{"total":15,"rows":[{"id":"2505.05408","title":"Crosslingual Reasoning through Test-Time Scaling","created":"2025-05-08","cited_by_count":46,"area":"lr"},{"id":"2505.13988","title":"The Hallucination Tax of Reinforcement Finetuning","created":"2025-05-20","cited_by_count":40,"area":"lr"},{"id":"2507.15849","title":"The Impact of Language Mixing on Bilingual LLM Reasoning","created":"2025-07-21","cited_by_count":12,"area":"lr"},{"id":"2506.09967","title":"Resa: Transparent Reasoning Models via SAEs","created":"2025-06-11","cited_by_count":6,"area":"lr"},{"id":"2507.18014","title":"Predictive Scaling Laws for Efficient GRPO Training of Large Reasoning Models","created":"2025-07-24","cited_by_count":6,"area":"lr"},{"id":"2603.04124","title":"BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning","created":"2026-03-04","cited_by_count":4,"area":"lr"},{"id":"2605.06241","title":"Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning","created":"2026-05-07","cited_by_count":3,"area":"lr"},{"id":"2601.06677","title":"Plasticity vs. Rigidity: The Impact of Low-Rank Adapters on Reasoning on a Micro-Budget","created":"2026-01-10","cited_by_count":1,"area":"lr"},{"id":"2604.18936","title":"Fine-Tuning Small Reasoning Models for Quantum Field Theory","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2505.17794","title":"RECIPE-TKG: From Sparse History to Structured Reasoning for LLM-based Temporal Knowledge Graph Completion","created":"2025-05-23","cited_by_count":0,"area":"lr"},{"id":"2603.16867","title":"Efficient Reasoning on the Edge","created":"2026-03-17","cited_by_count":0,"area":"lr"},{"id":"2607.18006","title":"MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2607.27787","title":"LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2609.39321","title":"GRPO Training Dynamics for Small Language Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.16489","title":"Growing and Transferring Pathways for LLM Reinforcement Learning","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}