arXiv cs.AI· Henrique Oliveira·· 10 小时前AI 评分34
F3-AGI v4.0：面向样本高效抽象推理的生物能量门控主动推理、元可塑性预处理与残差程序合成
F3-AGI v4.0: Bioenergetically-Gated Active Inference, Metaplastic Preconditioning, and Residual Program Synthesis for Sample-Efficient Abstract Reasoning
AI 导读
F3-AGI v4.0 在 ARC-AGI-1 公开评测集上以离线 CPU、零 LLM 调用解出 57/400 个任务（pass@2 14.25%），平均延迟 1.62 秒/任务。
正文 · 原文
Abstract:Few-shot abstract reasoning on ARC-AGI requires inducing algorithmic transformations from 2 to 5 demonstration pairs without task-specific pretraining. Because few-shot demonstrations under-constrain the hypothesis space, program synthesis suffers from the Rashomon effect (predictive multiplicity): heuristic search finds spurious programs with low training error that fail on test inputs, while unconstrained library growth degrades latency. We introduce F3-AGI v4.0, a CPU-native neuro-symbolic and active inference architecture comprising three mechanisms: (1) F3-Metabolic-Optim, combining mistake-gated plasticity, Fisher-EMA preconditioning, and virtual ATP gating; (2) Adaptive Complexity-Guided Program Synthesis (AACR) with a Cycle-3 ResidualPatchSynthesizer and smallest-pair early rejection; and (3) a 512D L2-normalized random projection driving Expected Free Energy (EFE) exploration with dead-signature pruning. Across three empirical studies: (i) on a synthetic 5-task class-incremental stream without replay, F3-Metabolic-Optim achieves 91.67% final accuracy with 9.17% forgetting, skipping 93.47% of updates, cutting L1 plasticity cost by 65.7%, and running 2.19x faster than EWC; (ii) on the 400-task ARC-AGI-1 public evaluation set (offline CPU, zero LLM calls), F3-AGI v4.0 solves 57/400 tasks (14.25% pass@2; 56/400 pass@1) with a mean latency of 1.62 s/task, decomposed into 19/50 (38.00%, 1.19 s/task, a 42.5x paired speedup over Horizon 2) on the 50-task calibration slice and 38/350 (10.86%) on the 350 strictly uninspected hold-out tasks (with 7 autonomous Cycle-3 patch solutions); and (iii) in a local 5-game (15-level) ARC-AGI-3-inspired interactive suite, our agent completes 15/15 levels with 89.44% level-weighted RHAE (90.72% unweighted).
| Comments: | 14 pages, 5 figures. Code and reproducibility materials: this https URL |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.13325 [cs.AI] |
| (or arXiv:2611.13325v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13325 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Henrique Oliveira [view email]
[v1]
Mon, 9 Nov 2026 22:47:43 UTC (163 KB)
来源：arXiv cs.AI · arxiv.org