{"list":"other","total":78,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"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":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2305.19118","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","created":"2023-05-30","cited_by_count":1011},{"id":"2007.15779","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","created":"2020-07-31","cited_by_count":1009},{"id":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2504.08066","title":"The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search","created":"2025-04-10","cited_by_count":422},{"id":"2502.18864","title":"Accelerating scientific discovery with Co-Scientist","created":"2025-02-26","cited_by_count":401},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2302.01560","title":"Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents","created":"2023-02-03","cited_by_count":398},{"id":"2206.10498","title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change","created":"2022-06-21","cited_by_count":382},{"id":"2403.07718","title":"WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?","created":"2024-03-12","cited_by_count":363},{"id":"2311.16452","title":"Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine","created":"2023-11-28","cited_by_count":329},{"id":"2311.10537","title":"MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning","created":"2023-11-16","cited_by_count":316},{"id":"2309.13007","title":"ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs","created":"2023-09-22","cited_by_count":309},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"2402.06782","title":"Debating with More Persuasive LLMs Leads to More Truthful Answers","created":"2024-02-09","cited_by_count":266},{"id":"2309.07430","title":"Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization","created":"2023-09-14","cited_by_count":246},{"id":"2406.07155","title":"Scaling Large Language Model-based Multi-Agent Collaboration","created":"2024-06-11","cited_by_count":241},{"id":"2404.18416","title":"Capabilities of Gemini Models in Medicine","created":"2024-04-29","cited_by_count":237},{"id":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225},{"id":"2305.10142","title":"Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback","created":"2023-05-17","cited_by_count":207},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204},{"id":"2309.07045","title":"SafetyBench: Evaluating the Safety of Large Language Models","created":"2023-09-13","cited_by_count":199},{"id":"2404.15155","title":"MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making","created":"2024-04-22","cited_by_count":163},{"id":"2307.15343","title":"Med-HALT: Medical Domain Hallucination Test for Large Language Models","created":"2023-07-28","cited_by_count":157},{"id":"2403.04783","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","created":"2024-03-02","cited_by_count":145},{"id":"2403.17927","title":"MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution","created":"2024-03-26","cited_by_count":134},{"id":"2304.09667","title":"GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information","created":"2023-04-19","cited_by_count":117},{"id":"2302.07257","title":"ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Models","created":"2023-02-14","cited_by_count":116},{"id":"2312.00164","title":"Towards Accurate Differential Diagnosis with Large Language Models","created":"2023-11-30","cited_by_count":116},{"id":"2401.18018","title":"On Prompt-Driven Safeguarding for Large Language Models","created":"2024-01-31","cited_by_count":116},{"id":"2406.11776","title":"Improving Multi-Agent Debate with Sparse Communication Topology","created":"2024-06-17","cited_by_count":107},{"id":"2407.04622","title":"On scalable oversight with weak LLMs judging strong LLMs","created":"2024-07-05","cited_by_count":99},{"id":"2407.05291","title":"WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks","created":"2024-07-07","cited_by_count":90},{"id":"2502.18439","title":"MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning","created":"2025-02-25","cited_by_count":86},{"id":"2401.05654","title":"Towards Conversational Diagnostic AI","created":"2024-01-11","cited_by_count":79},{"id":"2401.06866","title":"Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data","created":"2024-01-12","cited_by_count":66},{"id":"2403.02475","title":"Enhancing LLM Safety via Constrained Direct Preference Optimization","created":"2024-03-04","cited_by_count":49},{"id":"2403.03744","title":"MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models","created":"2024-03-06","cited_by_count":44},{"id":"2402.11550","title":"LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration","created":"2024-02-18","cited_by_count":38},{"id":"2403.16843","title":"Do LLM Agents Have Regret? A Case Study in Online Learning and Games","created":"2024-03-25","cited_by_count":35},{"id":"2504.13359","title":"Cost-of-Pass: An Economic Framework for Evaluating Language Models","created":"2025-04-17","cited_by_count":35},{"id":"2410.10014","title":"Safety-Aware Fine-Tuning of Large Language Models","created":"2024-10-13","cited_by_count":34},{"id":"2501.07834","title":"Flow: Modularized Agentic Workflow Automation","created":"2025-01-14","cited_by_count":34},{"id":"2501.05464","title":"LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models","created":"2024-12-31","cited_by_count":32},{"id":"2411.19865","title":"Reverse Thinking Makes LLMs Stronger Reasoners","created":"2024-11-29","cited_by_count":29},{"id":"2406.13890","title":"ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World","created":"2024-06-19","cited_by_count":28},{"id":"2406.06474","title":"Towards a Personal Health Large Language Model","created":"2024-06-10","cited_by_count":27},{"id":"2308.01834","title":"The Capability of Large Language Models to Measure Psychiatric Functioning","created":"2023-08-03","cited_by_count":26},{"id":"2412.18693","title":"Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning","created":"2024-12-24","cited_by_count":25},{"id":"2502.11184","title":"Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs","created":"2025-02-16","cited_by_count":23},{"id":"2504.18530","title":"Scaling Laws For Scalable Oversight","created":"2025-04-25","cited_by_count":23},{"id":"2409.19492","title":"MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models","created":"2024-09-29","cited_by_count":21},{"id":"2402.00667","title":"Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning","created":"2024-02-01","cited_by_count":18},{"id":"2412.09796","title":"AutoPatent: A Multi-Agent Framework for Automatic Patent Generation","created":"2024-12-13","cited_by_count":16},{"id":"2412.18947","title":"MedHallBench: A New Benchmark for Assessing Hallucination in Medical Large Language Models","created":"2024-12-25","cited_by_count":15},{"id":"2406.06435","title":"Language Models are Alignable Decision-Makers: Dataset and Application to the Medical Triage Domain","created":"2024-06-10","cited_by_count":14},{"id":"2503.06074","title":"Towards Conversational AI for Disease Management","created":"2025-03-08","cited_by_count":11},{"id":"2505.20824","title":"MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems","created":"2025-05-27","cited_by_count":9},{"id":"2504.17669","title":"Towards a HIPAA Compliant Agentic AI System in Healthcare","created":"2025-04-24","cited_by_count":8},{"id":"2407.00541","title":"Answering real-world clinical questions using large language model based systems","created":"2024-06-29","cited_by_count":3},{"id":"2407.18422","title":"A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety","created":"2024-07-25","cited_by_count":3},{"id":"2505.13577","title":"VocalAgent: Large Language Models for Vocal Health Diagnostics with Safety-Aware Evaluation","created":"2025-05-19","cited_by_count":2}],"next_cursor":null}