Cover Image

When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sheng, Leheng, Zhang, Yongtao, Ma, Wenchang, Shi, Yaorui, Huang, Ting, Wang, Xiang, Zhang, An, Shen, Ke, Chua, Tat-Seng
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics
by: Sheng, Leheng, et al.
Published: (2026)

When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR
by: Miao, Yuchun, et al.
Published: (2026)

On Reasoning Strength Planning in Large Reasoning Models
by: Sheng, Leheng, et al.
Published: (2025)

On Generative Agents in Recommendation
by: Zhang, An, et al.
Published: (2023)

Language Representations Can be What Recommenders Need: Findings and Potentials
by: Sheng, Leheng, et al.
Published: (2024)

Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules
by: Liu, Zhiyuan, et al.
Published: (2023)

General Debiasing for Graph-based Collaborative Filtering via Adversarial Graph Dropout
by: Zhang, An, et al.
Published: (2024)

Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents
by: Shi, Yaorui, et al.
Published: (2025)

ReactXT: Understanding Molecular "Reaction-ship" via Reaction-Contextualized Molecule-Text Pretraining
by: Liu, Zhiyuan, et al.
Published: (2024)

On Softmax Direct Preference Optimization for Recommendation
by: Chen, Yuxin, et al.
Published: (2024)

Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
by: Guo, Yanjun, et al.
Published: (2026)

AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint
by: Sheng, Leheng, et al.
Published: (2025)

When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
by: Zhao, Weixiang, et al.
Published: (2025)

Learning to Self-Verify Makes Language Models Better Reasoners
by: Chen, Yuxin, et al.
Published: (2026)

DRAFT: Task Decoupled Latent Reasoning for Agent Safety
by: Wang, Lin, et al.
Published: (2026)

Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding
by: Zhang, Zhihan, et al.
Published: (2024)

Reasoning Can Be Restored by Correcting a Few Decision Tokens
by: Shen, Changshuo, et al.
Published: (2026)

Disentangling Masked Autoencoders for Unsupervised Domain Generalization
by: Zhang, An, et al.
Published: (2024)

NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation
by: Liu, Zhiyuan, et al.
Published: (2025)

TTOM: Test-Time Optimization and Memorization for Compositional Video Generation
by: Qu, Leigang, et al.
Published: (2025)

Understanding Long Videos via LLM-Powered Entity Relation Graphs
by: Chu, Meng, et al.
Published: (2025)

Hello Again! LLM-powered Personalized Agent for Long-term Dialogue
by: Li, Hao, et al.
Published: (2024)

MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
by: Shi, Yaorui, et al.
Published: (2026)

Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning
by: Sun, Renliang, et al.
Published: (2025)

The Pitfalls of Memorization: When Memorization Hurts Generalization
by: Bayat, Reza, et al.
Published: (2024)

Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond
by: Li, Yongqi, et al.
Published: (2024)

Compose Your Aesthetics: Empowering Text-to-Image Models with the Principles of Art
by: Jin, Zhe, et al.
Published: (2025)

Does Your Reasoning Model Implicitly Know When to Stop Thinking?
by: Huang, Zixuan, et al.
Published: (2026)

Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation
by: Wang, Chengbing, et al.
Published: (2025)

Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving
by: Zhang, Dapeng, et al.
Published: (2025)

When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory
by: Shao, Jiaqi, et al.
Published: (2026)

When to Stop? Towards Efficient Code Generation in LLMs with Excess Token Prevention
by: Guo, Lianghong, et al.
Published: (2024)

Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments
by: Chen, Yuxin, et al.
Published: (2026)

Critical Windows of Complexity Control: When Transformers Decide to Reason or Memorize
by: Ali, Sarwan
Published: (2026)

Reasoning over Semantic IDs Enhances Generative Recommendation
by: He, Yingzhi, et al.
Published: (2026)

Learning When to Attend: Conditional Memory Access for Long-Context LLMs
by: Choudhary, Sakshi, et al.
Published: (2026)

Towards Goal-oriented Intelligent Tutoring Systems in Online Education
by: Deng, Yang, et al.
Published: (2023)

LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation
by: He, Yingzhi, et al.
Published: (2025)

When Can Memorization Improve Fairness?
by: Pepin, Bob, et al.
Published: (2024)

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models
by: Min, Dehai, et al.
Published: (2026)