{"total":10,"rows":[{"id":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2510.23393","title":"The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation","created":"2025-10-27","cited_by_count":16,"area":null},{"id":"2510.03199","title":"Best-of-Majority: Minimax-Optimal Strategy for Pass@$k$ Inference Scaling","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2510.03777","title":"GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time","created":"2025-10-04","cited_by_count":5,"area":null},{"id":"2605.20854","title":"Regret Analysis of Retry-Based Bandits","created":"2026-05-20","cited_by_count":4,"area":null},{"id":"2608.13566","title":"Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2607.02390","title":"DecompRL: Solving Harder Problems by Learning Modular Code Generation","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2609.25575","title":"Direct Optimization of Generators for Search in Automated Theorem Proving","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.34992","title":"Composable Decoding on the Probability Simplex: Theory and Implementation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.17735","title":"Train for Many, Update with One: Improving Multi-Sample Reasoning via Fenchel-Bregman Posterior Learning","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}