{"total":17,"rows":[{"id":"2509.15194","title":"Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation","created":"2025-09-18","cited_by_count":45,"area":null},{"id":"2607.08964","title":"Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading","created":"2026-07-09","cited_by_count":31,"area":null},{"id":"2509.25760","title":"TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning","created":"2025-09-30","cited_by_count":27,"area":null},{"id":"2608.05466","title":"Recursive Synthesis for Long-Horizon Terminal Tasks","created":"2026-08-05","cited_by_count":19,"area":null},{"id":"2511.15700","title":"First Frame Is the Place to Go for Video Content Customization","created":"2025-11-19","cited_by_count":12,"area":null},{"id":"2601.16093","title":"SAMTok: Representing Any Mask with Two Words","created":"2026-01-22","cited_by_count":11,"area":null},{"id":"2512.23244","title":"ViLaCD-R1: A Vision-Language Framework for Semantic Change Detection in Remote Sensing","created":"2025-12-29","cited_by_count":3,"area":null},{"id":"2604.02467","title":"VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation","created":"2026-04-02","cited_by_count":3,"area":null},{"id":"2605.13467","title":"PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2605.21931","title":"EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2510.22784","title":"PIP-LLM: Integrating PDDL-Integer Programming with LLMs for Coordinating Multi-Robot Teams Using Natural Language","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2603.01993","title":"Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detection","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2602.02444","title":"RANKVIDEO: Reasoning Reranking for Text-to-Video Retrieval","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2601.11178","title":"TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2602.04763","title":"Active Asymmetric Multi-Agent Multimodal Learning under Uncertainty","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2610.05425","title":"Unmentioned Checklist Findings Change How Reinforcement Learning Appears to Improve Chest Radiograph Report Checking","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}