Cover Image

Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yuan, Xiangchi, Chen, Xiang, Yu, Tong, Shi, Dachuan, Jin, Can, Lee, Wenke, Mitra, Saayan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Superficial Self-Improved Reasoners Benefit from Model Merging
by: Yuan, Xiangchi, et al.
Published: (2025)

SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
by: Shi, Dachuan, et al.
Published: (2025)

CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning
by: Shi, Dachuan, et al.
Published: (2026)

MetaState: Persistent Working Memory Enhances Reasoning in Discrete Diffusion Language Models
by: Xia, Kejing, et al.
Published: (2026)

ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces
by: Xu, Xin, et al.
Published: (2026)

CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement
by: Tao, Leitian, et al.
Published: (2024)

An Interactive Paradigm for Deep Research
by: Ai, Lin, et al.
Published: (2026)

Behavior Knowledge Merge in Reinforced Agentic Models
by: Yuan, Xiangchi, et al.
Published: (2026)

RULE: Reinforcement UnLEarning Achieves Forget-Retain Pareto Optimality
by: Zhang, Chenlong, et al.
Published: (2025)

NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning
by: Chen, Huayu, et al.
Published: (2025)

SAPO: Self-Adaptive Process Optimization Makes Small Reasoners Stronger
by: Chen, Kaiyuan, et al.
Published: (2026)

Reverse Thinking Makes LLMs Stronger Reasoners
by: Chen, Justin Chih-Yao, et al.
Published: (2024)

Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning
by: Wu, Chao-Chung, et al.
Published: (2025)

Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information
by: Hu, Zhengmian, et al.
Published: (2023)

LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models
by: Shi, Dachuan, et al.
Published: (2025)

A Penalty Goes a Long Way: Measuring Lexical Diversity in Synthetic Texts Under Prompt-Influenced Length Variations
by: Deshpande, Vijeta, et al.
Published: (2025)

Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgetting
by: Ding, Fei, et al.
Published: (2025)

Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
by: Deng, Yihe, et al.
Published: (2025)

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

Mitigating Catastrophic Forgetting in Continual Learning through Model Growth
by: Süalp, Ege, et al.
Published: (2025)

ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following
by: Yang, Yuancheng, et al.
Published: (2026)

AuroraEdge-V-2B: A Faster And Stronger Edge Visual Large Language Model
by: Chen, Xiang
Published: (2026)

Stronger Re-identification Attacks through Reasoning and Aggregation
by: Charpentier, Lucas Georges Gabriel, et al.
Published: (2025)

Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
by: Chen, Howard, et al.
Published: (2025)

Free(): Learning to Forget in Malloc-Only Reasoning Models
by: Zheng, Yilun, et al.
Published: (2026)

Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
by: Lai, Song, et al.
Published: (2025)

Demystifying Language Model Forgetting with Low-rank Example Associations
by: Jin, Xisen, et al.
Published: (2024)

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers
by: Qi, Zhenting, et al.
Published: (2024)

Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs
by: Yu, Zeping, et al.
Published: (2025)

Growing Through Experience: Scaling Episodic Grounding in Language Models
by: Zhang, Chunhui, et al.
Published: (2025)

What Will My Model Forget? Forecasting Forgotten Examples in Language Model Refinement
by: Jin, Xisen, et al.
Published: (2024)

Detecting Ambiguities to Guide Query Rewrite for Robust Conversations in Enterprise AI Assistants
by: Tanjim, Md Mehrab, et al.
Published: (2025)

Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting
by: Watts, Ishaan, et al.
Published: (2026)

Stronger Models are NOT Stronger Teachers for Instruction Tuning
by: Xu, Zhangchen, et al.
Published: (2024)

Stronger Random Baselines for In-Context Learning
by: Yauney, Gregory, et al.
Published: (2024)

Parameter Alignment Mitigates Catastrophic Forgetting in Multilingual Expert Language Models
by: Ahuja, Sanchit, et al.
Published: (2026)

Reinforcing Multimodal Reasoning Against Visual Degradation
by: Liu, Rui, et al.
Published: (2026)

Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models
by: Liu, Zheyuan, et al.
Published: (2025)

Demystifying Reinforcement Learning in Agentic Reasoning
by: Yu, Zhaochen, et al.
Published: (2025)

Semantic Soft Bootstrapping: Long Context Reasoning in LLMs without Reinforcement Learning
by: Mitra, Purbesh, et al.
Published: (2025)