Imagen de Portada

Emergent Search and Backtracking in Latent Reasoning Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cui, Jasmine, Ye, Charles
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ASTRO: Teaching Language Models to Reason by Reflecting and Backtracking In-Context
por: Kim, Joongwon, et al.
Publicado: (2025)

Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation
por: Wang, Bing, et al.
Publicado: (2026)

Backtracking for Safety
por: Sel, Bilgehan, et al.
Publicado: (2025)

Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models
por: Yang, Xiao-Wen, et al.
Publicado: (2025)

BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism
por: Wu, Qinzhuo, et al.
Publicado: (2025)

Prompt Injection as Role Confusion
por: Ye, Charles, et al.
Publicado: (2026)

Correction with Backtracking Reduces Hallucination in Summarization
por: Liu, Zhenzhen, et al.
Publicado: (2023)

Steering When Necessary: Flexible Steering Large Language Models with Backtracking
por: Cheng, Zifeng, et al.
Publicado: (2025)

Reinforcement Learning with Backtracking Feedback
por: Sel, Bilgehan, et al.
Publicado: (2026)

Backtracking Improves Generation Safety
por: Zhang, Yiming, et al.
Publicado: (2024)

Layer-Order Inversion: Rethinking Latent Multi-Hop Reasoning in Large Language Models
por: Liu, Xukai, et al.
Publicado: (2026)

Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models
por: Yang, Yukang, et al.
Publicado: (2025)

Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization
por: Ye, Wengao, et al.
Publicado: (2025)

OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework
por: Chen, Ben, et al.
Publicado: (2026)

Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
por: Wang, Haozhe, et al.
Publicado: (2025)

Unlocking the Working Memory of Large Language Models for Latent Reasoning
por: Aichberger, Lukas, et al.
Publicado: (2026)

Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
por: Chua, James, et al.
Publicado: (2025)

Emergent Representations of Program Semantics in Language Models Trained on Programs
por: Jin, Charles, et al.
Publicado: (2023)

Latent Reasoning with Supervised Thinking States
por: Amos, Ido, et al.
Publicado: (2026)

Latent Chain-of-Thought for Visual Reasoning
por: Sun, Guohao, et al.
Publicado: (2025)

SeLaR: Selective Latent Reasoning in Large Language Models
por: Fu, Renyu, et al.
Publicado: (2026)

Efficient Post-Training Refinement of Latent Reasoning in Large Language Models
por: Wang, Xinyuan, et al.
Publicado: (2025)

LaRS: Latent Reasoning Skills for Chain-of-Thought Reasoning
por: Xu, Zifan, et al.
Publicado: (2023)

Latent Causal Probing: A Formal Perspective on Probing with Causal Models of Data
por: Jin, Charles, et al.
Publicado: (2024)

Robust Search with Uncertainty-Aware Value Models for Language Model Reasoning
por: Yu, Fei, et al.
Publicado: (2025)

iCLP: Large Language Model Reasoning with Implicit Cognition Latent Planning
por: Chen, Sijia, et al.
Publicado: (2025)

Latent Reasoning via Sentence Embedding Prediction
por: Hwang, Hyeonbin, et al.
Publicado: (2025)

Learning to Ponder: Adaptive Reasoning in Latent Space
por: He, Yixin, et al.
Publicado: (2025)

BFS-PO: Best-First Search for Large Reasoning Models
por: Parascandolo, Fiorenzo, et al.
Publicado: (2026)

Accelerating Large Language Model Reasoning via Speculative Search
por: Wang, Zhihai, et al.
Publicado: (2025)

SEM: Reinforcement Learning for Search-Efficient Large Language Models
por: Sha, Zeyang, et al.
Publicado: (2025)

Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories
por: Liu, Peiyang, et al.
Publicado: (2026)

SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
por: Shi, Dachuan, et al.
Publicado: (2025)

Reasoning Beyond Chain-of-Thought: A Latent Computational Mode in Large Language Models
por: He, Zhenghao, et al.
Publicado: (2026)

Lessons from Studying Two-Hop Latent Reasoning
por: Balesni, Mikita, et al.
Publicado: (2024)

LongReasonArena: A Long Reasoning Benchmark for Large Language Models
por: Ding, Jiayu, et al.
Publicado: (2025)

Verbalized Confidence Triggers Self-Verification: Emergent Behavior Without Explicit Reasoning Supervision
por: Jang, Chaeyun, et al.
Publicado: (2025)

THOUGHTSCULPT: Reasoning with Intermediate Revision and Search
por: Chi, Yizhou, et al.
Publicado: (2024)

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
por: Chen, Mingyang, et al.
Publicado: (2025)

Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner
por: Zhou, Cai, et al.
Publicado: (2025)