Cover Image

Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dong, Songwei, Chen, Zihan, Shi, Chengshuai, Wang, Peng, Li, Jundong, Shen, Cong
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Efficient Prompt Optimization Through the Lens of Best Arm Identification
by: Shi, Chengshuai, et al.
Published: (2024)

FastGAS: Fast Graph-based Annotation Selection for In-Context Learning
by: Chen, Zihan, et al.
Published: (2024)

FedHERO: A Federated Learning Approach for Node Classification Task on Heterophilic Graphs
by: Chen, Zihan, et al.
Published: (2025)

Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits
by: Li, Donghao, et al.
Published: (2026)

Greedy Sampling Is Provably Efficient for RLHF
by: Wu, Di, et al.
Published: (2025)

$f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses
by: Wu, Di, et al.
Published: (2026)

Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion
by: Tan, Zhen, et al.
Published: (2026)

EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
by: Liu, Jiaqi, et al.
Published: (2026)

From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning
by: Chen, Zihan, et al.
Published: (2025)

Graph Prompting for Graph Learning Models: Recent Advances and Future Directions
by: Fu, Xingbo, et al.
Published: (2025)

ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data
by: Lei, Zhenyu, et al.
Published: (2024)

From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
by: Wang, Xiao, et al.
Published: (2026)

Memory Retention Is Not Enough to Master Memory Tasks in Reinforcement Learning
by: Shchendrigin, Oleg, et al.
Published: (2026)

Potent but Stealthy: Rethink Profile Pollution against Sequential Recommendation via Bi-level Constrained Reinforcement Paradigm
by: Su, Jiajie, et al.
Published: (2025)

GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks
by: Fu, Xingbo, et al.
Published: (2025)

One Sample is Enough to Make Conformal Prediction Robust
by: Zargarbashi, Soroush H., et al.
Published: (2025)

From Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges
by: Hong, Yihan, et al.
Published: (2026)

Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods?
by: Chen, Zihan, et al.
Published: (2025)

Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards
by: He, Haoran, et al.
Published: (2025)

One-Way Policy Optimization for Self-Evolving LLMs
by: Yang, Shuo, et al.
Published: (2026)

RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services
by: Zhao, Fei, et al.
Published: (2025)

Parameter Efficiency Is Not Memory Efficiency: Rethinking Fine-Tuning for On-Device LLM Adaptation
by: Tenison, Irene, et al.
Published: (2026)

How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning
by: Zhai, Zhiyuan, et al.
Published: (2026)

Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective
by: Dong, Yushun, et al.
Published: (2024)

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
by: Zhang, Mohan, et al.
Published: (2025)

Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models
by: Balef, Amir Rezaei, et al.
Published: (2026)

Sequential Stochastic Combinatorial Optimization Using Hierarchal Reinforcement Learning
by: Feng, Xinsong, et al.
Published: (2025)

Federated Graph Learning with Structure Proxy Alignment
by: Fu, Xingbo, et al.
Published: (2024)

Self-Evolving Curriculum for LLM Reasoning
by: Chen, Xiaoyin, et al.
Published: (2025)

DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation
by: Zhou, Yang, et al.
Published: (2026)

When Drafts Evolve: Speculative Decoding Meets Online Learning
by: Qian, Yu-Yang, et al.
Published: (2026)

FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation
by: Ding, Zhihao, et al.
Published: (2026)

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
by: Lin, Huawei, et al.
Published: (2026)

CSAttention: Centroid-Scoring Attention for Accelerating LLM Inference
by: Song, Chuxu, et al.
Published: (2026)

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
by: Wang, Yuyao, et al.
Published: (2026)

No Free Lunch: Rethinking Internal Feedback for LLM Reasoning
by: Zhang, Yanzhi, et al.
Published: (2025)

Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
by: Li, Sijia, et al.
Published: (2025)

Edge Prompt Tuning for Graph Neural Networks
by: Fu, Xingbo, et al.
Published: (2025)

Is Distance Matrix Enough for Geometric Deep Learning?
by: Li, Zian, et al.
Published: (2023)

APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents
by: Li, Yibo, et al.
Published: (2026)