{"total":16,"rows":[{"id":"2502.05234","title":"Optimizing Temperature for Language Models with Multi-Sample Inference","created":"2025-02-07","cited_by_count":33,"area":"lr"},{"id":"2503.03746","title":"Process-based Self-Rewarding Language Models","created":"2025-03-05","cited_by_count":22,"area":"lr"},{"id":"2502.19830","title":"Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation","created":"2025-02-27","cited_by_count":11,"area":"lr"},{"id":"2510.05251","title":"Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning","created":"2025-10-06","cited_by_count":10,"area":"lr"},{"id":"2510.08892","title":"Exploring Multi-Temperature Strategies for Token- and Rollout-Level Control in RLVR","created":"2025-10-10","cited_by_count":8,"area":"lr"},{"id":"2505.19250","title":"PATS: Process-Level Adaptive Thinking Mode Switching","created":"2025-05-25","cited_by_count":6,"area":"lr"},{"id":"2510.05987","title":"Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs","created":"2025-10-07","cited_by_count":5,"area":"lr"},{"id":"2602.04208","title":"SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models","created":"2026-02-04","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":"2510.26519","title":"Think Outside the Policy: In-Context Steered Policy Optimization","created":"2025-10-30","cited_by_count":3,"area":"lr"},{"id":"2602.02443","title":"Certain Head, Uncertain Tail: Expert-Sample for Test-Time Scaling in Fine-Grained MoE","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2608.29988","title":"AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning","created":"2026-08-30","cited_by_count":2,"area":"lr"},{"id":"2405.14075","title":"$T^2$ of Thoughts: Temperature Tree Elicits Reasoning in Large Language Models","created":"2024-05-23","cited_by_count":1,"area":"lr"},{"id":"2601.22536","title":"Decoding in Geometry: Alleviating Embedding-Space Crowding for Complex Reasoning","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2606.00755","title":"Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning","created":"2026-05-30","cited_by_count":1,"area":"lr"},{"id":"2604.24927","title":"Large Language Models Explore by Latent Distilling","created":"2026-04-27","cited_by_count":0,"area":"lr"}],"next_cursor":null}