Copertina

Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Bin, Zou, Guanyun, Wang, Bingbing, Zhao, Huan, Shi, Chuan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

When Agents Trade: Live Multi-Market Trading Benchmark for LLM Agents
di: Qian, Lingfei, et al.
Pubblicazione: (2025)

Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents
di: Cai, Yuxuan, et al.
Pubblicazione: (2026)

Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use
di: Kumar, Abhijit, et al.
Pubblicazione: (2026)

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

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

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

Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People
di: Grand, Gabriel, et al.
Pubblicazione: (2025)

MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments
di: Gao, Yicheng, et al.
Pubblicazione: (2026)

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

Long-term Task-oriented Agent: Proactive Long-term Intent Maintenance in Dynamic Environments
di: Shi, Qinglong, et al.
Pubblicazione: (2026)

Training Proactive and Personalized LLM Agents
di: Sun, Weiwei, et al.
Pubblicazione: (2025)

AcademicEval: Live Long-Context LLM Benchmark
di: Zhang, Haozhen, et al.
Pubblicazione: (2025)

AgentFold: Long-Horizon Web Agents with Proactive Context Management
di: Ye, Rui, et al.
Pubblicazione: (2025)

Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems
di: Zhu, Minghang, et al.
Pubblicazione: (2025)

VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild
di: Inc, Xiaohongshu
Pubblicazione: (2026)

Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
di: Lu, Yaxi, et al.
Pubblicazione: (2024)

Shopping Companion: Benchmarking and Training LLM Agents for Long-Horizon Preference-Grounded E-Commerce Tasks
di: Yu, Zijian, et al.
Pubblicazione: (2026)

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

Mitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory Representation
di: Jin, Zhengda, et al.
Pubblicazione: (2026)

FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents
di: Xiao, Ruixuan, et al.
Pubblicazione: (2024)

PPA-Plan: Proactive Pitfall Avoidance for Reliable Planning in Long-Context LLM Reasoning
di: Kim, Byeongjin, et al.
Pubblicazione: (2026)

Proactive defense against LLM Jailbreak
di: Zhao, Weiliang, et al.
Pubblicazione: (2025)

AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification
di: Zhang, Xuan, et al.
Pubblicazione: (2025)

Time-Scaling Is What Agents Need Now
di: Liu, Zhi, et al.
Pubblicazione: (2026)

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

Bridging the Gap: From Ad-hoc to Proactive Search in Conversations
di: Meng, Chuan, et al.
Pubblicazione: (2025)

Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents
di: Edwards, Nicholas, et al.
Pubblicazione: (2026)

Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification
di: Cegin, Jan, et al.
Pubblicazione: (2024)

Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue
di: Lin, Jingjie, et al.
Pubblicazione: (2026)

Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents
di: Xue, Tianci, et al.
Pubblicazione: (2026)

AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts
di: Fang, Shicheng, et al.
Pubblicazione: (2026)

ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions
di: Yang, Bufang, et al.
Pubblicazione: (2025)

ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild
di: Yang, Bufang, et al.
Pubblicazione: (2025)

LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks
di: Long, Xiang, et al.
Pubblicazione: (2026)

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

From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench
di: Xu, Ke, et al.
Pubblicazione: (2026)

PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
di: Xie, Zhifei, et al.
Pubblicazione: (2026)