CellARC: Measuring Intelligence with Cellular Automata

• URL: http://arxiv.org/abs/2511.07908v1
• Date: Wed, 12 Nov 2025 01:28:14 GMT
• Title: CellARC: Measuring Intelligence with Cellular Automata
• Abstract summary: CellARC is a synthetic benchmark for abstraction and reasoning built from 1D cellular automata.<n>Each episode has five support pairs and one query serialized in 256 multicolor tokens.<n>We release 95k training episodes plus two 1k test splits (interpolation/extrapolation)
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce CellARC, a synthetic benchmark for abstraction and reasoning built from multicolor 1D cellular automata (CA). Each episode has five support pairs and one query serialized in 256 tokens, enabling rapid iteration with small models while exposing a controllable task space with explicit knobs for alphabet size k, radius r, rule family, Langton's lambda, query coverage, and cell entropy. We release 95k training episodes plus two 1k test splits (interpolation/extrapolation) and evaluate symbolic, recurrent, convolutional, transformer, recursive, and LLM baselines. CellARC decouples generalization from anthropomorphic priors, supports unlimited difficulty-controlled sampling, and enables reproducible studies of how quickly models infer new rules under tight budgets. Our strongest small-model baseline (a 10M-parameter vanilla transformer) outperforms recent recursive models (TRM, HRM), reaching 58.0%/32.4% per-token accuracy on the interpolation/extrapolation splits, while a large closed model (GPT-5 High) attains 62.3%/48.1% on subsets of 100 test tasks. An ensemble that chooses per episode between the Transformer and the best symbolic baseline reaches 65.4%/35.5%, highlighting neuro-symbolic complementarity. Leaderboard: https://cellarc.mireklzicar.com

