Imagen de Portada

Expanding Search Space with Diverse Prompting Agents: An Efficient Sampling Approach for LLM Mathematical Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lee, Gisang, Park, Sangwoo, Park, Junyoung, Chung, Andrew, Park, Sieun, Park, Yoonah, Kim, Byungju, Cho, Min-gyu
Formato:	Preprint
Publicado:	2024
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

Addressing selectivity challenges in seawater splitting: Catalyst design for oxygen and chlorine evolution reactions
por: Gisang Park, et al.
Publicado: (2025)

QEFT: Quantization for Efficient Fine-Tuning of LLMs
por: Lee, Changhun, et al.
Publicado: (2024)

Improving Dialogue State Tracking through Combinatorial Search for In-Context Examples
por: Pyun, Haesung, et al.
Publicado: (2025)

Generalized Harnack Inequality for Mean Curvature Flow and Ancient Solutions
por: Park, Junyoung
Publicado: (2025)

Dynamical stability of various convex graphical translators
por: Park, Junyoung
Publicado: (2026)

SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models
por: Kim, Hyeonwoo, et al.
Publicado: (2024)

Beyond Performance Disparities: A Three-Level Audit of Representational Harm in CelebA
por: Park, Sieun, et al.
Publicado: (2026)

Learning to Retrieve User History and Generate User Profiles for Personalized Persuasiveness Prediction
por: Park, Sejun, et al.
Publicado: (2026)

Advancing 6D Pose Estimation in Augmented Reality -- Overcoming Projection Ambiguity with Uncontrolled Imagery
por: Manawadu, Mayura, et al.
Publicado: (2024)

Towards Efficient Visual-Language Alignment of the Q-Former for Visual Reasoning Tasks
por: Kim, Sungkyung, et al.
Publicado: (2024)

Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution
por: Kim, Bryan Sangwoo, et al.
Publicado: (2026)

Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures
por: Park, Junyoung, et al.
Publicado: (2026)

LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs
por: An, Sumin, et al.
Publicado: (2025)

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions
por: Park, Yoonah, et al.
Publicado: (2025)

MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline
por: Han, Donghoon, et al.
Publicado: (2024)

From Noise to Diversity: Random Embedding Injection in LLM Reasoning
por: Kim, Heejun, et al.
Publicado: (2026)

CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs
por: Kim, Jiwan, et al.
Publicado: (2025)

T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search
por: Lee, Hyomin, et al.
Publicado: (2026)

Sampling-Based Safety Filter with Probabilistic Restrictiveness Guarantee
por: Park, Junyoung, et al.
Publicado: (2026)

SEAL: Scaling to Emphasize Attention for Long-Context Retrieval
por: Lee, Changhun, et al.
Publicado: (2025)

Self-Refining Topology Optimization via an LLM-Based Multi-Agent Framework
por: Park, Hyunjee, et al.
Publicado: (2026)

Multi-Fidelity Bayesian Optimization With Across-Task Transferable Max-Value Entropy Search
por: Zhang, Yunchuan, et al.
Publicado: (2024)

Fréchet regression of multivariate distributions with nonparanormal transport
por: Park, Junyoung, et al.
Publicado: (2026)

Agentic Fuzzing: Opportunities and Challenges
por: Park, Junyoung, et al.
Publicado: (2026)

Optimizing In-Context Learning for Efficient Full Conformal Prediction
por: Deng, Weicao, et al.
Publicado: (2025)

Retrieval-Augmented Generation with Estimation of Source Reliability
por: Hwang, Jeongyeon, et al.
Publicado: (2024)

TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Image Denoising
por: Park, Junyoung, et al.
Publicado: (2026)

Gather-Scatter Mamba: Accelerating Propagation with Efficient State Space Model
por: Ko, Hyun-kyu, et al.
Publicado: (2025)

Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection
por: Zecchin, Matteo, et al.
Publicado: (2024)

Twenty-Three Independent Proofs That n=6 Is Mathematically Unique
por: Park, Min Woo
Publicado: (2026)

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge
por: In, Yeonjun, et al.
Publicado: (2025)

StableSketcher: Enhancing Diffusion Model for Pixel-based Sketch Generation via Visual Question Answering Feedback
por: Park, Jiho, et al.
Publicado: (2025)

Online Conformal Prediction with Adversarial Semi-bandit Feedback via Regret Minimization
por: Yang, Junyoung, et al.
Publicado: (2026)

Efficient Defective Clique Enumeration and Search with Worst-Case Optimal Search Space
por: Jang, Jihoon, et al.
Publicado: (2025)

Thunder-LLM: Efficiently Adapting LLMs to Korean with Minimal Resources
por: Kim, Jinpyo, et al.
Publicado: (2025)

SUIT: Knowledge Editing with Subspace-Aware Key-Value Mappings
por: Park, Haewon, et al.
Publicado: (2025)

Interpretable Prototype-based Graph Information Bottleneck
por: Seo, Sangwoo, et al.
Publicado: (2023)

LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemble
por: Lee, Yujeong, et al.
Publicado: (2024)

Genetic Algorithms with Neural Cost Predictor for Solving Hierarchical Vehicle Routing Problems
por: Sobhanan, Abhay, et al.
Publicado: (2023)

Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models
por: Park, Junyoung, et al.
Publicado: (2026)