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

arXiv:2605.28108 · cs.CL · Submitted 2026-05-27 · Read on arXiv

cs.CL

Submitted: 2026-05-27

Updated: 2026-09-15

Comments: Accepted to EMNLP 2026 Main Conference

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 27× in this paper · explained in 2 episodes
• Trace — 17× in this paper · explained in 2 episodes
• Accuracy — 13× in this paper · explained in 1 episode
• Calibration — 12× in this paper · explained in 7 episodes
• Personalization — 11× in this paper · explained in 2 episodes
• DeepSeek V4 Flash — 7× in this paper
• DeepSeek V4 Pro — 6× in this paper
• Ontology — 5× in this paper · explained in 2 episodes
• Scaffolding — 5× in this paper · explained in 3 episodes
• Actionability — 2× in this paper · explained in 3 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• Provenance — 2× in this paper · explained in 3 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Arbiter — 1× in this paper · explained in 1 episode
• Grounding — 1× in this paper · explained in 3 episodes
• Information Gain — 1× in this paper · explained in 2 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes

Sources

• Springdrift: An Auditable Persistent Runtime for LLM Agents with Case-Based Memory, Normative Safety, and Ambient Self-Perception
• PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents
• KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation
• BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design
• LifeSim: Long-Horizon User Life Simulator for Personalized Assistant Evaluation
• PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records
• Latent Preference Modeling for Multi-Session Personalized Tool Calling
• Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants
• $\pi$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
• MemGPT: Towards LLMs as Operating Systems

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering