{"total":20,"rows":[{"id":"2602.21492","title":"GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning","created":"2026-02-25","cited_by_count":12,"area":null},{"id":"2511.18491","title":"MindEval: Benchmarking Language Models on Multi-turn Mental Health Support","created":"2025-11-23","cited_by_count":10,"area":null},{"id":"2605.09808","title":"Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants","created":"2026-05-10","cited_by_count":10,"area":null},{"id":"2607.20734","title":"LLMs Get Lost in Evolving User Intent","created":"2026-07-22","cited_by_count":10,"area":null},{"id":"2601.04436","title":"Learning to Simulate Human Dialogue","created":"2026-01-07","cited_by_count":9,"area":null},{"id":"2603.05923","title":"Learning Next Action Predictors from Human-Computer Interaction","created":"2026-03-06","cited_by_count":7,"area":null},{"id":"2602.03429","title":"DiscoverLLM: From Executing Intents to Discovering Them","created":"2026-02-03","cited_by_count":6,"area":null},{"id":"2512.04068","title":"Learning Steerable Clarification Policies with Collaborative Self-play","created":"2025-12-03","cited_by_count":5,"area":null},{"id":"2606.23459","title":"TriggerBench: Investigating Prospective Memory for Large Language Models","created":"2026-06-22","cited_by_count":5,"area":null},{"id":"2603.23550","title":"Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction","created":"2026-03-21","cited_by_count":4,"area":null},{"id":"2605.20506","title":"Reinforcing Human Behavior Simulation via Verbal Feedback","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2602.04210","title":"Steering LLMs via Scalable Interactive Oversight","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2605.25680","title":"Simulating Human Memory with Language Models","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.04743","title":"TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2607.16352","title":"Clarify Before Executing: A Self-Evolving Agent for Resolving Intent Asymmetry in 3D Tool Orchestration","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2604.00414","title":"Decision-Centric Design for LLM Systems","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2609.35149","title":"From Migration to Calibration: Aligning Agents with Deployment Requirements","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37236","title":"Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38359","title":"Beyond Mode Collapse: Generating Diverse Synthetic Expert Conversations via Generative Flow Networks","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.13617","title":"Training User Simulators with Latent Intrinsic Feedback","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}