Imagen de Portada

Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in Large Reasoning Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Phan, Hoang, Yang, Xianjun, Yao, Kevin, Zhang, Jingyu, Bi, Shengjie, Tang, Xiaocheng, Khabsa, Madian, Liu, Lijuan, Lei, Deren
Formato:	Preprint
Publicado:	2025
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

Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder
por: Yang, Xianjun, et al.
Publicado: (2025)

High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning
por: Franzmeyer, Tim, et al.
Publicado: (2025)

Offline Learning and Forgetting for Reasoning with Large Language Models
por: Ni, Tianwei, et al.
Publicado: (2025)

Selective Forgetting for Large Reasoning Models
por: Le, Tuan, et al.
Publicado: (2026)

Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models
por: Zhang, Qingjie, et al.
Publicado: (2025)

Evaluating the Generalization Capabilities of Large Language Models on Code Reasoning
por: Yang, Rem, et al.
Publicado: (2025)

Arithmetic Reasoning with LLM: Prolog Generation & Permutation
por: Yang, Xiaocheng, et al.
Publicado: (2024)

Decoding the Critique Mechanism in Large Reasoning Models
por: Phan, Hoang, et al.
Publicado: (2026)

CRPE: Expanding The Reasoning Capability of Large Language Model for Code Generation
por: Gui, Ningxin, et al.
Publicado: (2025)

Beyond Forgetting: Machine Unlearning Elicits Controllable Side Behaviors and Capabilities
por: Dang, Tien, et al.
Publicado: (2026)

Cooperative Strategic Planning Enhances Reasoning Capabilities in Large Language Models
por: Wang, Danqing, et al.
Publicado: (2024)

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding
por: Li, Ming, et al.
Publicado: (2025)

Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
por: Huang, Wenxuan, et al.
Publicado: (2025)

Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners
por: Yuan, Xiangchi, et al.
Publicado: (2025)

Mitigating Catastrophic Forgetting in Mathematical Reasoning Finetuning through Mixed Training
por: Reynolds, John Graham
Publicado: (2025)

Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal
por: Huang, Jianheng, et al.
Publicado: (2024)

Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models
por: Xie, Zhifei, et al.
Publicado: (2025)

Reasoning Capabilities and Invariability of Large Language Models
por: Raganato, Alessandro, et al.
Publicado: (2025)

Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering
por: Li, Qiming, et al.
Publicado: (2025)

Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning
por: Huang, Wei, et al.
Publicado: (2025)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
por: Huang, Yao, et al.
Publicado: (2025)

How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs
por: Feng, Guhao, et al.
Publicado: (2024)

Benchmarking Spatiotemporal Reasoning in LLMs and Reasoning Models: Capabilities and Challenges
por: Quan, Pengrui, et al.
Publicado: (2025)

What Makes Reasoning Invalid: Echo Reflection Mitigation for Large Language Models
por: He, Chen, et al.
Publicado: (2025)

Reasoning Capabilities of Large Language Models on Dynamic Tasks
por: Wong, Annie, et al.
Publicado: (2025)

Evaluating Consistency and Reasoning Capabilities of Large Language Models
por: Saxena, Yash, et al.
Publicado: (2024)

Evaluating Interventional Reasoning Capabilities of Large Language Models
por: Kasetty, Tejas, et al.
Publicado: (2024)

Evaluating Accounting Reasoning Capabilities of Large Language Models
por: Zhou, Jie, et al.
Publicado: (2026)

Enhancing Causal Reasoning in Large Language Models: A Causal Attribution Model for Precision Fine-Tuning
por: Cai, Hengrui, et al.
Publicado: (2023)

Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning
por: Zhang, Xinlu, et al.
Publicado: (2024)

Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering
por: Tang, Xinyu, et al.
Publicado: (2025)

MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities
por: Yu, Weihao, et al.
Publicado: (2023)

ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models
por: Liu, Jincheng, et al.
Publicado: (2025)

Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales
por: Qiu, Shikai, et al.
Publicado: (2025)

When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition
por: Sun, Xiaokun, et al.
Publicado: (2026)

Enhancing the Reasoning Capabilities of Small Language Models via Solution Guidance Fine-Tuning
por: Bi, Jing, et al.
Publicado: (2024)

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

Cumulative Reasoning with Large Language Models
por: Zhang, Yifan, et al.
Publicado: (2023)

Your thoughts tell who you are: Characterize the reasoning patterns of LRMs
por: Chen, Yida, et al.
Publicado: (2025)

LightPlanner: Unleashing the Reasoning Capabilities of Lightweight Large Language Models in Task Planning
por: Zhou, Weijie, et al.
Publicado: (2025)