LLM Agents for Automated Post-Training via Structured Recipe Optimization

Automated post-training transforms pre-trained large language models (LLMs) into models capable of handling diverse domains by automatically constructing and optimizing a recipe of coupled decisions over data sources, data processing, cross-domain composition, and training configuration under a limited experimental budget. Existing automation either searches predefined recipe spaces that enable systematic optimization but remain fixed rather than adapting their available choices to the target tasks, or uses open-ended agents that discover task-specific choices but leave them implicit in trial-level edits, limiting their systematic reuse and recombination across trials. To fill this gap, we introduce $\text{optimization over a task-adapted recipe space}$, a novel paradigm that can adapt the recipe space itself to the target tasks while representing its choices explicitly for systematic reuse, recombination, and joint optimization. We instantiate this paradigm with $\text{Structured Recipe Optimization (SRO)}$, comprising an LLM-based Recipe-Space Designer that constructs the task-adapted recipe space and a Multi-Domain Recipe Optimizer that uses structured trial evidence to guide LLM candidate construction and multi-objective Bayesian trial selection. Extensive experiments show that SRO achieves the highest average score in all evaluated target-model and agent-LLM combinations. In joint post-training across three capability domains and six benchmarks, SRO reaches $\text{41.1 versus 15.4}$ for the strongest baseline on Qwen3-1.7B with GPT-5.4, and $\text{53.8 versus 40.8}$ on Qwen3-4B with DeepSeek-V4-Flash.