Cover Image

A transformer architecture alteration to incentivise externalised reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pavlova, Elizabeth, Koroliuk, Mariia, Viswanathan, Karthik, Tice, Cameron, Young, Edward James, Radmard, Puria
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Chain-of-thought obfuscation learned from output supervision can generalise to unseen tasks
by: Hadida, Nathaniel Mitrani, et al.
Published: (2026)

Diagnosing Pathological Chain-of-Thought in Reasoning Models
by: Liu, Manqing, et al.
Published: (2026)

Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment
by: Tice, Cameron, et al.
Published: (2026)

Setting up for failure: automatic discovery of the neural mechanisms of cognitive errors
by: Radmard, Puria, et al.
Published: (2025)

Large language models can learn and generalize steganographic chain-of-thought under process supervision
by: Skaf, Joey, et al.
Published: (2025)

Small transformer architectures for task switching
by: Gros, Claudius
Published: (2025)

When can transformers reason with abstract symbols?
by: Boix-Adsera, Enric, et al.
Published: (2023)

A flexible Bayesian non-parametric mixture model reveals multiple dependencies of swap errors in visual working memory
by: Radmard, Puria, et al.
Published: (2025)

Can Continuous-Time Diffusion Models Generate and Solve Globally Constrained Discrete Problems? A Study on Sudoku
by: Drozdova, Mariia
Published: (2026)

The cognitive companion: a lightweight parallel monitoring architecture for detecting and recovering from reasoning degradation in LLM agents
by: Khan, Rafflesia, et al.
Published: (2026)

Financial time series augmentation using transformer based GAN architecture
by: Podobiński, Andrzej, et al.
Published: (2026)

PACAD-Based Structural Reasoning for AGI: From Probabilistic Pattern-Matching to Verifiable Canonical Architectures – paper 1, version 2
by: Brown, Cameron
Published: (2026)

chat log: Goolge Search AI - Anthropic Claude benchmarks and model release statistics in comparison to PACAD-based training estimates
by: Brown, Cameron
Published: (2026)

Association-sensory spatiotemporal hierarchy and functional gradient-regularised recurrent neural network with implications for schizophrenia
by: Abulikemu, Subati, et al.
Published: (2025)

PACAD-Enhanced Opus: Specialized Benchmark Performance Estimates – 2-3 Week Cycle (14-21 Days, Median ~17 Days)
by: Brown, Cameron
Published: (2026)

Diffusion models under low-noise regime
by: Pavlova, Elizabeth, et al.
Published: (2025)

PACAD-Based Structural Reasoning for AGI: From Probabilistic Pattern-Matching to Verifiable Canonical Architectures – paper 1, version 1
by: Brown, Cameron
Published: (2026)

AEC — Axiomatic Engine Cycle v0.1 — Initial Specification Draft
by: Brown, Cameron
Published: (2026)

Demonstrating specification gaming in reasoning models
by: Bondarenko, Alexander, et al.
Published: (2025)

Physical models realizing the transformer architecture of large language models
by: Chen, Zeqian
Published: (2025)

AstroM$^3$: A self-supervised multimodal model for astronomy
by: Rizhko, Mariia, et al.
Published: (2024)

Causal reasoning in difference graphs
by: Assaad, Charles K.
Published: (2024)

Mathematical reasoning and the computer
by: Buzzard, Kevin
Published: (2025)

Learning to reason about rare diseases through retrieval-augmented agents
by: Kim, Ha Young, et al.
Published: (2025)

Harnessing the power of LLMs for normative reasoning in MASs
by: Savarimuthu, Bastin Tony Roy, et al.
Published: (2024)

Estimating Visual Attribute Effects in Advertising from Observational Data: A Deepfake-Informed Double Machine Learning Approach
by: Liu, Yizhi, et al.
Published: (2026)

CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks
by: Yu, Ping, et al.
Published: (2025)

Improving reasoning at inference time via uncertainty minimisation
by: Legrand, Nicolas, et al.
Published: (2026)

Logos: An evolvable reasoning engine for rational molecular design
by: Wen, Haibin, et al.
Published: (2026)

Effects of structure on reasoning in instance-level Self-Discover
by: Gunasekara, Sachith, et al.
Published: (2025)

Underwater object detection in sonar imagery with detection transformer and Zero-shot neural architecture search
by: Gu, XiaoTong, et al.
Published: (2025)

Are complicated loss functions necessary for teaching LLMs to reason?
by: Carrino, Gabriele, et al.
Published: (2026)

DecompSR: A dataset for decomposed analyses of compositional multihop spatial reasoning
by: McPheat, Lachlan, et al.
Published: (2025)

Understanding Goal Generalisation in Sequential Reinforcement Learning
by: Brown, Jason Ross, et al.
Published: (2026)

Solomonoff-Inspired Hypothesis Ranking with LLMs for Prediction Under Uncertainty
by: Barber, Josh, et al.
Published: (2025)

Limited Reasoning Space: The cage of long-horizon reasoning in LLMs
by: Li, Zhenyu, et al.
Published: (2026)

TIM-PRM: Verifying multimodal reasoning with Tool-Integrated PRM
by: Kuang, Peng, et al.
Published: (2025)

Unsupervised decoding of encoded reasoning using language model interpretability
by: Fang, Ching, et al.
Published: (2025)

Self-rewarding correction for mathematical reasoning
by: Xiong, Wei, et al.
Published: (2025)

Phi-4-reasoning Technical Report
by: Abdin, Marah, et al.
Published: (2025)