Imagen de Portada

A Theory for Length Generalization in Learning to Reason

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiao, Changnan, Liu, Bing
Formato:	Preprint
Publicado:	2024
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Open-World Continual Learning: Unifying Novelty Detection and Continual Learning
por: Kim, Gyuhak, et al.
Publicado: (2023)

PhySense: Principle-Based Physics Reasoning Benchmarking for Large Language Models
por: Xu, Yinggan, et al.
Publicado: (2025)

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control
por: He, Xingyang, et al.
Publicado: (2025)

On the Step Length Confounding in LLM Reasoning Data Selection
por: Wang, Bing, et al.
Publicado: (2026)

Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization
por: Huang, Yu, et al.
Publicado: (2025)

Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance
por: Xiong, Kai, et al.
Publicado: (2024)

Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
por: Liu, Wei, et al.
Publicado: (2025)

More Thinking, More Bias: Length-Driven Position Bias in Reasoning Models
por: Wang, Xiao
Publicado: (2026)

AnaCP: Toward Upper-Bound Continual Learning via Analytic Contrastive Projection
por: Momeni, Saleh, et al.
Publicado: (2025)

An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint
por: Sun, Yi, et al.
Publicado: (2025)

Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
por: Li, Xintong, et al.
Publicado: (2026)

ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning
por: Yi, Jingyang, et al.
Publicado: (2025)

DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning
por: He, Yang, et al.
Publicado: (2026)

Trace Length is a Simple Uncertainty Signal in Reasoning Models
por: Devic, Siddartha, et al.
Publicado: (2025)

LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization
por: Wu, Xingyu, et al.
Publicado: (2025)

Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning
por: Xiang, Violet, et al.
Publicado: (2025)

Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective
por: Chen, Yang, et al.
Publicado: (2024)

Learning Dynamic Belief Graphs for Theory-of-mind Reasoning
por: Chen, Ruxiao, et al.
Publicado: (2026)

Optimizing Length Compression in Large Reasoning Models
por: Cheng, Zhengxiang, et al.
Publicado: (2025)

Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length?
por: Lee, Celine, et al.
Publicado: (2025)

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models
por: Wu, Wei, et al.
Publicado: (2026)

MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind
por: Zhang, Zheng, et al.
Publicado: (2025)

The Impact of Reasoning Step Length on Large Language Models
por: Jin, Mingyu, et al.
Publicado: (2024)

Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model
por: Li, Yanhao, et al.
Publicado: (2025)

GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning
por: Han, Xiao, et al.
Publicado: (2026)

Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models
por: Zhang, Qiyuan, et al.
Publicado: (2026)

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
por: Cho, Hanseul, et al.
Publicado: (2024)

Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Traces
por: Tong, William L., et al.
Publicado: (2026)

GR-Ben: A General Reasoning Benchmark for Evaluating Process Reward Models
por: Sun, Zhouhao, et al.
Publicado: (2026)

Monitor-Generate-Verify (MGV): Formalising Metacognitive Theory for Language Model Reasoning
por: Oh, Nick, et al.
Publicado: (2025)

Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost
por: Nayab, Sania, et al.
Publicado: (2024)

First Try Matters: Revisiting the Role of Reflection in Reasoning Models
por: Kang, Liwei, et al.
Publicado: (2025)

Bidirectional Curriculum Generation: A Multi-Agent Framework for Data-Efficient Mathematical Reasoning
por: Hu, Boren, et al.
Publicado: (2026)

ReasonGRM: Enhancing Generative Reward Models through Large Reasoning Models
por: Chen, Bin, et al.
Publicado: (2025)

InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models
por: Yan, Yuchen, et al.
Publicado: (2025)

A Simple Generative Model of Logical Reasoning and Statistical Learning
por: Kido, Hiroyuki
Publicado: (2023)

Learning Logical Rules using Minimum Message Length
por: Sharma, Ruben, et al.
Publicado: (2025)

Protein-Conditioned Multi-Objective Reinforcement Learning for Full-Length mRNA Design
por: Shao, Zixi, et al.
Publicado: (2026)

On Vanishing Variance in Transformer Length Generalization
por: Li, Ruining, et al.
Publicado: (2025)

Mamba Modulation: On the Length Generalization of Mamba
por: Lu, Peng, et al.
Publicado: (2025)