{"total":16,"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":"2604.17892","title":"LEPO: Latent Reasoning Policy Optimization for Large Language Models","created":"2026-04-20","cited_by_count":4,"area":"lr"},{"id":"2606.13106","title":"Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning","created":"2026-06-11","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":"2608.01593","title":"Latent Thought Credit: Multi-Answer Credit Assignment for Latent Reasoning","created":"2026-08-03","cited_by_count":1,"area":"lr"},{"id":"2608.05541","title":"Hyper-ES: Effective Evolution Strategies for LLM Reasoning via Descent Direction Merging","created":"2026-08-06","cited_by_count":1,"area":"lr"},{"id":"2608.27351","title":"Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO","created":"2026-08-27","cited_by_count":1,"area":"lr"},{"id":"2605.09346","title":"RuPLaR : Efficient Latent Compression of LLM Reasoning Chains with Rule-Based Priors From Multi-Step to One-Step","created":"2026-05-10","cited_by_count":0,"area":"lr"},{"id":"2605.21654","title":"Value-Gradient Hypothesis of RL for LLMs","created":"2026-05-20","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":"2606.10768","title":"N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2607.20952","title":"The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoning","created":"2026-07-23","cited_by_count":0,"area":"lr"},{"id":"2608.31069","title":"A Model with No Head and Many Thoughts","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.02049","title":"The Dynamics of Continuous Mixture Collapse in Language Models","created":"2026-09-02","cited_by_count":0,"area":"lr"},{"id":"2609.38717","title":"Soft Spatial Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}