Imagen de Portada

Didactic to Constructive: Turning Expert Solutions into Learnable Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mendes, Ethan, Park, Jungsoo, Ritter, Alan
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Anticipatory Evaluation of Language Models
por: Park, Jungsoo, et al.
Publicado: (2025)

Language Models can Self-Improve at State-Value Estimation for Better Search
por: Mendes, Ethan, et al.
Publicado: (2025)

Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression
por: Park, Jungsoo, et al.
Publicado: (2026)

Can LLMs Help Uncover Insights about LLMs? A Large-Scale, Evolving Literature Analysis of Frontier LLMs
por: Park, Jungsoo, et al.
Publicado: (2025)

CARE: Turning LLMs Into Causal Reasoning Expert
por: Dong, Juncheng, et al.
Publicado: (2025)

Learning to Reason at the Frontier of Learnability
por: Foster, Thomas, et al.
Publicado: (2025)

How Many Experts Are Enough? Towards Optimal Semantic Specialization for Mixture-of-Experts
por: Park, Sumin, et al.
Publicado: (2025)

Auditing Language Model Unlearning via Information Decomposition
por: Goel, Anmol, et al.
Publicado: (2026)

Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning
por: Jali, Neharika, et al.
Publicado: (2026)

GeoRC: A Benchmark for Geolocation Reasoning Chains
por: Talreja, Mohit, et al.
Publicado: (2026)

Evaluating Robustness of Reward Models for Mathematical Reasoning
por: Kim, Sunghwan, et al.
Publicado: (2024)

Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
por: Didolkar, Aniket, et al.
Publicado: (2025)

Is Data Valuation Learnable and Interpretable?
por: Wu, Ou, et al.
Publicado: (2024)

Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis
por: Li, Xinyi, et al.
Publicado: (2025)

A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning
por: Liu, Licheng, et al.
Publicado: (2025)

Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization
por: Ding, Yifeng, et al.
Publicado: (2025)

LAPLEX: The FFT of Learnable Laplace Kernels
por: Struski, Łukasz, et al.
Publicado: (2026)

Fully Learnable Neural Reward Machines
por: Dewidar, Hazem, et al.
Publicado: (2025)

Peirce in the Machine: How Mixture of Experts Models Perform Hypothesis Construction
por: Rushing, Bruce
Publicado: (2024)

Learnable Chernoff Baselines for Inference-Time Alignment
por: Madhow, Sunil, et al.
Publicado: (2026)

A Learnability Analysis on Neuro-Symbolic Learning
por: He, Hao-Yuan, et al.
Publicado: (2025)

On the Regularization of Learnable Embeddings for Time Series Forecasting
por: Butera, Luca, et al.
Publicado: (2024)

Neural Algorithmic Reasoning with Multiple Correct Solutions
por: Kujawa, Zeno, et al.
Publicado: (2024)

Token-Efficient RL for LLM Reasoning
por: Lee, Alan, et al.
Publicado: (2025)

Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and Generalizability
por: Xu, Chenhui, et al.
Publicado: (2025)

MAGNET: Autonomous Expert Model Generation via Decentralized Autoresearch and BitNet Training
por: Kim, Yongwan, et al.
Publicado: (2026)

On the Probabilistic Learnability of Compact Neural Network Preimage Bounds
por: Marzari, Luca, et al.
Publicado: (2025)

Understanding Representation Learnability of Nonlinear Self-Supervised Learning
por: Yang, Ruofeng, et al.
Publicado: (2024)

Learnable Spatial-Temporal Positional Encoding for Link Prediction
por: Tieu, Katherine, et al.
Publicado: (2025)

NeuralOGCM: Differentiable Ocean Modeling with Learnable Physics
por: Wu, Hao, et al.
Publicado: (2025)

A Complete Characterization of Learnability for Stochastic Noisy Bandits
por: Hanneke, Steve, et al.
Publicado: (2024)

Towards Learnable Anchor for Deep Multi-View Clustering
por: Wang, Bocheng, et al.
Publicado: (2025)

Rethinking Time Encoding via Learnable Transformation Functions
por: Chen, Xi, et al.
Publicado: (2025)

LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training
por: Gwak, Minju, et al.
Publicado: (2026)

DAMEL: Dual-Axis Multi-Expert Learning for Class-Imbalanced Learning
por: Lee, Hyuck, et al.
Publicado: (2026)

Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation
por: Chun, Yongchan, et al.
Publicado: (2026)

But what is your honest answer? Aiding LLM-judges with honest alternatives using steering vectors
por: Eshuijs, Leon, et al.
Publicado: (2025)

Retrieval-Retro: Retrieval-based Inorganic Retrosynthesis with Expert Knowledge
por: Noh, Heewoong, et al.
Publicado: (2024)

Can LLMs Score Medical Diagnoses and Clinical Reasoning as well as Expert Panels?
por: Rouillard, Amy, et al.
Publicado: (2026)

On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective
por: Zhou, Zhi, et al.
Publicado: (2026)