Cover Image

Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cai, Yuxuan, Zhou, Jie, Chen, Qin, He, Liang
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark
by: Cai, Yuxuan, et al.
Published: (2025)

ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents
by: Fu, Xing, et al.
Published: (2026)

Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies
by: Cheng, Sitao, et al.
Published: (2025)

Invoke Interfaces Only When Needed: Adaptive Invocation for Large Language Models in Question Answering
by: Zhao, Jihao, et al.
Published: (2025)

Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?
by: Gulati, Anmol, et al.
Published: (2026)

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
by: Yang, Yutao, et al.
Published: (2026)

Ask-before-Plan: Proactive Language Agents for Real-World Planning
by: Zhang, Xuan, et al.
Published: (2024)

Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents
by: Wu, Bin, et al.
Published: (2026)

Do Proactive Agents Really Need an LLM to Decide When to Wake and What to Anchor?
by: Liu, Xiaoze, et al.
Published: (2026)

Ella: Embodied Social Agents with Lifelong Memory
by: Zhang, Hongxin, et al.
Published: (2025)

LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization
by: Li, Junsong, et al.
Published: (2025)

Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty
by: Xue, Chao, et al.
Published: (2026)

Think Only When You Need with Large Hybrid-Reasoning Models
by: Jiang, Lingjie, et al.
Published: (2025)

Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents
by: Zhang, Xing, et al.
Published: (2026)

Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions
by: Wang, Ziyue, et al.
Published: (2023)

PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents
by: Kim, Namyoung, et al.
Published: (2025)

MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalization
by: Zhang, Weizhi, et al.
Published: (2026)

Learning to Ask: When LLM Agents Meet Unclear Instruction
by: Wang, Wenxuan, et al.
Published: (2024)

Towards Lifelong Dialogue Agents via Timeline-based Memory Management
by: Ong, Kai Tzu-iunn, et al.
Published: (2024)

AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation
by: Wang, Zhengren, et al.
Published: (2026)

When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification
by: Zhao, Jiale, et al.
Published: (2026)

AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents
by: Zhu, Wenhui, et al.
Published: (2026)

On Safety Risks in Experience-Driven Self-Evolving Agents
by: Zhao, Weixiang, et al.
Published: (2026)

Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning
by: Chen, Qizhou, et al.
Published: (2024)

Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
by: Sun, Jingwei, et al.
Published: (2026)

Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
by: Hu, Zhanghao, et al.
Published: (2026)

Beyond Static Summarization: Proactive Memory Extraction for LLM Agents
by: Yang, Chengyuan, et al.
Published: (2026)

"Ask Me Anything": How Comcast Uses LLMs to Assist Agents in Real Time
by: Rome, Scott, et al.
Published: (2024)

HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning
by: Wang, Yangfan, et al.
Published: (2026)

Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs
by: Dong, Su, et al.
Published: (2026)

Knowing When to Ask -- Bridging Large Language Models and Data
by: Radhakrishnan, Prashanth, et al.
Published: (2024)

MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval
by: Li, Chunyu, et al.
Published: (2026)

Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
by: Zeng, Kun, et al.
Published: (2026)

Med-PMC: Medical Personalized Multi-modal Consultation with a Proactive Ask-First-Observe-Next Paradigm
by: Liu, Hongcheng, et al.
Published: (2024)

Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation
by: Wu, Yuqian, et al.
Published: (2026)

ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
by: Ho, Matthew, et al.
Published: (2025)

VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents
by: Wu, Zheng, et al.
Published: (2025)

SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Execution
by: Meng, Xiangcheng, et al.
Published: (2026)

When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation
by: Ni, Shiyu, et al.
Published: (2024)

Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
by: Cao, Zouying, et al.
Published: (2025)