HALO evaluates proactive agents with human annotations
HALO-8K dataset tests 10 models across 400 scenarios, revealing over-proactivity in 61.20% of rejections.
Stories per day · 30 days
2 RSS
Relatedbenchmark2evaluation1halo1human-grounded1multimodal1streaming1user-intent1video-agents1video-understanding1vision-language-models1
7 stories, newest first · one card per story
Stories tagged #proactive-agents
AskStream benchmark tests when video models should ask
The strongest model scores only 52.18% Ask-F1 across 438 videos labeled for wait, ask, and answer.
StreamVibe-VL infers evolving user intent for proactive video agents
The benchmark has 4.1K evaluation and 85K training samples; timing and answer quality rose 10.7% over baselines.
Meta, OpenAI and Uber Just Taught AI Agents to Talk First. What About When to Stay Quiet?
Meta Muse, OpenAI Dots, and Uber's driver assistant push proactive messages, raising when agents should interrupt.
Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym
A paper defines 3T principles and PROACTIVITY-GYM for evaluating proactive LLM agents on capability, timing, and trust.
Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents
ExpActivator activates only situation-applicable GUI history, lifting step success 28% while using far fewer tokens.
When Intelligence Becomes Agency: A Theory of Governed, Proactive Agency for Symbiotic AI Systems
Researchers propose a formal framework for governed proactive AI agency, linking activation decisions to continuing authorization, accountability, and bounded delegation in symbiotic systems.