{"list":"other","total":158,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2310.08560","title":"MemGPT: Towards LLMs as Operating Systems","created":"2023-10-12","cited_by_count":1389},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"id":"2502.12110","title":"A-MEM: Agentic Memory for LLM Agents","created":"2025-02-17","cited_by_count":1063},{"id":"2312.08935","title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","created":"2023-12-14","cited_by_count":928},{"id":"2410.10813","title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","created":"2024-10-14","cited_by_count":707},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668},{"id":"2504.12516","title":"BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents","created":"2025-04-16","cited_by_count":647},{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"id":"2503.13657","title":"Why Do Multi-Agent LLM Systems Fail?","created":"2025-03-17","cited_by_count":604},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571},{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491},{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485},{"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":"2501.13956","title":"Zep: A Temporal Knowledge Graph Architecture for Agent Memory","created":"2025-01-20","cited_by_count":400},{"id":"2510.04618","title":"Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models","created":"2025-10-06","cited_by_count":398},{"id":"2306.05301","title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","created":"2023-06-08","cited_by_count":393},{"id":"2504.11536","title":"ReTool: Reinforcement Learning for Strategic Tool Use in LLMs","created":"2025-04-15","cited_by_count":392},{"id":"2009.03393","title":"Generative Language Modeling for Automated Theorem Proving","created":"2020-09-07","cited_by_count":388},{"id":"2409.07429","title":"Agent Workflow Memory","created":"2024-09-11","cited_by_count":383},{"id":"2303.10512","title":"AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning","created":"2023-03-18","cited_by_count":357},{"id":"2503.05592","title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","created":"2025-03-07","cited_by_count":336},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328},{"id":"2512.13564","title":"Memory in the Age of AI Agents","created":"2025-12-15","cited_by_count":303},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"id":"2305.17144","title":"Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory","created":"2023-05-25","cited_by_count":289},{"id":"2504.21801","title":"DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition","created":"2025-04-30","cited_by_count":287},{"id":"2504.03160","title":"DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments","created":"2025-04-04","cited_by_count":286},{"id":"2509.25140","title":"ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory","created":"2025-09-29","cited_by_count":284},{"id":"2504.10458","title":"GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents","created":"2025-04-14","cited_by_count":244},{"id":"2502.14802","title":"From RAG to Memory: Non-Parametric Continual Learning for Large Language Models","created":"2025-02-20","cited_by_count":231},{"id":"2508.05004","title":"R-Zero: Self-Evolving Reasoning LLM from Zero Data","created":"2025-08-07","cited_by_count":228},{"id":"2311.01455","title":"RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation","created":"2023-11-02","cited_by_count":218},{"id":"2505.04588","title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","created":"2025-05-07","cited_by_count":208},{"id":"2402.07456","title":"OS-Copilot: Towards Generalist Computer Agents with Self-Improvement","created":"2024-02-12","cited_by_count":205},{"id":"2508.06600","title":"BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent","created":"2025-08-08","cited_by_count":200},{"id":"2507.02833","title":"Generalizing Verifiable Instruction Following","created":"2025-07-03","cited_by_count":194},{"id":"2504.07079","title":"SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills","created":"2025-04-09","cited_by_count":192},{"id":"2508.15144","title":"Mobile-Agent-v3: Fundamental Agents for GUI Automation","created":"2025-08-21","cited_by_count":190},{"id":"2410.08164","title":"Agent S: An Open Agentic Framework that Uses Computers Like a Human","created":"2024-10-10","cited_by_count":187},{"id":"2504.11354","title":"Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning","created":"2025-04-15","cited_by_count":180},{"id":"2504.07952","title":"Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory","created":"2025-04-10","cited_by_count":163},{"id":"2503.19470","title":"ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning","created":"2025-03-25","cited_by_count":161},{"id":"2508.03613","title":"Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction","created":"2025-08-05","cited_by_count":154},{"id":"2410.02089","title":"RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning","created":"2024-10-02","cited_by_count":151},{"id":"1803.04585","title":"Categorizing Variants of Goodhart's Law","created":"2018-03-13","cited_by_count":149},{"id":"2402.09727","title":"A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts","created":"2024-02-15","cited_by_count":146},{"id":"2306.03901","title":"ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory","created":"2023-06-06","cited_by_count":140},{"id":"2404.06474","title":"Autonomous