Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents
cs.AI, cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Project page: https://dolev31
Terminology
Sources
- gpt-oss-120b & gpt-oss-20b Model Card
- Agentic Coding Needs Proactivity, Not Just Autonomy
- VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions
- CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrieval
- Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity
- Balancing Autonomy and Alignment: A Multi-Dimensional Taxonomy for Autonomous LLM-powered Multi-Agent Architectures
- ProactBench: Beyond What The User Asked For
- VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild
- Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
- Length Desensitization in Direct Preference Optimization
- Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations
- PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering
- Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants
- Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias
- UserBench: An Interactive Gym Environment for User-Centric Agents
- UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
- Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation
- Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation
- ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Data
- When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection