arXiv AI August 11, 2026 By Hiroyuki Chuma, Kanji Otsuk, Yoichi Sato

How to Build Marcus's Algebraic Mind: Algebro-Deterministic Substrate over Galois Fields

arXiv:2605. 21379v3 Announce Type: replace-cross Abstract: In The Algebraic Mind (2001), Marcus held that any adequate cognitive architecture needs operations over variables, recursively structured representations, and an individual/kind distinction, and that multilayer perceptrons support none of them; he left a register-and-treelet implementation as a conjecture.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

llms

arXiv Machine Learning

Jul 1

Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors

arXiv:2606. 31845v1 Announce Type: cross Abstract: A transformer's feed-forward (FFN) sublayer materializes the distinctions attention gathers, yet gives no account of what it computes.

By Mark Oskin

llms

arXiv Machine Learning

Jun 2

Task Structure Reverses Layerwise State Encoding in Sequence Models

arXiv:2606. 00926v1 Announce Type: new Abstract: Mechanistic studies of sequence models often treat layerwise state encodings as architectural traits: recurrent models concentrate readable state, attention-based models distribute it.

By Yuhang Jiang

llms fine-tuning benchmarks

arXiv AI

Jun 24

Repeated Shared Access Enables Grokking, but Edit Propagation Depends on an Addressable Memory

arXiv:2606. 20737v2 Announce Type: replace Abstract: We study factual edit propagation in a controlled synthetic knowledge-graph QA setting using a 2x2 grid that crosses loop recurrence with shared-memory access: a dense transformer (Dense), a looped transformer (Loop), a dense backbone with shared memory (Dense+Mem), and a looped backbone with shared memory (loop-memory coupling, LMC).

By Yanan Niu

llms

arXiv Machine Learning

Jul 10

Computation, Condensation, and the Incompleteness Between Them: A Coupled Foundation of Intelligence

arXiv:2303. 04203v4 Announce Type: replace Abstract: The theory of computation was built to answer Turing's question: what is effectively calculable by an unbounded, immortal, disembodied agent following rules?

By Xin Li

agents

arXiv AI

Jun 26

Sutra: Tensor-Op RNNs as a Compilation Target for Vector Symbolic Architectures

arXiv:2605. 20919v3 Announce Type: replace-cross Abstract: Sutra is a typed, purely functional programming language whose compiled forward pass is a PyTorch neural network.

By Emma Leonhart

llms rag

arXiv AI

Aug 11

ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems

arXiv:2604. 23878v3 Announce Type: replace Abstract: ZenBrain is a seven-layer, neuroscience-derived memory architecture for LLM agents that unifies fifteen mechanisms - from Two-Factor synaptic consolidation to a Simulation-Selection sleep loop - under a single MemoryCoordinator: nine foundational algorithms plus six Predictive Memory Architecture components.

By Alexander Bering

llms agents benchmarks

Related stories

Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors

Task Structure Reverses Layerwise State Encoding in Sequence Models

Repeated Shared Access Enables Grokking, but Edit Propagation Depends on an Addressable Memory

Computation, Condensation, and the Incompleteness Between Them: A Coupled Foundation of Intelligence

Sutra: Tensor-Op RNNs as a Compilation Target for Vector Symbolic Architectures

ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems