首页 > AI前沿 > Exploring Weight-Space Programming: Capabilities, Generalization, and Limitations

Exploring Weight-Space Programming: Capabilities, Generalization, and Limitations

arXiv机器学习 2026-11-06 20:22 116 阅读 查看原文

Weight-Space Programming (WSP) enables reasoning agents to directly inspect and modify neural network parameters, offering an alternative to gradient-based model adaptation. However, its capabilities, cross-task generalization, and practical limitations remain insufficiently understood. We systematically investigate WSP through 16 editing trajectories across seven benchmarks and two model scales (Qwen3.5-0.8B and Qwen3.5-9B). Our findings reveal three key insights.

First, WSP can achieve substantial performance gains through highly localized interventions. On full held-out evaluations, accuracy improves by up to 29.45,