Experience Scaling: Post-Deployment Evolution For Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908555138826240 |
|---|---|
| author | Yin, Xingkun Huang, Kaibin Kim, Dong In Du, Hongyang |
| author_facet | Yin, Xingkun Huang, Kaibin Kim, Dong In Du, Hongyang |
| contents | Scaling model size, training data, and compute power have driven advances in large language models (LLMs), but these approaches are reaching saturation as human-generated text is exhausted and further gains diminish. We propose experience scaling, a framework for continuous post-deployment evolution for LLMs through autonomous interaction with the environment and collaborative sharing of accumulated experience. The framework captures raw interactions, distills them into compact, reusable knowledge, and periodically refines stored content to preserve relevance and efficiency. We validate the framework in simulated real-world scenarios involving generalization to previously unseen but related tasks, repetitive queries, and over-saturated knowledge stores. Across all settings, experience scaling improves accuracy, sustains performance over time, and maintains gains when applied to novel situations. These results demonstrate that structured post-deployment learning can extend LLM capabilities beyond the limits of static human-generated data, offering a scalable path for continued intelligence progress. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_18771 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Experience Scaling: Post-Deployment Evolution For Large Language Models Yin, Xingkun Huang, Kaibin Kim, Dong In Du, Hongyang Artificial Intelligence Scaling model size, training data, and compute power have driven advances in large language models (LLMs), but these approaches are reaching saturation as human-generated text is exhausted and further gains diminish. We propose experience scaling, a framework for continuous post-deployment evolution for LLMs through autonomous interaction with the environment and collaborative sharing of accumulated experience. The framework captures raw interactions, distills them into compact, reusable knowledge, and periodically refines stored content to preserve relevance and efficiency. We validate the framework in simulated real-world scenarios involving generalization to previously unseen but related tasks, repetitive queries, and over-saturated knowledge stores. Across all settings, experience scaling improves accuracy, sustains performance over time, and maintains gains when applied to novel situations. These results demonstrate that structured post-deployment learning can extend LLM capabilities beyond the limits of static human-generated data, offering a scalable path for continued intelligence progress. |
| title | Experience Scaling: Post-Deployment Evolution For Large Language Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.18771 |