{"total":15,"rows":[{"id":"2604.27998","title":"Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning","created":"2026-04-30","cited_by_count":10,"area":"lr"},{"id":"2602.01705","title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2606.06447","title":"Latent Reasoning with Normalizing Flows","created":"2026-06-04","cited_by_count":4,"area":"lr"},{"id":"2604.26940","title":"Select to Think: Unlocking SLM Potential with Local Sufficiency","created":"2026-04-29","cited_by_count":3,"area":"lr"},{"id":"2605.27255","title":"Pair-In, Pair-Out: Latent Multi-Token Prediction for Efficient LLMs","created":"2026-05-26","cited_by_count":2,"area":"lr"},{"id":"2606.25354","title":"Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing","created":"2026-06-24","cited_by_count":2,"area":"lr"},{"id":"2607.16972","title":"Training Continuous Chain of Thought Models: A Tale of Two Regimes","created":"2026-07-18","cited_by_count":2,"area":"lr"},{"id":"2607.18264","title":"MUX: Continuous Reasoning via Multiplexed Tokens","created":"2026-05-19","cited_by_count":2,"area":"lr"},{"id":"2605.02263","title":"Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning","created":"2026-05-04","cited_by_count":1,"area":"lr"},{"id":"2608.01593","title":"Latent Thought Credit: Multi-Answer Credit Assignment for Latent Reasoning","created":"2026-08-03","cited_by_count":1,"area":"lr"},{"id":"2605.11726","title":"Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.24331","title":"CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning","created":"2026-05-23","cited_by_count":0,"area":"lr"},{"id":"2606.05859","title":"TARPO: Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization","created":"2026-06-04","cited_by_count":0,"area":"lr"},{"id":"2606.13862","title":"SuperThoughts: Reasoning Tokens in Superposition","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2609.39294","title":"ANI: Adaptive Numerical Injection for Unifying Semantic and Arithmetic Representations in Numerical Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}