{"total":17,"rows":[{"id":"2601.05242","title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization","created":"2026-01-08","cited_by_count":193,"area":"lr"},{"id":"2508.09726","title":"Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning","created":"2025-08-13","cited_by_count":75,"area":"lr"},{"id":"2508.02120","title":"Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models","created":"2025-08-04","cited_by_count":37,"area":"lr"},{"id":"2512.21540","title":"Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model","created":"2025-12-25","cited_by_count":13,"area":"lr"},{"id":"2509.25426","title":"RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs","created":"2025-09-29","cited_by_count":6,"area":"lr"},{"id":"2509.25827","title":"Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling","created":"2025-09-30","cited_by_count":4,"area":"lr"},{"id":"2603.12372","title":"Efficient Reasoning with Balanced Thinking","created":"2026-03-12","cited_by_count":4,"area":"lr"},{"id":"2510.23486","title":"Learning to Reason Efficiently with Discounted Reinforcement Learning","created":"2025-10-27","cited_by_count":3,"area":"lr"},{"id":"2606.22716","title":"Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards","created":"2026-06-21","cited_by_count":3,"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":"2605.07316","title":"Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.19639","title":"Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2602.00760","title":"APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"id":"2603.18533","title":"Balancing the Reasoning Load: Difficulty-Differentiated Policy Optimization with Length Redistribution for Efficient and Robust Reinforcement Learning","created":"2026-03-19","cited_by_count":0,"area":"lr"},{"id":"2605.22211","title":"CLORE: Content-Level Optimization for Reasoning Efficiency","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2606.19927","title":"CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2607.21793","title":"QLPO: Quadrant-weighted Sampling for Length-aware Policy Optimization","created":"2026-07-23","cited_by_count":0,"area":"lr"}],"next_cursor":null}