Evaluation and Refinement of Digital Agents","created":"2024-04-09","cited_by_count":137},{"id":"2310.05029","title":"Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading","created":"2023-10-08","cited_by_count":133},{"id":"2508.16153","title":"Memento: Fine-tuning LLM Agents without Fine-tuning LLMs","created":"2025-08-22","cited_by_count":127},{"id":"2502.18443","title":"olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models","created":"2025-02-25","cited_by_count":125},{"id":"2504.15965","title":"From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs","created":"2025-04-22","cited_by_count":124},{"id":"2506.20670","title":"MMSearch-R1: Incentivizing LMMs to Search","created":"2025-06-25","cited_by_count":124},{"id":"2403.03186","title":"Cradle: Empowering Foundation Agents Towards General Computer Control","created":"2024-03-05","cited_by_count":117},{"id":"2010.14603","title":"Learning to be Safe: Deep RL with a Safety Critic","created":"2020-10-27","cited_by_count":116},{"id":"2504.06821","title":"Inducing Programmatic Skills for Agentic Tasks","created":"2025-04-09","cited_by_count":111},{"id":"2508.03680","title":"Agent Lightning: Train ANY AI Agents with Reinforcement Learning","created":"2025-08-05","cited_by_count":109},{"id":"2502.05589","title":"On Memory Construction and Retrieval for Personalized Conversational Agents","created":"2025-02-08","cited_by_count":105},{"id":"1709.04555","title":"Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network","created":"2017-09-13","cited_by_count":103},{"id":"2508.06433","title":"Memp: Exploring Agent Procedural Memory","created":"2025-08-08","cited_by_count":103},{"id":"2407.04363","title":"AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents","created":"2024-07-05","cited_by_count":102},{"id":"2507.23726","title":"Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving","created":"2025-07-31","cited_by_count":101},{"id":"2304.13343","title":"SCM: Enhancing Large Language Model with Self-Controlled Memory Framework","created":"2023-04-26","cited_by_count":98},{"id":"2308.08239","title":"MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation","created":"2023-08-16","cited_by_count":97},{"id":"2407.18416","title":"PersonaGym: Evaluating Persona Agents and LLMs","created":"2024-07-25","cited_by_count":97},{"id":"2509.01055","title":"VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use","created":"2025-09-01","cited_by_count":96},{"id":"2510.18874","title":"Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting","created":"2025-10-21","cited_by_count":94},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91},{"id":"2502.12659","title":"The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1","created":"2025-02-18","cited_by_count":91},{"id":"1812.01070","title":"Learning Multimodal Graph-to-Graph Translation for Molecular Optimization","created":"2018-12-03","cited_by_count":88},{"id":"2502.18770","title":"Reward Shaping to Mitigate Reward Hacking in RLHF","created":"2025-02-26","cited_by_count":88},{"id":"2505.15107","title":"StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization","created":"2025-05-21","cited_by_count":88},{"id":"2412.16075","title":"Formal Mathematical Reasoning: A New Frontier in AI","created":"2024-12-20","cited_by_count":81},{"id":"2505.12370","title":"Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning","created":"2025-05-18","cited_by_count":81},{"id":"2410.14052","title":"From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs","created":"2024-10-17","cited_by_count":79},{"id":"2505.15810","title":"GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents","created":"2025-05-21","cited_by_count":74},{"id":"2512.10696","title":"Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution","created":"2025-12-11","cited_by_count":73},{"id":"2510.05592","title":"In-the-Flow Agentic System Optimization for Effective Planning and Tool Use","created":"2025-10-07","cited_by_count":72},{"id":"2410.14803","title":"DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents","created":"2024-10-18","cited_by_count":68},{"id":"2504.08600","title":"SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning","created":"2025-04-11","cited_by_count":68},{"id":"2505.00024","title":"Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning","created":"2025-04-25","cited_by_count":68},{"id":"2305.14322","title":"RET-LLM: Towards a General Read-Write Memory for Large Language Models","created":"2023-05-23","cited_by_count":64},{"id":"2311.08719","title":"Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory","created":"2023-11-15","cited_by_count":64},{"id":"2510.23595","title":"Multi-Agent Evolve: LLM Self-Improve through Co-evolution","created":"2025-10-27","cited_by_count":60},{"id":"2404.12534","title":"Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean","created":"2024-04-18","cited_by_count":58},{"id":"2510.01346","title":"Aristotle: IMO-level Automated Theorem Proving","created":"2025-10-01","cited_by_count":58},{"id":"2502.13295","title":"Demonstrating specification gaming in reasoning models","created":"2025-02-18","cited_by_count":56}],"next_cursor":"100"}