Paper directory

Find original papers, repositories, and project pages.

With codeSelected

2026-10arXiv 2610

Knowing When to Yield: Grounded Arbitration of User Corrections in Text-Based Embodied Agents

Paper

2026-10arXiv 2610

OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction

Multimodal / Wearable Memory Intervention Timing Streaming

Paper Project Repo Model Dataset

2026-10arXiv 2610

OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents

Tool Use Safety & Consent Benchmark

Paper

2026-09ECCV 2026 Wearable AI Challenge

Ambient @ EgoProactive 2026: Proactive Egocentric Assistance with Visually Grounded Supervision

Multimodal / Wearable Intervention Timing Optimization Streaming

Paper Repo

2026-09arXiv 2609

APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants

Multimodal / Wearable Memory Benchmark Streaming

Paper

2026-09arXiv 2609

Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization

Clarification Planning Benchmark

Paper

2026-09arXiv 2609

Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents

Definition Intent Inference Optimization

Paper Project Repo

2026-09CoRL 2026

Bayesian Active Learning for Intent Disambiguation in Interactive Robot Planning

Embodied Clarification Planning

Paper

2026-09arXiv 2609

Beyond Instruction-Driven Editing: Source-Grounded Problem Discovery with User-Governed Repair for Scientific Posters

GUI Human Factors Safety & Consent

Paper

2026-09arXiv 2609

Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent

Clarification Intent Inference Benchmark

Paper

2026-09arXiv 2609

Breaking Up is Hard to Do: AI Companions that Won't Let Their Users Go

Human Factors Safety & Consent Dialogue

Paper

2026-09arXiv 2609

CC-Mediation: Evaluating Large Language Models for Cross-Cultural Conflict Mediation

Dialogue Intervention Timing Benchmark

Paper Repo

2026-09arXiv 2609

Clarify the User or Verify the World? Uncertainty Routing for Proactive Agents

Clarification Tool Use Planning

Paper

2026-09arXiv 2609

Cognitive Action Reasoning for Proactive Robots from Human-Centered Multimodal Observations

Embodied Intent Inference Benchmark

Paper

2026-09arXiv 2609

Designing Proactive Thought Partners for Writing

Human Factors Intervention Timing Personalization

Paper

2026-09arXiv 2609

Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents

GUI Safety & Consent Intervention Timing

Paper Repo

2026-09arXiv 2609

DocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documents

Collaboration Intervention Timing GUI

Paper

2026-09arXiv 2609

DuplexAct-Bench: Broadening Full-Duplex Speech Evaluation toward Proactive Interaction across Diverse Behavioral Requirements

Multimodal / Wearable Intervention Timing Benchmark Streaming

Paper Project

2026-09arXiv 2609

FinInteract: Benchmarking Clarification and Intent Integration in Ambiguous Financial Question Answering

Clarification Benchmark Dialogue

Paper

2026-09arXiv 2609

Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym

Definition Human Factors Benchmark

Paper

Enable JavaScript for search and filtering.

Knowing When to Yield: Grounded Arbitration of User Corrections in Text-Based Embodied Agents

OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction

OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents

Ambient @ EgoProactive 2026: Proactive Egocentric Assistance with Visually Grounded Supervision

APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants

Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization

Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents

Bayesian Active Learning for Intent Disambiguation in Interactive Robot Planning

Beyond Instruction-Driven Editing: Source-Grounded Problem Discovery with User-Governed Repair for Scientific Posters

Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent

Breaking Up is Hard to Do: AI Companions that Won't Let Their Users Go

CC-Mediation: Evaluating Large Language Models for Cross-Cultural Conflict Mediation

Clarify the User or Verify the World? Uncertainty Routing for Proactive Agents

Cognitive Action Reasoning for Proactive Robots from Human-Centered Multimodal Observations

Designing Proactive Thought Partners for Writing

Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents

DocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documents

DuplexAct-Bench: Broadening Full-Duplex Speech Evaluation toward Proactive Interaction across Diverse Behavioral Requirements

FinInteract: Benchmarking Clarification and Intent Integration in Ambiguous Financial Question Answering

Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym

Full-Duplex Speech Models Take the Floor When Asked, Not When Needed

Generative Tutorial: Towards Live Contextualized Visual Instructions for Physical Tasks

