{"list":"other","total":56,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2402.14008","title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems","created":"2024-02-21","cited_by_count":1136},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"2409.12122","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","created":"2024-09-18","cited_by_count":1090},{"id":"2507.18071","title":"Group Sequence Policy Optimization","created":"2025-07-24","cited_by_count":835},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"id":"2007.08199","title":"Learning from Noisy Labels with Deep Neural Networks: A Survey","created":"2020-07-16","cited_by_count":582},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"2503.18892","title":"SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild","created":"2025-03-24","cited_by_count":511},{"id":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2310.17631","title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges","created":"2023-10-26","cited_by_count":367},{"id":"2507.17746","title":"Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains","created":"2025-07-23","cited_by_count":366},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332},{"id":"2402.10669","title":"Humans or LLMs as the Judge? A Study on Judgement Biases","created":"2024-02-16","cited_by_count":323},{"id":"2410.12784","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","created":"2024-10-16","cited_by_count":318},{"id":"1703.00887","title":"How to Escape Saddle Points Efficiently","created":"2017-03-02","cited_by_count":285},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238},{"id":"2506.10947","title":"Spurious Rewards: Rethinking Training Signals in RLVR","created":"2025-06-12","cited_by_count":209},{"id":"2406.12624","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","created":"2024-06-18","cited_by_count":205},{"id":"2404.12272","title":"Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences","created":"2024-04-18","cited_by_count":144},{"id":"1710.06451","title":"A Bayesian Perspective on Generalization and Stochastic Gradient Descent","created":"2017-10-17","cited_by_count":135},{"id":"2507.18624","title":"Checklists Are Better Than Reward Models For Aligning Language Models","created":"2025-07-24","cited_by_count":128},{"id":"1802.06175","title":"An Alternative View: When Does SGD Escape Local Minima?","created":"2018-02-17","cited_by_count":115},{"id":"1810.01032","title":"Reinforcement Learning with Perturbed Rewards","created":"2018-10-02","cited_by_count":79},{"id":"1705.08417","title":"Reinforcement Learning with a Corrupted Reward Channel","created":"2017-05-23","cited_by_count":70},{"id":"2508.16949","title":"Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning","created":"2025-08-23","cited_by_count":63},{"id":"2511.10507","title":"AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following","created":"2025-11-13","cited_by_count":51},{"id":"2510.00915","title":"Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers","created":"2025-10-01","cited_by_count":45},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27},{"id":"2505.22203","title":"From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning","created":"2025-05-28","cited_by_count":22},{"id":"2505.14625","title":"TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning","created":"2025-05-20","cited_by_count":21},{"id":"2603.25133","title":"RubricEval: A Rubric-Level Meta-Evaluation Benchmark for LLM Judges in Instruction Following","created":"2026-03-26","cited_by_count":20},{"id":"2510.18924","title":"Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients","created":"2025-10-21","cited_by_count":13},{"id":"2603.12246","title":"Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training","created":"2026-03-12","cited_by_count":13},{"id":"2511.07738","title":"From Exploration to Exploitation: A Two-Stage Entropy RLVR Approach for Noise-Tolerant MLLM Training","created":"2025-11-11","cited_by_count":5},{"id":"2603.16140","title":"Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards","created":"2026-03-17","cited_by_count":5},{"id":"2601.01904","title":"Evaluating Feature Dependent Noise in Preference-based Reinforcement Learning","created":"2026-01-05","cited_by_count":2}],"next_cursor":null}