mlsanityData to 14 Oct 2026

LLM Agents for Automated Post-Training via Structured Recipe Optimization

arXiv 2610.18572 ↗First posted 13 Oct 2026cs.AI cs.LGcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks also fits: Reinforcement learning for LLM agents

Abstract (arXiv)

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 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 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 41.1 versus 15.4 for the strongest baseline on Qwen3-1.7B with GPT-5.4, and 53.8 versus 40.8 on Qwen3-4B with DeepSeek-V4-Flash. Our code is available at https://github.com/RuohLiuq/SRO.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 21 of its 27 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

21 of 27 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026AutoTrainess: Teaching Language Models to Improve Language Models Autonomously30 Jun
  2. 2026Agent^2 RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training?12 Apr
  3. 2026PostTrainBench: Can LLM Agents Automate LLM Post-Training?9 Mar

Other references · 18

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  5. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  6. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 739
  7. 2024LESS: Selecting Influential Data for Targeted Instruction Tuningcited by 532
  8. 2023UltraFeedback: Boosting Language Models with Scaled AI Feedbackcited by 406
  9. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  10. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 135
  11. 2025A Survey on Post-training of Large Language Modelscited by 54
  12. 2026Multi-Task GRPO: Reliable LLM Reasoning Across Taskscited by 14
6 more
  1. 2025Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Schedulingcited by 10
  2. 2025DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collectionscited by 9
  3. 2026Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVRcited by 5
  4. 2026DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixturescited by 4
  5. 2026Automatic Configuration of LLM Post-Training Pipelinescited by 3
  6. 2026DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agents
  2. 2026AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensive
  3. 2025AutoPDL: Automatic Prompt Optimization for LLM Agents
  4. 2026What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search
  5. 2025OPT-BENCH: Evaluating LLM Agent on Large-Scale Search Spaces Optimization Problems
  6. 2026FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents
  7. 2025LLMs for Bayesian Optimization in Scientific Domains: Are We There Yet?
  8. 2024Offline Training of Language Model Agents with Functions as Learnable Weights