改AI的1023个参数，数学涨了近30分
不用重新训练，直接伸手进模型内部改几个参数，就能让它数学成绩涨近30分——而且只动了1023个。研究者让一个「会推理的智能体」自己去翻模型的权重、挑地方下手，在7个测试集、两种模型规模上跑了16条修改路径。结果很分裂：有的路径在MATH-500上把准确率拉高29.45个百分点，GPQA Diamond、IFEval、SciBench也分别涨了4.42、36.72、17.11；而且改数学的那份模型，没再动其他地方，顺手把GPQA、IFEval、SciBench也带高了3.03、12.18、20.10分，但写代码的SciCode纹丝不动。另一面是，16条路径里有6条在改完之后验证不出可靠提升，干脆把权重原样退了回去。它不是你明天能用上的东西：这更像在证明「模型内部有一小撮开关，拨对了收益极大」，但怎么找到那撮开关、怎么确认没拨坏，目前还是碰运气。
📄 原文摘要(英文)
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, 4.42, 36.72, and 17.11 percentage points on MATH-500, GPQA Diamond, IFEval, and SciBench, respectively. Notably, modifying only 1,023 parameters yields a 29.45-point improvement. Second, WSP exhibits promising but uneven cross-task generalization. A Math-edited checkpoint improves GPQA Diamond, IFEval, and SciBench by 3.03, 12.18, and 20.10 points, respectively, without further editing, while leaving SciCode performance unchanged. Third, effective editing remains challenging and inconsistent. Outcomes vary substantially across trajectories, and six of the 16 trajectories retain the original weights when candidate improvements cannot be reliably validated. Together, these results highlight WSP's potential for highly localized model adaptation while revealing important challenges in intervention discovery, reliability, and cross-task transfer. Homepage: https://wsp-scope.github.io/ GitHub: https://github.com/WSP-Scope/WSP-Scope-Project