Imagen de Portada

Boosting LLM Reasoning via Spontaneous Self-Correction

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhao, Xutong, Xu, Tengyu, Wang, Xuewei, Chen, Zhengxing, Jin, Di, Tan, Liang, Yen-Ting, Yu, Zishun, Zhao, Zhuokai, He, Yun, Wang, Sinong, Fang, Han, Chandar, Sarath, Zhu, Chen
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization
por: Yu, Zishun, et al.
Publicado: (2025)

GRPO-$λ$: Credit Assignment improves LLM Reasoning
por: Parthasarathi, Prasanna, et al.
Publicado: (2025)

Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback
por: Lin, Yen-Ting, et al.
Publicado: (2025)

Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training
por: Liu, Yixin, et al.
Publicado: (2026)

Self-Generated Critiques Boost Reward Modeling for Language Models
por: Yu, Yue, et al.
Publicado: (2024)

Effect of Document Packing on the Latent Multi-Hop Reasoning Capabilities of Large Language Models
por: Prato, Gabriele, et al.
Publicado: (2025)

NeuroFaith: Evaluating LLM Self-Explanation Faithfulness via Internal Representation Alignment
por: Bhan, Milan, et al.
Publicado: (2025)

Faithfulness Measurable Masked Language Models
por: Madsen, Andreas, et al.
Publicado: (2023)

Are self-explanations from Large Language Models faithful?
por: Madsen, Andreas, et al.
Publicado: (2024)

Self-Evolving Multi-Agent Systems via Decentralized Memory
por: Hao, Guangya, et al.
Publicado: (2026)

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
por: Wang, Chaoqi, et al.
Publicado: (2025)

Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
por: Nilaksh, et al.
Publicado: (2026)

Direct Acquisition Optimization for Low-Budget Active Learning
por: Zhao, Zhuokai, et al.
Publicado: (2024)

Probing the effectiveness of World Models for Spatial Reasoning through Test-time Scaling
por: Jha, Saurav, et al.
Publicado: (2025)

Preference Optimization with Multi-Sample Comparisons
por: Wang, Chaoqi, et al.
Publicado: (2024)

Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination
por: Huang, Jerry, et al.
Publicado: (2024)

STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
por: Dong, Kefan, et al.
Publicado: (2025)

LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents
por: Baldelli, Davide, et al.
Publicado: (2026)

Neural Coherence : Find higher performance to out-of-distribution tasks from few samples
por: Guiroy, Simon, et al.
Publicado: (2025)

The Expressive Limits of Diagonal SSMs for State-Tracking
por: Shakerinava, Mehran, et al.
Publicado: (2026)

Intelligent Switching for Reset-Free RL
por: Patil, Darshan, et al.
Publicado: (2024)

Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models
por: Huang, Jerry, et al.
Publicado: (2024)

Interpretability Needs a New Paradigm
por: Madsen, Andreas, et al.
Publicado: (2024)

Exploring Quantization for Efficient Pre-Training of Transformer Language Models
por: Chitsaz, Kamran, et al.
Publicado: (2024)

Towards Practical Tool Usage for Continually Learning LLMs
por: Huang, Jerry, et al.
Publicado: (2024)

Why Don't Prompt-Based Fairness Metrics Correlate?
por: Zayed, Abdelrahman, et al.
Publicado: (2024)

Should We Attend More or Less? Modulating Attention for Fairness
por: Zayed, Abdelrahman, et al.
Publicado: (2023)

Lookbehind-SAM: k steps back, 1 step forward
por: Mordido, Gonçalo, et al.
Publicado: (2023)

Towards LLM-Powered Verilog RTL Assistant: Self-Verification and Self-Correction
por: Huang, Hanxian, et al.
Publicado: (2024)

Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding
por: Fang, Yixiong, et al.
Publicado: (2024)

TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning
por: Yang, Shenzhi, et al.
Publicado: (2025)

The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning
por: Aghajohari, Milad, et al.
Publicado: (2025)

Data-Driven Adversarial Online Control for Unknown Linear Systems
por: Liu, Zishun, et al.
Publicado: (2023)

Multi-level Advantage Credit Assignment for Cooperative Multi-Agent Reinforcement Learning
por: Zhao, Xutong, et al.
Publicado: (2025)

Scalable Layer‐Controlled Oxidation of Bi 2 O 2 Se for Self‐Rectifying Memristor Arrays With sub‐pA Sneak Currents
por: Yingjie Zhao, et al.
Publicado: (2024)

Token-Budget-Aware LLM Reasoning
por: Han, Tingxu, et al.
Publicado: (2024)

Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning
por: Nilaksh, et al.
Publicado: (2026)

Mastering Memory Tasks with World Models
por: Samsami, Mohammad Reza, et al.
Publicado: (2024)

LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training
por: Wu, Bo, et al.
Publicado: (2025)

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration
por: Zhang, Qifan, et al.
Publicado: (2026)