mlsanityData to 7 Oct 2026

Retrieval Augmented Learning: A Retrial-based Large Language Model Self-Supervised Learning and Autonomous Knowledge Generation

arXiv 2505.01073 ↗First posted 2 May 2025cs.AIcited by 1

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

The lack of domain-specific data in the pre-training of Large Language Models (LLMs) severely limits LLM-based decision systems in specialized applications, while post-training a model in the scenarios requires significant computational resources. In this paper, we present Retrial-Augmented Learning (RAL), a reward-free self-supervised learning framework for LLMs that operates without model training. By developing Retrieval-Augmented Generation (RAG) into a module for organizing intermediate data, we realized a three-stage autonomous knowledge generation of proposing a hypothesis, validating the hypothesis, and generating the knowledge. The method is evaluated in the LLM-PySC2 environment, a representative decision-making platform that combines sufficient complexity with domain-specific knowledge requirements. Experiments demonstrate that the proposed method effectively reduces hallucination by generating and utilizing validated knowledge, and increases decision-making performance at an extremely low cost. Meanwhile, the approach exhibits potential in out-of-distribution(OOD) tasks, robustness, and transferability, making it a cost-friendly but effective solution for decision-making problems and autonomous knowledge generation.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 22 of its 32 references that are in the map. First posted on arXiv 2 May 2025.

Builds on

22 of 32 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024How Much Can RAG Help the Reasoning of LLM?3 Oct

Other references · 21

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2015Continuous control with deep reinforcement learningcited by 3,279
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  4. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  5. 2025s1: Simple test-time scalingcited by 1,311
  6. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  7. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 490
  8. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
  9. 2025TTRL: Test-Time Reinforcement Learningcited by 253
  10. 2023Exploring Large Language Models for Communication Games: An Empirical Study on Werewolfcited by 238
  11. 2024TradingAgents: Multi-Agents LLM Financial Trading Frameworkcited by 182
  12. 2025Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scalingcited by 135
9 more
  1. 2024Reinforcement Learning Enhanced LLMs: A Surveycited by 69
  2. 2023LLaMA Rider: Spurring Large Language Models to Explore the Open Worldcited by 21
  3. 2024SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language modelscited by 18
  4. 2024LLM-PySC2: Starcraft II learning environment for Large Language Modelscited by 9
  5. 2024SMAC-R1: The Emergence of Intelligence in Decision-Making Taskscited by 6
  6. 2024SMAC-Hard: Enabling Mixed Opponent Strategy Script and Self-play on SMACcited by 5
  7. 2025Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems in Minecraftcited by 5
  8. 2025Hierarchical Expert Prompt for Large-Language-Model: An Approach Defeat Elite AI in TextStarCraft II for the First Timecited by 4
  9. 2025Reflection of Episodes: Learning to Play Game from Expert and Self Experiencescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
  2. 2024Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models
  3. 2025R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning
  4. 2025Optimizing Knowledge Integration in Retrieval-Augmented Generation with Self-Selection
  5. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
  6. 2025SKILL-RAG: Self-Knowledge Induced Learning and Filtering for Retrieval-Augmented Generation
  7. 2024Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling
  8. 2025Post-training an LLM for RAG? Train on Self-Generated Demonstrations