HiThink Turn: An Intent-Aware Turn-Taking Control Module for Full-Duplex Dialogue

IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications

Learning When and How to Intervene: A Hindsight-Distilled Sentinel for Coding Agents

Live Assistant: Learning Whether, When, and Whom to Assist in Real-World Live Social Streams

New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models

Omni Interaction Agent Technical Report

Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help

PASTABench: Proactive Assessment of Sequential Trajectories for Agent Safety

PrecogUI: Proactive GUI Agents via Pre-cognitive Simulation and Experience Retrieval

Proactive Dialogue Policy Optimization via Cognitive-State Transition

Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation

ProMediConv: Benchmarking Proactive Conversational Agents in Legal Dispute Mediation

Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality

Rational Clarification by Assistive Agents via Value-of-Information Reasoning

Realtime-Venus: A Full-Duplex Interaction System with Asynchronous Delegation

Referential Uncertainty in Human--AI Collaboration

Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents

RobotEQ 3.0: Towards Personalized Social Proactive Intelligence in Embodied Agents

Robots That Take Initiative: A Framework for Building and Evaluating Proactive Robots

RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation

Safety Nudges: User-Facing Interventions for Real-Time AI Risk Awareness

Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting

Time-Aware Assistive Navigation

TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding

TWIST: A Proposed Benchmark for Intervention Quality in Conversational Memory, with a Human-Validated Draft-Alignment

When and How Should an Agent Clarify? CIGAsk: Teaching LLMs to Clarify via Counterfactual Information Gain

When Intelligence Becomes Agency: A Theory of Governed, Proactive Agency for Symbiotic AI Systems

When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents

Working with Agentic 'Teammates': When a New Organizational Actor Collides with the Human Ecosystem of Work

A Self-Triggered Agentic Push Recommendation System

Act2Intention: A Benchmark For Developing Active Mobile Agents Through Inferring User Intention from GUI Actions

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports

AI Watchdog: Agent Interfaces for Detecting and Defending Against Manipulative Dark Patterns in AI Conversations

Beyond Information Seeking: Severity-Aware Question Supervision for Proactive Medical Dialogue

Bridging Search and CRM: Productionizing AI Product Research Agents for Customer Re-Engagement

CLAIM: Leading Open-domain Active Clarification of Large Language Models with Uncertainty Measurement

Clarify User Expertise: Towards Proactive Conversational Agents Tailoring Responses to User Proficiency

From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations

From Sports to Safety: Benchmarking Proactive Risk Inference in MLLMs

GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience

InsightToast: Proactive Information Retrieval & Glanceable Visualization in the Side Channel of Data-Rich Meetings

ITO: Real-time Browser Tab Orchestration Through Intent Detection

JarvisBench: Always-on Intelligence Between Humans and Agents

MMPCBench: Benchmarking Multimodal Large Language Models on Proactive Critique of Flawed Inputs

MOSS-VL Technical Report

Not Just Reason, Not Just Scan: Reinforcement Learning for Proactive Scientific Error Verification over Academic Paper

OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs

On the Prospects of Dynamic LLM Conversations in Software Development

Preference-Driven Online Adaptation for Personalized Interaction Initiation in Proactive AI Assistants

StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding

StreamSoccer: Event-Driven Memory for Streaming Soccer Commentary

Towards Cognitive Process-Aware Proactive Writing Support

VeriForge: Mitigating Latent Knowledge Gaps in Narrative Drafting via Mixed-Initiative Scaffolding

VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?

When Seeing Is Not Enough: Benchmarking Interactive Visual Grounding in LVLMs

Why2Speak: Faithful Reasoning for Abstaining Action Policies

"Excuse me, may I say something..." CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations

AI Assistants Overassist

ChatMuse: Supporting In-Person Small-Group Conversation Experience with a Proactive Assistive AI Agent in Mixed Reality

ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents

InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning

Let LLM Tutors Ask First: Proactive LLM-Based Tutoring at Scale in a 1,500-Student Online Classroom

PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records

ProACT: Towards Breakdown-Aware Proactive Agent in Multi-User Collaboration

ProActor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling Agents

ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs

PROPER Agents: Proactivity Driven Personalized Agents for Advancing Knowledge Gap Navigation

Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers

Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents

Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos

When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification

Communication Policy Evolution for Proactive LLM Agents

Designing for Doubt: The Case for Informed Abstention in Autonomous Agents

JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence

Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents

See, Infer, Intervene: Proactive World Modeling for Goal-Oriented Social Intelligence

Ψ-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues

An Empirical Study of Proactive Coding Assistants in Real-World Software Development

Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents

Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World

CogniFold: Always-On Proactive Memory via Cognitive Folding

Do Proactive Agents Need an LLM to Decide When to Act?

