Skip to content

Strategy Accumulation and Guided Execution for Automated LLM Fine-Tuning

Sep 2026 · 0 citations · 54 references
Computer Science

TL;DR

Results show that persistent strategy experience provides effective guidance for automated fine-tuning on unseen tasks, and propose Strategy Accumulation and Guided Execution (SAGE), a two-stage framework that makes automated fine-tuning search cumulative.

Abstract

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.

View source

Similar papers

#artificial intelligence Preprint Sep 2026

LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery

Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable but can omit useful evidence from other experiments, whereas including the full experimental history produces long, redundant contexts. We introduce a simple, single-agent d...

Bo Yuan, Wenqian Ye, Ze-Lin Zhao et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Direct Optimization of Generators for Search in Automated Theorem Proving

This work extends Compute-Aligned Training to this setting through an abstraction of policy-guided search, deriving tractable, trace-supported losses and introduces a search-agnostic uniform-allocation (UA) loss that accounts for the budget without specifying the specific search.

Adam Ousherovitch, A. Tewari · 0 citations
#natural language process... Open access Oct 2026

SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents

SEDIMA is introduced, a persistent hierarchical insight memory for evolutionary search agents that distills raw traces into natural-language insights, clusters them by semantic similarity using attention-weighted centroids, and retrieves relevant guidance to condition future mutations, accumulating transferable knowled...

Amirhossein Abaskohi, Mahdi Mostajabdaveh, Zi-Rui Zhou · 0 citations
#small language model Preprint Aug 2026

StrategyBench: Evaluating Explicit Strategy Induction in Large Language Models

This work proposes StrategyBench, which selects strategy-inducible tasks from BIG-Bench, constructs reference strategies, and defines evaluation metrics along two dimensions: strategy quality and downstream utility, and experiments show that explicit strategy utility differs substantially across task categories and dep...

Jing-Han Tan, Yuanzhe Wang, Lu Chen et al. · 0 citations
Sep 2026

AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery

AlgoEvo is introduced, a unified agentic architecture that transforms automated algorithm discovery into an interactive, knowledge-accumulating process, demonstrating strong intra-task accumulation, cross-task transfer, and the ability to reproduce or exceed the strongest existing methods through flexible skill activat...

Jun-Hao Qiu, Qing-Long Hu, Ji Cheng et al. · 2 citations
Conference Open access Sep 2026

A Review on Test-Time Scaling for Agentic Large Language Models

A novel RAIE taxonomy along four scaling dimensions is proposed, which optimizes the entire thought process through search algorithms and self-verification, and introduces a task-oriented guideline for choosing the best TTS strategy.

Jia-Yu An, Zheng Chen, Yong-Cheng Jing et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Sep 29, 2026

Who we become when we talk to machines

Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.