{"list":"other","total":95,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2310.08560","title":"MemGPT: Towards LLMs as Operating Systems","created":"2023-10-12","cited_by_count":1389},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"2305.19118","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","created":"2023-05-30","cited_by_count":1011},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"2305.10250","title":"MemoryBank: Enhancing Large Language Models with Long-Term Memory","created":"2023-05-17","cited_by_count":556},{"id":"2404.13208","title":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions","created":"2024-04-19","cited_by_count":493},{"id":"1708.08611","title":"Safe Reinforcement Learning via Shielding","created":"2017-08-29","cited_by_count":449},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2510.04618","title":"Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models","created":"2025-10-06","cited_by_count":398},{"id":"1705.08551","title":"Safe Model-based Reinforcement Learning with Stability Guarantees","created":"2017-05-23","cited_by_count":366},{"id":"2401.05561","title":"TrustLLM: Trustworthiness in Large Language Models","created":"2024-01-10","cited_by_count":285},{"id":"2509.25140","title":"ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory","created":"2025-09-29","cited_by_count":284},{"id":"1711.02827","title":"Inverse Reward Design","created":"2017-11-08","cited_by_count":249},{"id":"2507.02259","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","created":"2025-07-03","cited_by_count":246},{"id":"2403.17134","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","created":"2024-03-25","cited_by_count":232},{"id":"2310.17884","title":"Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory","created":"2023-10-27","cited_by_count":230},{"id":"2409.00138","title":"PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action","created":"2024-08-29","cited_by_count":171},{"id":"1506.02188","title":"Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach","created":"2015-06-06","cited_by_count":170},{"id":"2505.10468","title":"AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges","created":"2025-05-15","cited_by_count":169},{"id":"2012.08630","title":"Open Problems in Cooperative AI","created":"2020-12-15","cited_by_count":168},{"id":"2008.06388","title":"Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans","created":"2020-08-14","cited_by_count":158},{"id":"1712.06924","title":"Safe Policy Improvement with Baseline Bootstrapping","created":"2017-12-19","cited_by_count":144},{"id":"2306.03901","title":"ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory","created":"2023-06-06","cited_by_count":140},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123},{"id":"2506.07398","title":"G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems","created":"2025-06-09","cited_by_count":122},{"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":"2402.06627","title":"Feedback Loops With Language Models Drive In-Context Reward Hacking","created":"2024-02-09","cited_by_count":77},{"id":"1502.03919","title":"Policy Gradient for Coherent Risk Measures","created":"2015-02-13","cited_by_count":76},{"id":"2502.15657","title":"Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?","created":"2025-02-21","cited_by_count":75},{"id":"2502.11528","title":"A Survey of Personalized Large Language Models: Progress and Future Directions","created":"2025-02-17","cited_by_count":71},{"id":"2403.02817","title":"Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications","created":"2024-03-05","cited_by_count":59},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58},{"id":"2507.22844","title":"RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents","created":"2025-07-30","cited_by_count":58},{"id":"2510.25445","title":"Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions","created":"2025-10-29","cited_by_count":48},{"id":"2402.02025","title":"A Survey of Constraint Formulations in Safe Reinforcement Learning","created":"2024-02-03","cited_by_count":44},{"id":"2505.14534","title":"Lessons from Defending Gemini Against Indirect Prompt Injections","created":"2025-05-20","cited_by_count":43},{"id":"2405.09591","title":"A Comprehensive Survey on Data Augmentation","created":"2024-05-15","cited_by_count":40},{"id":"2408.02373","title":"Operationalizing Contextual Integrity in Privacy-Conscious Assistants","created":"2024-08-05","cited_by_count":37},{"id":"2409.13903","title":"CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data","created":"2024-09-20","cited_by_count":37},{"id":"2410.06209","title":"LeanAgent: Lifelong Learning for Formal Theorem Proving","created":"2024-10-08","cited_by_count":35},{"id":"2006.16471","title":"Object Detection Under Rainy Conditions for Autonomous Vehicles: A Review of State-of-the-Art and Emerging Techniques","created":"2020-06-30","cited_by_count":31},{"id":"2510.06186","title":"RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback","created":"2025-10-07","cited_by_count":25},{"id":"2408.03624","title":"AgentsCoMerge: Large Language Model Empowered Collaborative Decision Making for Ramp Merging","created":"2024-08-07","cited_by_count":22},{"id":"2504.00914","title":"On the Robustness of Agentic Function Calling","created":"2025-04-01","cited_by_count":19},{"id":"2505.17342","title":"A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safety","created":"2025-05-22","cited_by_count":13},{"id":"2510.08308","title":"First Try Matters: Revisiting the Role of Reflection in Reasoning Models","created":"2025-10-09","cited_by_count":12},{"id":"2205.12753","title":"An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation","created":"2022-05-25","cited_by_count":11},{"id":"2510.00307","title":"BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models","created":"2025-09-30","cited_by_count":11},{"id":"2410.04753","title":"ImProver: Agent-Based Automated Proof Optimization","created":"2024-10-07","cited_by_count":10},{"id":"2509.11939","title":"PrivWeb: Unobtrusive and Content-aware Privacy Protection For Web Agents","created":"2025-09-15","cited_by_count":9},{"id":"2502.00537","title":"Detecting Ambiguities to Guide Query Rewrite for Robust Conversations in Enterprise AI Assistants","created":"2025-02-01","cited_by_count":8},{"id":"2410.15489","title":"Generative AI Agents in Autonomous Machines: A Safety Perspective","created":"2024-10-20","cited_by_count":7},{"id":"2503.02328","title":"Limited Effectiveness of LLM-based Data Augmentation for COVID-19 Misinformation Stance Detection","created":"2025-03-04","cited_by_count":7},{"id":"2509.14278","title":"Beyond Data Privacy: New Privacy Risks for Large Language Models","created":"2025-09-16","cited_by_count":6},{"id":"2509.14647","title":"AgentCompass: Towards Reliable Evaluation of Agentic Workflows in Production","created":"2025-09-18","cited_by_count":6},{"id":"2510.17640","title":"RESample: A Robust Data Augmentation Framework via Exploratory Sampling for Robotic Manipulation","created":"2025-10-20","cited_by_count":6},{"id":"2506.18932","title":"AI Safety vs. AI Security: Demystifying the Distinction and Boundaries","created":"2025-06-21","cited_by_count":5},{"id":"2507.13729","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","created":"2025-07-18","cited_by_count":5},{"id":"2510.14133","title":"Formalizing the Safety, Security, and Functional Properties of Agentic AI Systems","created":"2025-10-15","cited_by_count":5},{"id":"2309.12815","title":"Improving Generalization in Game Agents with Data Augmentation in Imitation Learning","created":"2023-09-22","cited_by_count":4},{"id":"2411.08341","title":"Generative AI for Data Augmentation in Wireless Networks: Analysis, Applications, and Case Study","created":"2024-11-13","cited_by_count":4},{"id":"2501.11864","title":"LLM-Agents Driven Automated Simulation Testing and Analysis of small Uncrewed Aerial Systems","created":"2025-01-21","cited_by_count":4},{"id":"2506.09080","title":"FinHEAR: Human Expertise and Adaptive Risk-Aware Temporal Reasoning for Financial Decision-Making","created":"2025-06-10","cited_by_count":3},{"id":"2509.03286","title":"Accountability Framework for Healthcare AI Systems: Towards Joint Accountability in Decision Making","created":"2025-09-03","cited_by_count":2}],"next_cursor":null}