Buchumschlag

DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Jiang, Yuxuan, Li, Dawei, Ferraro, Francis
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance
von: Jiang, Yuxuan, et al.
Veröffentlicht: (2026)

Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMs
von: Jiang, Yuxuan, et al.
Veröffentlicht: (2024)

Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization
von: He, Junlin, et al.
Veröffentlicht: (2026)

CoRE: Condition-based Reasoning for Identifying Outcome Variance in Complex Events
von: Vallurupalli, Sai, et al.
Veröffentlicht: (2025)

Efficient Mathematical Reasoning Models via Dynamic Pruning and Knowledge Distillation
von: Yu, Fengming, et al.
Veröffentlicht: (2025)

Skill-Aware Data Selection and Fine-Tuning for Data-Efficient Reasoning Distillation
von: Zhang, Lechen, et al.
Veröffentlicht: (2026)

Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models
von: Xiang, Yang, et al.
Veröffentlicht: (2025)

Think Less, Know More: State-Aware Reasoning Compression with Knowledge Guidance for Efficient Reasoning
von: Sui, Yi, et al.
Veröffentlicht: (2026)

Is Sarcasm Detection A Step-by-Step Reasoning Process in Large Language Models?
von: Yao, Ben, et al.
Veröffentlicht: (2024)

ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models
von: Yuan, Zhihang, et al.
Veröffentlicht: (2023)

If We May De-Presuppose: Robustly Verifying Claims through Presupposition-Free Question Decomposition
von: Dipta, Shubhashis Roy, et al.
Veröffentlicht: (2025)

Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation
von: Dai, Chengwei, et al.
Veröffentlicht: (2024)

LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models
von: Hao, Shibo, et al.
Veröffentlicht: (2024)

Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking
von: Zhu, Junda, et al.
Veröffentlicht: (2025)

Skill-Conditioned Gated Self-Distillation for LLM Reasoning
von: Huang, Jiazhen, et al.
Veröffentlicht: (2026)

MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning
von: Dutta, Aritra, et al.
Veröffentlicht: (2026)

Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models
von: Jiang, Song, et al.
Veröffentlicht: (2023)

Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval
von: Dipta, Shubhashis Roy, et al.
Veröffentlicht: (2025)

Evaluating and Enhancing Large Language Models for Conversational Reasoning on Knowledge Graphs
von: Huang, Yuxuan
Veröffentlicht: (2023)

Knowledge Distillation for Temporal Knowledge Graph Reasoning with Large Language Models
von: Xing, Wang, et al.
Veröffentlicht: (2026)

Cognition-of-Thought Elicits Social-Aligned Reasoning in Large Language Models
von: Zhang, Xuanming, et al.
Veröffentlicht: (2025)

D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use
von: Xu, Bowen, et al.
Veröffentlicht: (2026)

ASDA: Automated Skill Distillation and Adaptation for Financial Reasoning
von: Yim, Tik Yu, et al.
Veröffentlicht: (2026)

Stabilizing Efficient Reasoning with Step-Level Advantage Selection
von: Wang, Han, et al.
Veröffentlicht: (2026)

Self-Enhanced Reasoning Training: Activating Latent Reasoning in Small Models for Enhanced Reasoning Distillation
von: Zhang, Yong, et al.
Veröffentlicht: (2025)

The Impact of Reasoning Step Length on Large Language Models
von: Jin, Mingyu, et al.
Veröffentlicht: (2024)

Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
von: Zhao, Siyan, et al.
Veröffentlicht: (2026)

A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
von: Qu, Xiaoye, et al.
Veröffentlicht: (2025)

Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models
von: Liu, Yantao, et al.
Veröffentlicht: (2024)

Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification
von: Liu, Chengwu, et al.
Veröffentlicht: (2025)

AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition
von: Chen, Zhaorun, et al.
Veröffentlicht: (2024)

Reasoning on Efficient Knowledge Paths:Knowledge Graph Guides Large Language Model for Domain Question Answering
von: Wang, Yuqi, et al.
Veröffentlicht: (2024)

Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models
von: Wang, Teng, et al.
Veröffentlicht: (2025)

Evaluating Step-by-Step Reasoning through Symbolic Verification
von: Zhang, Yi-Fan, et al.
Veröffentlicht: (2022)

Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning
von: Cao, Lang, et al.
Veröffentlicht: (2024)

STEPER: Step-wise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Models
von: Lee, Kyumin, et al.
Veröffentlicht: (2025)

Efficient Inference for Large Reasoning Models: A Survey
von: Liu, Yue, et al.
Veröffentlicht: (2025)

Efficient Vision-Language Reasoning via Adaptive Token Pruning
von: Li, Xue, et al.
Veröffentlicht: (2025)

Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation
von: Jiang, Yuxuan, et al.
Veröffentlicht: (2026)

The Valley of Code Reasoning: Scaling Knowledge Distillation of Large Language Models
von: He, Muyu, et al.
Veröffentlicht: (2025)