{"total":19,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2510.00915","title":"Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers","created":"2025-10-01","cited_by_count":45,"area":"lr"},{"id":"2601.21821","title":"MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods","created":"2026-01-29","cited_by_count":30,"area":"lr"},{"id":"2510.23038","title":"Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning","created":"2025-10-27","cited_by_count":17,"area":"lr"},{"id":"2510.04265","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","created":"2025-10-05","cited_by_count":15,"area":"lr"},{"id":"2601.13606","title":"ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch","created":"2026-01-20","cited_by_count":10,"area":"lr"},{"id":"2602.15620","title":"STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens","created":"2026-02-17","cited_by_count":9,"area":"lr"},{"id":"2510.22543","title":"FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning","created":"2025-10-26","cited_by_count":7,"area":"lr"},{"id":"2509.24285","title":"SCI-Verifier: Scientific Verifier with Thinking","created":"2025-09-29","cited_by_count":6,"area":"lr"},{"id":"2511.14366","title":"ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning","created":"2025-11-18","cited_by_count":6,"area":"lr"},{"id":"2512.10756","title":"OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification","created":"2025-12-11","cited_by_count":4,"area":"lr"},{"id":"2510.11031","title":"LogiNumSynth: Synthesizing Joint Logical-Numerical Reasoning Problems for Language Models","created":"2025-10-13","cited_by_count":2,"area":"lr"},{"id":"2602.06795","title":"Generating Data-Driven Reasoning Rubrics for Domain-Adaptive Reward Modeling","created":"2026-02-06","cited_by_count":1,"area":"lr"},{"id":"2610.01352","title":"MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning","created":"2026-10-01","cited_by_count":1,"area":"lr"},{"id":"2604.02794","title":"CharTool: Tool-Integrated Visual Reasoning for Chart Understanding","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2608.25637","title":"AutoVerifier: Residual-Guided Non-Parametric Optimization for Reference-Based Answer Verification","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2609.12181","title":"Physics as the label for measuring and correcting materials reasoning in multimodal models","created":"2026-09-10","cited_by_count":0,"area":"lr"},{"id":"2609.27572","title":"DCRL: Decoupling and Coupling Reinforcement Learning via Policy-Reward Manifold Alignment","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2610.17824","title":"Checking the Checkers: A Synthesis of Verifier Noise and Robustness in RLVR","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}