arXiv cs.AI· Harsidak Singh Banwait·· 11 小时前AI 评分52
论文提出 SARBLOH：ARC-AGI-3 上感知而非规划主导交互推理
Transforming Integer Grids to Spatial Intuition: Perception, Not Planning, Governs ARC-AGI-3
AI 导读
论文提出 SARBLOH，一个基于开源权重的智能体，核心论点是 ARC-AGI-3 的交互推理由空间感知而非规划能力主导。其零参数 O(HW) 感知引擎在 35 ms 内把每帧转为物体清单，配合二分时序跟踪、区分已证不变量与可供性假设的几何简报以及标注画布，再以代码即动作的运行时让智能体编写算法假设而非底层操作。
正文 · 原文
Abstract:Sample-efficient fluid intelligence requires agents that rapidly form working models of unfamiliar interactive environments. ARC-AGI-3 tests this across uninstructed visual games scored by Relative Human Action Efficiency, which penalizes exploratory waste quadratically. When frontier models read raw integer grids, serialization destroys spatial topology, and they spend hundreds of actions rediscovering basic boundaries and symmetries. We introduce SARBLOH, an open-weight agent built on the premise that spatial perception, not planning capacity, governs interactive reasoning on ARC-AGI-3. A zero-parameter O(HW) perception engine turns each frame, in 35 ms, into an object inventory with bipartite temporal tracking, a geometric briefing that separates proven invariants from affordance hypotheses, and an annotated canvas. Paired with a code-as-action runtime, the agent writes algorithmic hypotheses instead of low-level moves. Across eight presentations, grounded perception raises the rubric score from 3/28 to 25/28 points while cutting token use by 89.4%. On 23 held-out games, geometric invariants generalize with 100% accuracy, while single-frame affordance guesses fall to 6-50%, so active verification probes remain necessary. On the public set, Run A (briefing off) solved 143 of 183 levels in 8.2 hours at 59.4% single-pass efficiency; Run B (briefing on) reached 63.5%. Within the nine-hour budget on one Kaggle RTX PRO 6000 GPU, SARBLOH scored 16.53 on the hidden Kaggle evaluation, 13.7x the first Milestone winner.
| Comments: | 24 pages, 17 figures, 8 tables. Submitted to the ARC Prize 2026 paper track. Code: this https URL |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.06793 [cs.LG] |
| (or arXiv:2611.06793v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06793 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Harsidak Singh Banwait [view email]
[v1]
Wed, 4 Nov 2026 17:11:04 UTC (1,338 KB)
来源：arXiv cs.AI · arxiv.org