Related papers

• A Dominant Diffuse Phase in the Sparse Autoencoder Phase Diagram [0.0]
  Sparse autoencoders (SAEs) are increasingly used to recover interpretable features from neural-network activations.<n>The MAIS-O43 open problem proposes a controlled experiment to characterize when recovery of a true synthetic dictionary gives way to feature merging.
  arXiv  Detail & Related papers  (2026-09-09T15:13:42Z)
• AgentWeave: Routing Before Reasoning for Efficient Function Calling in Tool-Rich Language Models [0.0]
  We introduce AgentWeave, a deterministic pre-inference routing layer that constructs a bounded model-visible action space.<n>Relative to all-tools exposure, AgentWeave presents 70.18% fewer tools, uses 61.70% fewer input tokens, and exhibits 50.95% lower mean local-model latency.
  arXiv  Detail & Related papers  (2026-08-24T10:38:08Z)
• Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model [0.0]
  We run a controlled ablation study of a full agentic RAG pipeline evaluated on 5,000 questions.<n>We find that fixed hybrid retrieval via reciprocal rank fusion consistently outperforms rule-based adaptive routing.
  arXiv  Detail & Related papers  (2026-06-19T15:50:35Z)
• Closed-Form Spectral Regularization for Multi-Task Model Merging [96.82449201305234]
  Model merging combines several independently fine-tuned experts into a single multi-task model without any training data.<n>State-of-the-art merging methods formulate merging as a layer-wise interference problem.<n>We propose SWUDI, a closed-form method that combines a soft exponential filter, which matches the gradient-flow trajectory of iterative descent.
  arXiv  Detail & Related papers  (2026-06-05T14:00:47Z)
• Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning [51.88950852117154]
  Chunk-Level Guided Generation is a training-free alternative that uses an off-the-shelf large language model as a process scorer.<n>We show that scoring variable-length reasoning steps with large-model likelihoods is unreliable due to a systematic length bias.<n>Chunk-Level Guided Generation produces substantially shorter reasoning traces than PRM guided search.
  arXiv  Detail & Related papers  (2026-06-01T04:43:36Z)
• DAStatFormer: A Hybrid Multibranch Transformer with Statistical Feature Integration for DAS-Based Pattern Recognitions [0.19573380763700718]
  DAStatFormer is a hybrid multibranch Transformer that combines compact multidomain statistical features with Gated Transformer Networks.<n>It achieves up to 99.4% accuracy and near-perfect real-world performance.<n>These results demonstrate its suitability for Distributed, real-time DAS-based monitoring.
  arXiv  Detail & Related papers  (2026-05-22T13:58:37Z)
• dVoting: Fast Voting for dLLMs [71.572316901001]
  Diffusion Large Language Models (dLLMs) represent a new paradigm beyond autoregressive modeling.<n>dLLMs can generate tokens at arbitrary positions in parallel, endowing them with significant potential for parallel test-time scaling.<n>We introduce dVoting, a fast voting technique that boosts reasoning capability without training, with only an acceptable extra computational overhead.
  arXiv  Detail & Related papers  (2026-02-12T16:35:05Z)
• Tiny Recursive Models on ARC-AGI-1: Inductive Biases, Identity Conditioning, and Test-Time Compute [0.0]
  We empirically analyze the ARC Prize TRM checkpoint on ARC-AGI-1.<n>We show that test-time augmentation and majority-vote ensembling account for a substantial fraction of reported performance.<n>We also compare TRM with a naive QLoRA fine-tune of Llama 3 8B on canonical ARC-AGI-1.
  arXiv  Detail & Related papers  (2025-12-04T06:20:44Z)
• PanFoMa: A Lightweight Foundation Model and Benchmark for Pan-Cancer [54.958921946378304]
  We introduce PanFoMa, a lightweight hybrid neural network that combines the strengths of Transformers and state-space models.<n>PanFoMa consists of a front-end local-context encoder with shared self-attention layers to capture complex, order-independent gene interactions.<n>We also construct a large-scale pan-cancer single-cell benchmark, PanFoMaBench, containing over 3.5 million high-quality cells.
  arXiv  Detail & Related papers  (2025-12-02T08:31:31Z)
• Diffusion Language Models are Super Data Learners [61.721441061210896]
  When unique data is limited, diffusion language models (DLMs) consistently surpass autoregressive (AR) models by training for more epochs.<n>We attribute the gains to three compounding factors: (1) any-order modeling, (2) super-dense compute from iterative bidirectional denoising, and (3) built-in Monte Carlo augmentation.
  arXiv  Detail & Related papers  (2025-11-05T08:17:42Z)
• Pulsar Detection with Deep Learning [0.0]
  This thesis builds a deep learning pipeline for radio pulsar candidate selection that fuses array-derived features with image diagnostics.<n>From approximately 500 GB of GMRT data, raw voltages are converted to filterbanks, then de-dispersed and folded across trial dispersion measures.<n>Each candidate yields four diagnostics--summed profile, time vs. phase, subbands vs. phase, and DM curve--represented as arrays and images.
  arXiv  Detail & Related papers  (2025-10-26T05:12:45Z)
• Ensemble Threshold Calibration for Stable Sensitivity Control [0.0]
  We present an end-to-end framework that achieves exact recall with sub-percent variance over tens of millions of geometry pairs.<n>Our approach consistently hits a recall target within a small error, decreases redundant verifications relative to other calibrations, and runs end-to-end on a single TPU v3 core.
  arXiv  Detail & Related papers  (2025-10-02T15:22:28Z)
• Generalized Parallel Scaling with Interdependent Generations [58.43994876504917]
  We propose Bridge to generate interdependent responses in parallel.<n>With only a small amount of new parameters, Bridge improves the relative mean accuracy gains from reinforcement learning.
  arXiv  Detail & Related papers  (2025-10-01T17:33:35Z)
• Automated Knowledge Graph Construction using Large Language Models and Sentence Complexity Modelling [0.39089069256361736]
  We introduce CoDe-KG, an end-to-end pipeline for extracting sentence-level knowledge graphs.<n>We contribute a dataset of over 150,000 knowledge triples, which is open source.<n>We show that hybrid chain-of-thought and few-shot prompting yields up to 99.8% exact-match accuracy on sentence simplification.
  arXiv  Detail & Related papers  (2025-09-22T00:01:50Z)
• Prototype Training with Dual Pseudo-Inverse and Optimized Hidden Activations [0.14504054468850663]
  Proto-PINV+H is a fast training paradigm that combines closed-form weight computation with optimisation of a small set of synthetic inputs.<n>On MNIST (60k train, 10k test) and Fashion-MNIST (60k train, 10k test), our method reaches 97.8% and 89.3% test accuracy on the official 10k test sets, respectively.
  arXiv  Detail & Related papers  (2025-08-13T13:13:32Z)
• Advancing Tabular Stroke Modelling Through a Novel Hybrid Architecture and Feature-Selection Synergy [0.9999629695552196]
  The present work develops and validates a data-driven and interpretable machine-learning framework designed to predict strokes.<n>Ten routinely gathered demographic, lifestyle, and clinical variables were sourced from a public cohort of 4,981 records.<n>The proposed model achieved an accuracy rate of 97.2% and an F1-score of 97.15%, indicating a significant enhancement compared to the leading individual model.
  arXiv  Detail & Related papers  (2025-05-18T21:46:45Z)
• ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis [50.020850767257095]
  We propose ProofAug, a procedure that equips LLMs with automation methods at various granularities.<n>Our method is validated on the miniF2F benchmark using the open-source deep-math-7b-base model and the Isabelle proof assistant.<n>We also implement a Lean 4 version of ProofAug that can improve the pass@1 performance of Kimina-Prover-seek-Distill-1.5B from 44.3% to 50.4%.
  arXiv  Detail & Related papers  (2025-01-30T12:37:06Z)
• Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition [62.83832841523525]
  We propose a fast and accurate parallel transformer, termed Paraformer. It accurately predicts the number of output tokens and extract hidden variables. It can attain comparable performance to the state-of-the-art AR transformer, with more than 10x speedup.
  arXiv  Detail & Related papers  (2022-06-16T17:24:14Z)
• Squeezeformer: An Efficient Transformer for Automatic Speech Recognition [99.349598600887]
  Conformer is the de facto backbone model for various downstream speech tasks based on its hybrid attention-convolution architecture. We propose the Squeezeformer model, which consistently outperforms the state-of-the-art ASR models under the same training schemes.
  arXiv  Detail & Related papers  (2022-06-02T06:06:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.