{"total":16,"rows":[{"id":"2511.06411","title":"SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization","created":"2025-11-09","cited_by_count":21,"area":"lr"},{"id":"2511.16231","title":"Pass@k Metric for RLVR: A Diagnostic Tool of Exploration, But Not an Objective","created":"2025-11-20","cited_by_count":12,"area":"lr"},{"id":"2603.26535","title":"PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization","created":"2026-03-27","cited_by_count":11,"area":"lr"},{"id":"2605.06094","title":"VISD: Enhancing Video Reasoning via Structured Self-Distillation","created":"2026-05-07","cited_by_count":10,"area":"lr"},{"id":"2602.21189","title":"Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training","created":"2026-02-24","cited_by_count":8,"area":"lr"},{"id":"2605.00380","title":"ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning","created":"2026-05-01","cited_by_count":6,"area":"lr"},{"id":"2604.12632","title":"Calibration-Aware Policy Optimization for Reasoning LLMs","created":"2026-04-14","cited_by_count":5,"area":"lr"},{"id":"2603.18886","title":"Reasoning over mathematical objects: on-policy reward modeling and test time aggregation","created":"2026-03-19","cited_by_count":3,"area":"lr"},{"id":"2604.14142","title":"From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space","created":"2026-04-15","cited_by_count":3,"area":"lr"},{"id":"2606.06080","title":"On Advantage Estimates for Max@K Policy Gradients","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2602.04265","title":"Boosting LLM Reasoning via Human-Inspired Reward Shaping","created":"2026-02-04","cited_by_count":1,"area":"lr"},{"id":"2604.04894","title":"Asymmetric Advantage Modulation Calibrates Entropy Dynamics in RLVR","created":"2026-04-06","cited_by_count":1,"area":"lr"},{"id":"2608.02149","title":"Beyond the Mean: Multi-Moment Policy Optimization for LLM Reasoning","created":"2026-08-03","cited_by_count":1,"area":"lr"},{"id":"2608.03467","title":"When Correct Solutions Repeat: Rarity-Aware Credit Redistribution for GRPO","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"id":"2609.25773","title":"Video-HopChain: Multi-Hop Questions and Confidence-Gated Exploration for Video Reasoning Models","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.31571","title":"Strategically Diverse Sampling for Self-Training","created":"2026-09-25","cited_by_count":0,"area":"lr"}],"next_cursor":null}