{"total":15,"rows":[{"id":"2305.00633","title":"Self-Evaluation Guided Beam Search for Reasoning","created":"2023-05-01","cited_by_count":196,"area":"lr"},{"id":"2502.12215","title":"Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?","created":"2025-02-17","cited_by_count":70,"area":"lr"},{"id":"2502.05234","title":"Optimizing Temperature for Language Models with Multi-Sample Inference","created":"2025-02-07","cited_by_count":33,"area":"lr"},{"id":"2501.08248","title":"Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models","created":"2025-01-14","cited_by_count":11,"area":"lr"},{"id":"2509.17570","title":"Asking a Language Model for Diverse Responses","created":"2025-09-22","cited_by_count":9,"area":"lr"},{"id":"2502.19279","title":"CritiQ: Mining Data Quality Criteria from Human Preferences","created":"2025-02-26","cited_by_count":6,"area":"lr"},{"id":"2407.03951","title":"Uncertainty-Guided Likelihood Tree Search","created":"2024-07-04","cited_by_count":4,"area":"lr"},{"id":"2602.01698","title":"Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2506.04708","title":"Accelerated Test-Time Scaling with Model-Free Speculative Sampling","created":"2025-06-05","cited_by_count":2,"area":"lr"},{"id":"2604.18002","title":"Neural Garbage Collection: Learning to Forget while Learning to Reason","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2509.23196","title":"From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMs","created":"2025-09-27","cited_by_count":1,"area":"lr"},{"id":"2604.20500","title":"Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees","created":"2026-04-22","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"},{"id":"2605.26385","title":"Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2610.03361","title":"Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}