Towards Effective Experiential Learning: Dual Guidance for Utilization and Internalization

• URL: http://arxiv.org/abs/2603.24093v1
• Date: Wed, 25 Mar 2026 08:52:56 GMT
• Title: Towards Effective Experiential Learning: Dual Guidance for Utilization and Internalization
• Abstract summary: We propose textbfDual textbfGuidance textbfOptimization(textbfDGO) to improve training effectiveness.
• Score: 71.41478888201401
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, reinforcement learning~(RL) has become an important approach for improving the capabilities of large language models~(LLMs). In particular, reinforcement learning from verifiable rewards~(RLVR) has emerged as a promising paradigm for reasoning tasks. However, existing RL-based training still remains only a rough approximation to human learning. Human learners leverage both external and internal experience to guide exploration and gradually internalize useful trajectories into stable knowledge. Motivated by this gap, we ask: how can LLMs better utilize and internalize experience during RLVR training? To answer this question, we propose \textbf{D}ual \textbf{G}uidance \textbf{O}ptimization~(\textbf{DGO}), a unified framework that leverages \emph{external} and \emph{internal experience} to improve training effectiveness. Specifically, DGO first constructs an experience bank from previously explored trajectories. The policy then performs exploration under the joint guidance of the experience bank and the model's internal knowledge. The resulting trajectories are further used to refine the experience bank and optimize model parameters, forming a closed loop of experience utilization and internalization. Experiments show that DGO consistently outperforms baseline methods, suggesting that better utilization and internalization of experience lead to more effective reasoning.

Related papers

• Rethinking Continual Experience Internalization for Self-Evolving LLM Agents [36.80404778289742]
  We find that principle-level experience is more durable than instance-level experience.<n>Step-wise injection significantly outperforms global injection by aligning experience with intermediate decision states.<n>Off-policy context-distillation on high-quality teacher trajectories provides a substantially more stable training signal than on-policy context-distillation.
  arXiv  Detail & Related papers  (2026-06-03T10:30:09Z)
• Rethinking Experience Utilization in Self-Evolving Language Model Agents [51.10420305280499]
  Self-evolving agents improve by accumulating and reusing experience from past interactions.<n>This paper studies experience utilization as a critical design dimension of self-evolving agents.
  arXiv  Detail & Related papers  (2026-05-08T02:48:49Z)
• Retrieval-Augmented LLM Agents: Learning to Learn from Experience [16.248836438253814]
  We study how to train retrieval-augmented LLM agents to leverage retrieved trajectories in-context.<n>We establish a robust supervised fine-tuning (SFT) recipe using LoRA that outperforms several state-of-the-art agent training pipelines.<n>Our results demonstrate that this combined approach significantly improves generalization to unseen tasks.
  arXiv  Detail & Related papers  (2026-03-18T20:45:04Z)
• Online Experiential Learning for Language Models [99.90826536842337]
  Online Experiential Learning (OEL) is a framework that enables language models to continuously improve from their own deployment experience.<n>OEL operates in two stages: first, transferable experiential knowledge is extracted and accumulated from interaction trajectories collected on the user side.<n>We evaluate OEL on text-based game environments across multiple model scales and both thinking and non-thinking variants.
  arXiv  Detail & Related papers  (2026-03-17T17:57:49Z)
• LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs [73.27182315028021]
  LANPO is a framework that cleanly separates the roles of feedback: language guides exploration, while numerical rewards drive optimization.<n>Our work provides a robust method for integrating historical experiences into the LLM RL loop, creating more effective and data-efficient learning agents.
  arXiv  Detail & Related papers  (2025-10-18T15:51:19Z)
• ExGRPO: Learning to Reason from Experience [82.83309610498446]
  Reinforcement learning from verifiable rewards (RLVR) is an emerging paradigm for improving the reasoning ability of large language models.<n>Standard on-policy training discards rollout experiences after a single update, leading to computational inefficiency and instability.<n>In this paper, we are the first to investigate what makes a reasoning experience valuable and identify rollout correctness and entropy as effective indicators of experience value.
  arXiv  Detail & Related papers  (2025-10-02T17:31:30Z)
• Personalized Exercise Recommendation with Semantically-Grounded Knowledge Tracing [54.44838681588145]
  ExRec is a framework for personalized exercise recommendation with semantically-grounded knowledge tracing.<n>We show that ExRec generalizes robustly to new, unseen questions and that it produces interpretable student learning trajectories.
  arXiv  Detail & Related papers  (2025-07-15T07:54:04Z)
• R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning [83.256752220849]
  Large Language Models (LLMs) are powerful but prone to hallucinations due to static knowledge.<n>We introduce R1-Searcher++, a framework designed to train LLMs to adaptively leverage both internal and external knowledge sources.<n>Our experiments demonstrate that R1-Searcher++ outperforms previous RAG and reasoning methods and achieves efficient retrieval.
  arXiv  Detail & Related papers  (2025-05-22T17:58:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.