{"total":8,"rows":[{"id":"2607.21051","title":"Sample-Efficient Learning from Agent Experience","created":"2026-07-23","cited_by_count":3,"area":null},{"id":"2609.15972","title":"Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2605.19354","title":"Next-Acceleration-Scale Prediction for Autoregressive MRI Reconstruction","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2607.05346","title":"OptiAgent: End-to-End Optimization Modeling via Multi-Agent Iterative Refinement","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.32201","title":"Instruct, Not Answer: Using Instruction Privileges in On-Policy Context Distillation","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33417","title":"Grounding Memory Summarization in Utility Intent","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.08781","title":"IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.20261","title":"Harness Policy Distillation: Aligning Agent Policies with Runtime Semantics","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}