Imagen de Portada

How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Abbe, Emmanuel, Bengio, Samy, Lotfi, Aryo, Sandon, Colin, Saremi, Omid
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning
por: Mahrooghi, Ilia, et al.
Publicado: (2026)

Generalization on the Unseen, Logic Reasoning and Degree Curriculum
por: Abbe, Emmanuel, et al.
Publicado: (2023)

RL for Reasoning by Adaptively Revealing Rationales
por: Amani, Mohammad Hossein, et al.
Publicado: (2025)

Chain-of-Sketch: Enabling Global Visual Reasoning
por: Lotfi, Aryo, et al.
Publicado: (2024)

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

To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models
por: Malach, Eran, et al.
Publicado: (2025)

AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking
por: Gao, Silin, et al.
Publicado: (2025)

Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection
por: Chegini, Atoosa, et al.
Publicado: (2025)

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
por: Mirzadeh, Iman, et al.
Publicado: (2024)

Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control
por: Jiralerspong, Thomas, et al.
Publicado: (2025)

$k$-server-bench: Automating Potential Discovery for the $k$-Server Conjecture
por: Brilliantov, Kirill, et al.
Publicado: (2026)

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
por: Shojaee, Parshin, et al.
Publicado: (2025)

Neural Network Parameter-optimization of Gaussian pmDAGs
por: Saremi, Mehrzad
Publicado: (2023)

How Far Can Fairness Constraints Help Recover From Biased Data?
por: Sharma, Mohit, et al.
Publicado: (2023)

Boolformer: Symbolic Regression of Logic Functions with Transformers
por: d'Ascoli, Stéphane, et al.
Publicado: (2023)

GFlowNet Foundations
por: Bengio, Yoshua, et al.
Publicado: (2021)

GFlowNet Pretraining with Inexpensive Rewards
por: Pandey, Mohit, et al.
Publicado: (2024)

Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?
por: Zheng, Haizhong, et al.
Publicado: (2025)

LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs?
por: Ziomek, Juliusz, et al.
Publicado: (2026)

What Structural Inductive Bias Helps Transformers Reason Over Knowledge Graphs? A Study with Tabula RASA
por: Petersen, Jonas, et al.
Publicado: (2026)

Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structures
por: He, Yu, et al.
Publicado: (2025)

How Far Are We from True Unlearnability?
por: Ye, Kai, et al.
Publicado: (2025)

Temporal Inductive Path Neural Network for Temporal Knowledge Graph Reasoning
por: Dong, Hao, et al.
Publicado: (2023)

ULLER: A Unified Language for Learning and Reasoning
por: van Krieken, Emile, et al.
Publicado: (2024)

A Comprehensive Study of Supervised Machine Learning Models for Zero-Day Attack Detection: Analyzing Performance on Imbalanced Data
por: Lotfi, Zahra, et al.
Publicado: (2025)

On the Inductive Bias of Stacking Towards Improving Reasoning
por: Saunshi, Nikunj, et al.
Publicado: (2024)

Hypothesis Search: Inductive Reasoning with Language Models
por: Wang, Ruocheng, et al.
Publicado: (2023)

Action abstractions for amortized sampling
por: Boussif, Oussama, et al.
Publicado: (2024)

The Kinetics of Reasoning: How Chain-of-Thought Shapes Learning in Transformers?
por: Pengmei, Zihan, et al.
Publicado: (2025)

LEAD: Breaking the No-Recovery Bottleneck in Long-Horizon Reasoning
por: Pushkin, Denys, et al.
Publicado: (2026)

Mars: Situated Inductive Reasoning in an Open-World Environment
por: Tang, Xiaojuan, et al.
Publicado: (2024)

The Role of Deductive and Inductive Reasoning in Large Language Models
por: Cai, Chengkun, et al.
Publicado: (2024)

Expert-Guided LLM Reasoning for Battery Discovery: From AI-Driven Hypothesis to Synthesis and Characterization
por: Liu, Shengchao, et al.
Publicado: (2025)

CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning
por: Leang, Joshua Ong Jun, et al.
Publicado: (2024)

PatchTrAD: A Patch-Based Transformer focusing on Patch-Wise Reconstruction Error for Time Series Anomaly Detection
por: Vilhes, Samy-Melwan, et al.
Publicado: (2025)

Vanishing Gradients in Reinforcement Finetuning of Language Models
por: Razin, Noam, et al.
Publicado: (2023)

Inductive Moment Matching
por: Zhou, Linqi, et al.
Publicado: (2025)

Agent Factories for High Level Synthesis: How Far Can General-Purpose Coding Agents Go in Hardware Optimization?
por: Bhandwaldar, Abhishek, et al.
Publicado: (2026)

Can Post-Training Transform LLMs into Causal Reasoners?
por: Chen, Junqi, et al.
Publicado: (2026)

Temporal Inductive Logic Reasoning over Hypergraphs
por: Yang, Yuan, et al.
Publicado: (2022)