Imagen de Portada

CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Nasvytis, Linas, Han, Simon Jerome, Prystawski, Ben, Grant, Satchel, Goodman, Noah D., Fan, Judith E.
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Emergent Symbol-like Number Variables in Artificial Neural Networks
por: Grant, Satchel, et al.
Publicado: (2025)

Model Alignment Search
por: Grant, Satchel
Publicado: (2025)

Leveraging Speech to Identify Signatures of Insight and Transfer in Problem Solving
por: Nasvytis, Linas, et al.
Publicado: (2026)

Addressing divergent representations from causal interventions on neural networks
por: Grant, Satchel, et al.
Publicado: (2025)

Scaling up the think-aloud method
por: Wurgaft, Daniel, et al.
Publicado: (2025)

Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection
por: Nasvytis, Linas, et al.
Publicado: (2024)

Language and Experience: A Computational Model of Social Learning in Complex Tasks
por: Colas, Cédric, et al.
Publicado: (2025)

Diagnosing Bottlenecks in Data Visualization Understanding by Vision-Language Models
por: Tartaglini, Alexa R., et al.
Publicado: (2025)

Large Language Model Reasoning Failures
por: Song, Peiyang, et al.
Publicado: (2026)

Lossy communication constrains iterated learning
por: Prystawski, Ben, et al.
Publicado: (2025)

Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity
por: Grant, Satchel, et al.
Publicado: (2026)

From Next-Token to Mathematics: The Learning Dynamics of Mathematical Reasoning in Language Models
por: Mishra, Shubhra, et al.
Publicado: (2024)

CORE: Contrastive Masked Feature Reconstruction on Graphs
por: Bo, Jianyuan, et al.
Publicado: (2025)

CORE: Concept-Oriented Reinforcement for Bridging the Definition-Application Gap in Mathematical Reasoning
por: Gao, Zijun, et al.
Publicado: (2025)

CORE: Collaborative Reasoning via Cross Teaching
por: Mishra, Kshitij, et al.
Publicado: (2026)

Towards Stepwise Domain Knowledge-Driven Reasoning Optimization and Reflection Improvement
por: Liu, Chengyuan, et al.
Publicado: (2025)

CORE: A Conceptual Reasoning Layer for Large Language Models
por: Hegde, Vishwas, et al.
Publicado: (2025)

TTSR: Test-Time Self-Reflection for Continual Reasoning Improvement
por: He, Haoyang, et al.
Publicado: (2026)

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

Evaluating and Optimizing Educational Content with Large Language Model Judgments
por: He-Yueya, Joy, et al.
Publicado: (2024)

Poly-EPO: Training Exploratory Reasoning Models
por: Orney, Ifdita Hasan, et al.
Publicado: (2026)

Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations
por: Geiger, Atticus, et al.
Publicado: (2023)

CORE-Acu: Structured Reasoning Traces and Knowledge Graph Safety Verification for Acupuncture Clinical Decision Support
por: Xu, Liuyi, et al.
Publicado: (2026)

Learning Formal Mathematics From Intrinsic Motivation
por: Poesia, Gabriel, et al.
Publicado: (2024)

STaR-GATE: Teaching Language Models to Ask Clarifying Questions
por: Andukuri, Chinmaya, et al.
Publicado: (2024)

Abductive and Contrastive Explanations for Scoring Rules in Voting
por: Contet, Clément, et al.
Publicado: (2024)

CORE-Seg: Reasoning-Driven Segmentation for Complex Lesions via Reinforcement Learning
por: Xie, Yuxin, et al.
Publicado: (2026)

Is Child-Directed Speech Effective Training Data for Language Models?
por: Feng, Steven Y., et al.
Publicado: (2024)

CLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection
por: Liu, Linbo, et al.
Publicado: (2026)

CalBench: Evaluating Coordination-Privacy Trade-offs in Multi-Agent LLMs
por: Zou, Chelsea, et al.
Publicado: (2026)

Neural Probabilistic Circuits: Enabling Compositional and Interpretable Predictions through Logical Reasoning
por: Chen, Weixin, et al.
Publicado: (2025)

Seeding for Success: Skill and Stochasticity in Tabletop Games
por: Goodman, James, et al.
Publicado: (2025)

Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement
por: Hou, Xinmeng, et al.
Publicado: (2026)

STRIVE: Structured Reasoning for Self-Improvement in Claim Verification
por: Gong, Haisong, et al.
Publicado: (2025)

CORE: Full-Path Evaluation of LLM Agents Beyond Final State
por: Michelakis, Panagiotis, et al.
Publicado: (2025)

RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability
por: Cai, Kaitong, et al.
Publicado: (2025)

Teaching Large Reasoning Models Effective Reflection
por: Wang, Hanbin, et al.
Publicado: (2026)

CriticAL: Critic Automation with Language Models
por: Li, Michael Y., et al.
Publicado: (2024)

CORE: Robust Out-of-Distribution Detection via Confidence and Orthogonal Residual Scoring
por: Yang, Jin Mo, et al.
Publicado: (2026)

Perfect Information Monte Carlo with Postponing Reasoning
por: Arjonilla, Jérôme, et al.
Publicado: (2024)