EgoPro-Bench: Benchmarking Personalized Proactive Interaction in Egocentric Video Streams

IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams

MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation

OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding

PACT: Proactive Asking for Continual Task Assistance in Human-Robot Collaboration

ProactBench: Beyond What The User Asked For

Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding

StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents

VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions

π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows

Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering

AURA: Always-On Understanding and Real-Time Assistance via Video Streams

From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench

Help Without Being Asked: A Deployed Proactive Agent System for On-Call Support with Continuous Self-Improvement

KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation

MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction

PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory

Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents

Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding

GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Tasks

PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents

Proact-VL: A Proactive VideoLLM for Real-Time AI Companions

ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models

ProEvent: An Event-centric Benchmark for Proactive Agents

PsyProbe: Proactive and Interpretable Dialogue through User State Modeling for Exploratory Counseling

StreamReady: Learning What to Answer and When in Long Streaming Videos

Exploring The Impact of Proactive Generative AI Agent Roles in Time-Sensitive Collaborative Problem-Solving Tasks

From Fragmentation to Integration: Exploring the Design Space of AI Agents for Human-as-the-Unit Privacy Management

ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices

ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Data

Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization

Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification

Developer Interaction Patterns with Proactive AI: A Five-Day Field Study

Long-term Task-oriented Agent: Proactive Long-term Intent Maintenance in Dynamic Environments

Proactivity-driven Personalized Agents for Advancing Human Learning through Engagement, Reflection, and Self-Efficacy

ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding

Value of Information: A Framework for Human–Agent Communication

ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems

StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos

Structured Uncertainty guided Clarification for LLM Agents

Training Proactive and Personalized LLM Agents

AgentFold: Long-Horizon Web Agents with Proactive Context Folding

Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents

Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety

Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video

ProMediate: A Simulation Testbed for Evaluating Proactive Mediation in Multi-Party Negotiation

PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents

ProPerSim: Developing Proactive and Personalized AI Assistants through User-Assistant Simulation

VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents

AppAgent-Pro: A Proactive GUI Agent System for Multidomain Information Integration and User Assistance

ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents

When not to help: planning for lasting human-AI collaboration

FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents

ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agent

ProMemAssist: Exploring Timely Proactive Assistance Through Working Memory Modeling in Multi-Modal Wearable Devices

Tunable LLM-based Proactive Recommendation Agent

Proactive Assistant Dialogue Generation from Streaming Egocentric Videos

ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions

PACE: Proactive Assistance in Human-Robot Collaboration Through Action-Completion Estimation

CodingGenie: A Proactive LLM-Powered Programming Assistant

OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts

Proactive Conversational AI: A Comprehensive Survey of Advancements and Opportunities

Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support

Mirai: A Wearable Proactive AI Inner-Voice for Contextual Nudging

WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatch

AiGet: Transforming Everyday Moments into Hidden Knowledge Discovery with AI Assistance on Smart Glasses

Proactive Conversational Agents with Inner Thoughts

ProTOD: Proactive Task-oriented Dialogue System Based on LLMs

When AI-Based Agents Are Proactive: Implications for Competence and System Satisfaction in Human-AI Collaboration

YETI: Proactive Interventions by Multimodal AI Agents in Augmented Reality Tasks

PCQPR: Proactive Conversational Question Planning with Reflection

Need Help? Designing Proactive AI Assistants for Programming

Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance

Redefining Proactivity for Information Seeking Dialogue

Satori: Towards Proactive AR Assistant with Belief-Desire-Intention User Modeling

AssistantX: An LLM-Powered Proactive Assistant in Collaborative Human-Populated Environments

Ask-before-Plan: Proactive Language Agents for Real-World Planning

Towards Human-centered Proactive Conversational Agents

Asking the Right Question at the Right Time: Human and Model Uncertainty Guidance to Ask Clarification Questions

ProMISe: A Proactive Multi-turn Dialogue Dataset for Information-seeking Intent Resolution