Cover Image

Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Xiao-Wen, Zhu, Xuan-Yi, Wei, Wen-Da, Zhang, Ding-Chu, Shao, Jie-Jing, Zhou, Zhi, Guo, Lan-Zhe, Li, Yu-Feng
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language Models
by: Yang, Xiao-Wen, et al.
Published: (2026)

Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models
by: Yang, Xiao-Wen, et al.
Published: (2025)

One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training
by: Ma, Lianbo, et al.
Published: (2024)

Quantitative Estimation of Target Task Performance from Unsupervised Pretext Task in Semi/Self-Supervised Learning
by: Jia, Lin-Han, et al.
Published: (2025)

Editorial: A Step Back to Leap Forward—Strategic Nucleos(t)ide Analogue Discontinuation Towards HBV Functional Cure
by: Xuwen Xu, et al.
Published: (2025)

Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training
by: You, Hong-Jie, et al.
Published: (2025)

One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models
by: Cameron, Chris, et al.
Published: (2026)

LawGPT: A Chinese Legal Knowledge-Enhanced Large Language Model
by: Zhou, Zhi, et al.
Published: (2024)

Dynamic Backtracking in GFlowNets: Enhancing Decision Steps with Reward-Dependent Adjustment Mechanisms
by: Guo, Shuai, et al.
Published: (2024)

ChinaTravel: An Open-Ended Travel Planning Benchmark with Compositional Constraint Validation for Language Agents
by: Shao, Jie-Jing, et al.
Published: (2024)

To Backtrack or Not to Backtrack: When Sequential Search Limits Model Reasoning
by: Qin, Tian, et al.
Published: (2025)

LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
by: Liang, Zhanhao, et al.
Published: (2026)

Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible
by: Jia, Lin-Han, et al.
Published: (2025)

Picture Book Sexism: Two Steps Forward and One Step Back?
by: Koss, Helen G.
Published: (1978)

Covalent Organic Frameworks for Electrocatalysis: Design, Applications, and Perspectives
by: Jing‐Dong Feng, et al.
Published: (2024)

Revisiting the Travel Planning Capabilities of Large Language Models
by: Zhang, Bo-Wen, et al.
Published: (2026)

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

Hindsight Credit Assignment for Long-Horizon LLM Agents
by: Tan, Hui-Ze, et al.
Published: (2026)

Adaptive Backtracking for Privacy Protection in Large Language Models
by: Yao, Zhihao, et al.
Published: (2025)

Vision-Language Model Selection and Reuse for Downstream Adaptation
by: Tan, Hao-Zhe, et al.
Published: (2025)

Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning
by: Zhou, Zhi, et al.
Published: (2025)

Offline Imitation Learning with Model-based Reverse Augmentation
by: Shao, Jie-Jing, et al.
Published: (2024)

Robust Semi-Supervised Learning in Open Environments
by: Guo, Lan-Zhe, et al.
Published: (2024)

A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
by: Zhou, Zhi, et al.
Published: (2025)

Correlated insulators and charge density wave states in chirally twisted triple bilayer graphene
by: Zhou, Geng-Dong, et al.
Published: (2024)

Emergent Search and Backtracking in Latent Reasoning Models
by: Cui, Jasmine, et al.
Published: (2026)

Exploring Performance Contrasts in TableQA: Step-by-Step Reasoning Boosts Bigger Language Models, Limits Smaller Language Models
by: Yang, Haoyan, et al.
Published: (2024)

Thinking with Tables: Enhancing Multi-Modal Tabular Understanding via Neuro-Symbolic Reasoning
by: Yu, Kun-Yang, et al.
Published: (2026)

Think with Self-Decoupling and Self-Verification: Automated RTL Design with Backtrack-ToT
by: Chao, Zhiteng, et al.
Published: (2025)

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets
by: Jia, Zexi, et al.
Published: (2025)

LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking
by: Ma, Yukai, et al.
Published: (2025)

The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces
by: Rezazadeh, Navid, et al.
Published: (2026)

Sherlock: Self-Correcting Reasoning in Vision-Language Models
by: Ding, Yi, et al.
Published: (2025)

KAT to KANs: A Review of Kolmogorov-Arnold Networks and the Neural Leap Forward
by: Basina, Divesh, et al.
Published: (2024)

InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding
by: Liu, Haogeng, et al.
Published: (2024)

Boosting Ag 2 S Solar Cell Efficiency by Back Interface Engineering
by: Weiwei Dong, et al.
Published: (2026)

Stepping Forward on the Last Mile
by: Feng, Chen, et al.
Published: (2024)

Backtrackable Inprocessing
by: Nadel, Alexander
Published: (2026)

Backtracking for Safety
by: Sel, Bilgehan, et al.
Published: (2025)

Pressure‐Induced Forward‐Shift of Proton‐Coupled Electron Transfer Step Boosts CO‐to‐Acetate Throughput
by: Jian Jin, et al.
Published: (2026)