Buchumschlag

Adaptive Ability Decomposing for Unlocking Large Reasoning Model Effective Reinforcement Learning

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Chen, Zhipeng, Qin, Xiaobo, Zhao, Wayne Xin, Wu, Youbin, Wen, Ji-Rong
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computation and Language Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning
von: Deng, Jia, et al.
Veröffentlicht: (2025)

Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models
von: Chen, Zhipeng, et al.
Veröffentlicht: (2025)

Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration
von: Chen, Zhipeng, et al.
Veröffentlicht: (2026)

Towards Effective Code-Integrated Reasoning
von: Bai, Fei, et al.
Veröffentlicht: (2025)

ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph
von: Jiang, Jinhao, et al.
Veröffentlicht: (2023)

R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
von: Song, Huatong, et al.
Veröffentlicht: (2025)

JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
von: Zhou, Kun, et al.
Veröffentlicht: (2024)

R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning
von: Song, Huatong, et al.
Veröffentlicht: (2025)

A Survey on Enhancing Causal Reasoning Ability of Large Language Models
von: Li, Xin, et al.
Veröffentlicht: (2025)

Towards Coarse-to-Fine Evaluation of Inference Efficiency for Large Language Models
von: Chen, Yushuo, et al.
Veröffentlicht: (2024)

UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities
von: Du, Dong, et al.
Veröffentlicht: (2025)

Extracting and Combining Abilities For Building Multi-lingual Ability-enhanced Large Language Models
von: Chen, Zhipeng, et al.
Veröffentlicht: (2024)

TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models
von: Chu, Zheng, et al.
Veröffentlicht: (2023)

Code-driven Number Sequence Calculation: Enhancing the inductive Reasoning Abilities of Large Language Models
von: Chen, Kedi, et al.
Veröffentlicht: (2025)

Unlocking Continual Learning Abilities in Language Models
von: Du, Wenyu, et al.
Veröffentlicht: (2024)

Experience-Guided Reflective Co-Evolution of Prompts and Heuristics for Automatic Algorithm Design
von: Liu, Yihong, et al.
Veröffentlicht: (2025)

Eliciting Causal Abilities in Large Language Models for Reasoning Tasks
von: Wang, Yajing, et al.
Veröffentlicht: (2024)

Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems
von: Min, Yingqian, et al.
Veröffentlicht: (2024)

Enhancing LLM Reasoning with Reward-guided Tree Search
von: Jiang, Jinhao, et al.
Veröffentlicht: (2024)

Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
von: Wang, Bing, et al.
Veröffentlicht: (2026)

Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration
von: Deng, Wenhao, et al.
Veröffentlicht: (2025)

Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training
von: Yang, Jinxia, et al.
Veröffentlicht: (2024)

Revisiting the Graph Reasoning Ability of Large Language Models: Case Studies in Translation, Connectivity and Shortest Path
von: Dai, Xinnan, et al.
Veröffentlicht: (2024)

Precedent-Informed Reasoning: Mitigating Overthinking in Large Reasoning Models via Test-Time Precedent Learning
von: Wang, Qianyue, et al.
Veröffentlicht: (2026)

Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information
von: Huang, Youcheng, et al.
Veröffentlicht: (2025)

Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models
von: Sun, Haoxiang, et al.
Veröffentlicht: (2025)

Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
von: Cheng, Xiaoxue, et al.
Veröffentlicht: (2025)

A Survey on Large Language Model based Autonomous Agents
von: Wang, Lei, et al.
Veröffentlicht: (2023)

Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models
von: Chen, Guanxu, et al.
Veröffentlicht: (2025)

Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models
von: Liu, Shuodi, et al.
Veröffentlicht: (2025)

Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning
von: Wang, Yiqi, et al.
Veröffentlicht: (2024)

LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling
von: Tang, Zecheng, et al.
Veröffentlicht: (2025)

Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
von: Chen, Changyu, et al.
Veröffentlicht: (2024)

Improving Arithmetic Reasoning Ability of Large Language Models through Relation Tuples, Verification and Dynamic Feedback
von: Miao, Zhongtao, et al.
Veröffentlicht: (2024)

Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning
von: Fei, Zhaoye, et al.
Veröffentlicht: (2025)

Learning to Compress: Unlocking the Potential of Large Language Models for Text Representation
von: Zhang, Yeqin, et al.
Veröffentlicht: (2025)

Unlocking the Working Memory of Large Language Models for Latent Reasoning
von: Aichberger, Lukas, et al.
Veröffentlicht: (2026)

Unlocking Reasoning Capability on Machine Translation in Large Language Models
von: Rajaee, Sara, et al.
Veröffentlicht: (2026)

Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models
von: Liu, Zeyu, et al.
Veröffentlicht: (2025)

Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities
von: Zhao, Weixiang, et al.
Veröffentlicht: (2025)