arXiv cs.AI· Syed Affan Daimi·· 23 小时前AI 评分31
Proximal Targets:让循环精炼模型学会处理多解问题
Proximal Targets: Training Looped Refiners on Problems with Many Correct Answers
AI 导读
针对 HRM、TRM 等循环精炼模型在多解问题上因深度监督指向单一存储答案而产生损失下限的问题,研究者提出 proximal target:每一轮都朝距其自身输入最近的正确答案训练。
正文 · 原文
Abstract:Looped refiners such as HRM and TRM apply one small network repeatedly to a draft answer, and deep supervision trains every pass toward one stored answer per puzzle. We prove that when a puzzle has many correct answers this target sets a loss floor that no model capacity removes, and that the loss-minimising pass blends the answers into an invalid grid. We propose the proximal target: train each pass toward the correct answer nearest to its own input, found by scanning a list of answers, by a search solver started at the draft, or within a band of quality set by a knob; correct answers become fixed points, and a pass only has to make fewer errors than its input has for the loop to converge, which its training loss bounds. With the same 1.7M-parameter network and 5 seeds, the proximal target solves 98.8% of Sudoku puzzles with 2-64 answers (standard target: 2.5%), 93.8% of sparse puzzles with more than 10,000 answers without any list of answers (0.0%), and 90.9% of 200-node 3-colourings after training on graphs of at most 50 nodes (36.9%), and different random starts end at different answers. Against GRAM, a stochastic-latent reasoner, a single run is correct far more often (98.8% vs. 57.7%) and twenty runs find more of the answers (53.6% vs. 37.4%), while GRAM is slightly ahead on its own 10-node colouring benchmark; in Scrabble the knob becomes a calibrated strength dial.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.22737 [cs.AI] |
| (or arXiv:2611.22737v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22737 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Syed Daimi Affan [view email]
[v1]
Tue, 17 Nov 2026 13:07:46 UTC (320 KB)
来源:arXiv cs.AI · arxiv.org