{"list":"other","total":60,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"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":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2507.18071","title":"Group Sequence Policy Optimization","created":"2025-07-24","cited_by_count":835},{"id":"2310.03714","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","created":"2023-10-05","cited_by_count":832},{"id":"2302.11382","title":"A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT","created":"2023-02-21","cited_by_count":619},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564},{"id":"2305.04091","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","created":"2023-05-06","cited_by_count":560},{"id":"2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","created":"2023-09-28","cited_by_count":551},{"id":"2507.19457","title":"GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning","created":"2025-07-25","cited_by_count":542},{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491},{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464},{"id":"2402.07927","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","created":"2024-02-05","cited_by_count":431},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2309.12288","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","created":"2023-09-21","cited_by_count":407},{"id":"2408.08435","title":"Automated Design of Agentic Systems","created":"2024-08-15","cited_by_count":407},{"id":"2504.11536","title":"ReTool: Reinforcement Learning for Strategic Tool Use in LLMs","created":"2025-04-15","cited_by_count":392},{"id":"2503.04697","title":"L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning","created":"2025-03-06","cited_by_count":384},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384},{"id":"2504.13958","title":"ToolRL: Reward is All Tool Learning Needs","created":"2025-04-16","cited_by_count":362},{"id":"2406.07496","title":"TextGrad: Automatic \"Differentiation\" via Text","created":"2024-06-11","cited_by_count":273},{"id":"2409.12183","title":"To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning","created":"2024-09-18","cited_by_count":263},{"id":"2507.02833","title":"Generalizing Verifiable Instruction Following","created":"2025-07-03","cited_by_count":194},{"id":"2504.01296","title":"ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning","created":"2025-04-02","cited_by_count":192},{"id":"2404.03683","title":"Stream of Search (SoS): Learning to Search in Language","created":"2024-04-01","cited_by_count":145},{"id":"2504.07912","title":"Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining","created":"2025-04-10","cited_by_count":129},{"id":"2312.04474","title":"Chain of Code: Reasoning with a Language Model-Augmented Code Emulator","created":"2023-12-07","cited_by_count":123},{"id":"2402.03620","title":"Self-Discover: Large Language Models Self-Compose Reasoning Structures","created":"2024-02-06","cited_by_count":110},{"id":"2502.01600","title":"Reinforcement Learning for Long-Horizon Interactive LLM Agents","created":"2025-02-03","cited_by_count":108},{"id":"2307.08689","title":"COLLIE: Systematic Construction of Constrained Text Generation Tasks","created":"2023-07-17","cited_by_count":70},{"id":"2403.15452","title":"What Are Tools Anyway? A Survey from the Language Model Perspective","created":"2024-03-18","cited_by_count":54},{"id":"2407.10930","title":"Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together","created":"2024-07-15","cited_by_count":40},{"id":"2502.06855","title":"Self-Supervised Prompt Optimization","created":"2025-02-07","cited_by_count":37},{"id":"2312.08566","title":"Learning adaptive planning representations with natural language guidance","created":"2023-12-13","cited_by_count":36},{"id":"2508.13141","title":"OptimalThinkingBench: Evaluating Over and Underthinking in LLMs","created":"2025-08-18","cited_by_count":35},{"id":"2403.08140","title":"BAGEL: Bootstrapping Agents by Guiding Exploration with Language","created":"2024-03-12","cited_by_count":34},{"id":"2406.15708","title":"Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization","created":"2024-06-22","cited_by_count":29},{"id":"2102.03406","title":"Symbolic Behaviour in Artificial Intelligence","created":"2021-02-05","cited_by_count":25},{"id":"2410.03524","title":"Steering Large Language Models between Code Execution and Textual Reasoning","created":"2024-10-04","cited_by_count":24},{"id":"2403.02993","title":"Localized Zeroth-Order Prompt Optimization","created":"2024-03-05","cited_by_count":23},{"id":"2504.07081","title":"Self-Steering Language Models","created":"2025-04-09","cited_by_count":13},{"id":"2507.05707","title":"Agentic-R1: Distilled Dual-Strategy Reasoning","created":"2025-07-08","cited_by_count":3}],"next_cursor":null}