{"total":20,"rows":[{"id":"2507.20673","title":"Geometric-Mean Policy Optimization","created":"2025-07-28","cited_by_count":111,"area":"lr"},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2508.02511","title":"Test-time Prompt Intervention","created":"2025-08-04","cited_by_count":12,"area":"lr"},{"id":"2509.18849","title":"MAPO: Mixed Advantage Policy Optimization","created":"2025-09-23","cited_by_count":11,"area":"lr"},{"id":"2509.25160","title":"GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts","created":"2025-09-29","cited_by_count":8,"area":"lr"},{"id":"2601.11340","title":"Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models","created":"2026-01-16","cited_by_count":8,"area":"lr"},{"id":"2509.07558","title":"VL Norm: Rethink Loss Aggregation in RLVR","created":"2025-09-09","cited_by_count":4,"area":"lr"},{"id":"2510.04072","title":"Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"id":"2602.06453","title":"On the Plasticity and Stability for Post-Training Large Language Models","created":"2026-02-06","cited_by_count":4,"area":"lr"},{"id":"2511.14258","title":"Entropy-Guided Reasoning Compression","created":"2025-11-18","cited_by_count":3,"area":"lr"},{"id":"2605.24998","title":"Better, Faster: Harnessing Self-Improvement in Large Reasoning Models","created":"2026-05-24","cited_by_count":3,"area":"lr"},{"id":"2602.12113","title":"Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2601.22521","title":"One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.01198","title":"A State-Transition Framework for Efficient LLM Reasoning","created":"2026-02-01","cited_by_count":1,"area":"lr"},{"id":"2603.18656","title":"Balanced Thinking: Improving Chain of Thought Training in Vision Language Models","created":"2026-03-19","cited_by_count":1,"area":"lr"},{"id":"2604.16890","title":"Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2605.27293","title":"BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2607.09786","title":"Length Penalties Make Chain-of-Thought Less Monitorable","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2605.22211","title":"CLORE: Content-Level Optimization for Reasoning Efficiency","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2609.29664","title":"To Think or Not to Think: Allocating Reasoning Where It Helps","created":"2026-08-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}