{"list":"other","total":58,"rows":[{"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":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504},{"id":"2501.04519","title":"rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking","created":"2025-01-08","cited_by_count":313},{"id":"2404.05427","title":"AutoCodeRover: Autonomous Program Improvement","created":"2024-04-08","cited_by_count":278},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228},{"id":"2407.01476","title":"Tree Search for Language Model Agents","created":"2024-07-01","cited_by_count":151},{"id":"2410.02089","title":"RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning","created":"2024-10-02","cited_by_count":151},{"id":"2410.06992","title":"SWE-Bench+: Enhanced Coding Benchmark for LLMs","created":"2024-10-09","cited_by_count":99},{"id":"2007.02863","title":"Counterfactual Data Augmentation using Locally Factored Dynamics","created":"2020-07-06","cited_by_count":93},{"id":"2501.05040","title":"SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution","created":"2025-01-09","cited_by_count":90},{"id":"2509.21240","title":"Tree Search for LLM Agent Reinforcement Learning","created":"2025-09-25","cited_by_count":79},{"id":"2508.14111","title":"From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery","created":"2025-08-18","cited_by_count":77},{"id":"2603.08754","title":"Hindsight Credit Assignment for Long-Horizon LLM Agents","created":"2026-03-07","cited_by_count":65},{"id":"2011.09464","title":"Counterfactual Credit Assignment in Model-Free Reinforcement Learning","created":"2020-11-18","cited_by_count":64},{"id":"2506.12928","title":"Scaling Test-time Compute for LLM Agents","created":"2025-06-15","cited_by_count":63},{"id":"2012.09092","title":"Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation","created":"2020-12-16","cited_by_count":59},{"id":"2406.01422","title":"Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration","created":"2024-06-03","cited_by_count":58},{"id":"2503.15223","title":"Are \"Solved Issues\" in SWE-bench Really Solved Correctly? An Empirical Study","created":"2025-03-19","cited_by_count":49},{"id":"2511.16108","title":"SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent","created":"2025-11-20","cited_by_count":48},{"id":"2408.14354","title":"SWE-bench-java: A GitHub Issue Resolving Benchmark for Java","created":"2024-08-26","cited_by_count":34},{"id":"2601.01426","title":"SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving","created":"2026-01-04","cited_by_count":31},{"id":"2502.20127","title":"SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning","created":"2025-02-27","cited_by_count":28},{"id":"2402.13188","title":"Question Calibration and Multi-Hop Modeling for Temporal Question Answering","created":"2024-02-20","cited_by_count":25},{"id":"2302.12530","title":"Dual Path Modeling for Semantic Matching by Perceiving Subtle Conflicts","created":"2023-02-24","cited_by_count":21},{"id":"2103.06224","title":"An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning","created":"2021-03-10","cited_by_count":20},{"id":"2510.01132","title":"A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning","created":"2025-10-01","cited_by_count":17},{"id":"2505.16975","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","created":"2025-05-22","cited_by_count":16},{"id":"2509.21486","title":"Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governance","created":"2025-09-25","cited_by_count":16},{"id":"2503.17551","title":"Audio-Enhanced Vision-Language Modeling with Latent Space Broadening for High Quality Data Expansion","created":"2025-03-21","cited_by_count":15},{"id":"2604.16529","title":"Scaling Test-Time Compute for Agentic Coding","created":"2026-04-16","cited_by_count":15},{"id":"2605.25492","title":"SafetyRepro: Configuration-Conditional Rank Instability on Alignment Benchmarks","created":"2026-05-25","cited_by_count":15},{"id":"2501.16154","title":"AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought","created":"2025-01-27","cited_by_count":14},{"id":"2603.00520","title":"SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark","created":"2026-02-28","cited_by_count":12},{"id":"2006.07200","title":"Learning to Communicate Using Counterfactual Reasoning","created":"2020-06-12","cited_by_count":9},{"id":"2507.14239","title":"CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation","created":"2025-07-17","cited_by_count":9},{"id":"2510.09988","title":"Unifying Tree Search Algorithm and Reward Design for LLM Reasoning: A Survey","created":"2025-10-11","cited_by_count":9},{"id":"2602.12342","title":"Intrinsic Credit Assignment for Long Horizon Interaction","created":"2026-02-12","cited_by_count":9},{"id":"2606.15127","title":"Beyond Accuracy: Measuring Bias Acknowledgment in Chain-of-Thought Reasoning for Responsible AI Evaluation","created":"2026-06-13","cited_by_count":9},{"id":"2508.19506","title":"Learning Game-Playing Agents with Generative Code Optimization","created":"2025-08-27","cited_by_count":8},{"id":"2509.02033","title":"StructCoh: Structured Contrastive Learning for Context-Aware Text Semantic Matching","created":"2025-09-02","cited_by_count":8},{"id":"2603.23994","title":"Understanding the Challenges in Iterative Generative Optimization with LLMs","created":"2026-03-25","cited_by_count":8},{"id":"2604.10079","title":"Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models","created":"2026-04-11","cited_by_count":8},{"id":"2412.15251","title":"IPS: In-Prompt Process Supervision for Short Video Content Moderation","created":"2024-12-15","cited_by_count":7},{"id":"2602.11767","title":"TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents","created":"2026-02-12","cited_by_count":7},{"id":"2604.10072","title":"Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty","created":"2026-04-11","cited_by_count":6},{"id":"2601.11311","title":"FORESTLLM: Large Language Models Make Random Forest Great on Few-shot Tabular Learning","created":"2026-01-16","cited_by_count":5},{"id":"2605.03314","title":"When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning","created":"2026-05-05","cited_by_count":5},{"id":"2604.12126","title":"Long-Horizon Plan Execution in Large Tool Spaces through Entropy-Guided Branching","created":"2026-04-13","cited_by_count":3},{"id":"2608.07596","title":"LIRA: Local Cross-Layer Information Routing for Vision-Language-Action Decoding","created":"2026-08-06","cited_by_count":3},{"id":"2601.20064","title":"DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation","created":"2026-01-27","cited_by_count":2},{"id":"2505.01548","title":"Learning Flow-Guided Registration for RGB-Event Semantic Segmentation","created":"2025-05-02","cited_by_count":1},{"id":"2602.07670","title":"Surprisal-Guided Selection: Compute-Optimal Test-Time Strategies for Execution-Grounded Code Generation","created":"2026-02-07","cited_by_count":1}],"next_cursor":null}