effective guidance for automated fine-tuning on unseen tasks.