Growing Through Experience: Scaling Episodic Grounding in Language Models

• URL: http://arxiv.org/abs/2506.01312v1
• Date: Mon, 02 Jun 2025 04:52:19 GMT
• Title: Growing Through Experience: Scaling Episodic Grounding in Language Models
• Authors: Chunhui Zhang, Sirui, Wang, Zhongyu Ouyang, Xiangchi Yuan, Soroush Vosoughi,
• Abstract summary: Language models (LMs) require robust episodic grounding to excel at physical planning tasks.<n>Current episodic grounding approaches struggle with scalability and integration.<n>We propose a scalable weak-to-strong episodic learning framework that effectively transfers episodic behaviors from smaller to larger LMs.
• Score: 67.27024505353384
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language models (LMs) require robust episodic grounding-the capacity to learn from and apply past experiences-to excel at physical planning tasks. Current episodic grounding approaches struggle with scalability and integration, limiting their effectiveness, especially for medium-sized LMs (7B parameters). While larger LMs (70-405B parameters) possess superior hierarchical representations and extensive pre-trained knowledge, they encounter a fundamental scale paradox: despite their advanced abstraction capabilities, they lack efficient mechanisms to leverage experience streams. We propose a scalable weak-to-strong episodic learning framework that effectively transfers episodic behaviors from smaller to larger LMs. This framework integrates Monte Carlo tree search for structured experience collection with a novel distillation method, preserving the inherent LM capabilities while embedding episodic memory. Experiments demonstrate our method surpasses state-of-the-art proprietary LMs by 3.45% across diverse planning and question-answering tasks. Layer-wise probing further indicates significant improvements in task alignment, especially within deeper LM layers, highlighting stable generalization even for previously unseen scenarios with increased planning complexity-conditions where baseline methods degrade markedly.

Related papers

• Transferable Modeling Strategies for Low-Resource LLM Tasks: A Prompt and Alignment-Based Approach [1.3286097954612326]
  This paper addresses the limited transfer and adaptation capabilities of large language models in low-resource language scenarios.<n>It proposes a unified framework that combines a knowledge transfer module with parameter-efficient fine-tuning strategies.<n>It enhances task-specific adaptability while preserving the general capabilities of large language models.
  arXiv  Detail & Related papers  (2025-07-01T09:34:49Z)
• Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models [79.90523648823522]
  Multi-stage continual learning can lead to catastrophic forgetting.<n>This paper evaluates three mitigation strategies-model merging, discounting the LoRA scaling factor, and experience replay.<n>Results show that experience replay is the most effective, with further gains achieved by combining it with other methods.
  arXiv  Detail & Related papers  (2025-05-23T05:50:14Z)
• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive.<n>Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones.<n>We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning [104.27224674122313]
  Fine-tuning MLLM has become a common practice to improve performance on specific downstream tasks. To balance the trade-off between generalization and specialization, we propose measuring the parameter importance for both pre-trained and fine-tuning distributions.
  arXiv  Detail & Related papers  (2024-11-17T01:16:37Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)
• Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers [9.549646359252346]
  Large Language Models (LLMs) possess outstanding capabilities in addressing various natural language processing (NLP) tasks.<n>The sheer size of these models poses challenges in terms of storage, training and inference due to the inclusion of billions of parameters through layer stacking.<n>We show that even with fewer layers, LLMs maintain similar or better performance levels, particularly in prompt-based fine-tuning for text classification tasks.
  arXiv  Detail & Related papers  (2024-02-18T20:47:10Z)
• Language Models Meet World Models: Embodied Experiences Enhance Language Models [48.70726641605047]
  Large language models (LMs) often struggle with simple reasoning and planning in physical environments. We propose a new paradigm of enhancing LMs by finetuning them with world models.
  arXiv  Detail & Related papers  (2023-05-18T00:35:38Z)

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.