Papers/2611.21885
🧪 Test?View on arXiv

Language Models Can Rewrite Their Own Weights

Unknown

self-improvementmodel optimizationlanguage models
2611.21885
Builder Relevance
80%
15h ago

Abstract

This paper explores the concept of self-rewriting in language models, demonstrating that a model can improve its own weights without gradients or additional training.

Reality Card

Core Claim

A 27B language model can diagnose its failures and rewrite its own weights to improve accuracy by 6.6 points on unseen problems.

Method / Result

The model's self-editing process resulted in a consistent accuracy increase over eight sessions.

Limitations

The findings may be limited to larger models, as smaller models did not exhibit the same self-editing capabilities.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers