{"list":"other","total":79,"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":"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":"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":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"2306.06070","title":"Mind2Web: Towards a Generalist Agent for the Web","created":"2023-06-09","cited_by_count":1242},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"2402.01680","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","created":"2024-01-21","cited_by_count":769},{"id":"2304.08244","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","created":"2023-04-14","cited_by_count":591},{"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":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431},{"id":"2402.02716","title":"Understanding the planning of LLM agents: A survey","created":"2024-02-05","cited_by_count":421},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"2402.01622","title":"TravelPlanner: A Benchmark for Real-World Planning with Language Agents","created":"2024-02-02","cited_by_count":392},{"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":"2303.17491","title":"Language Models can Solve Computer Tasks","created":"2023-03-30","cited_by_count":372},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312},{"id":"1806.11532","title":"TextWorld: A Learning Environment for Text-based Games","created":"2018-06-29","cited_by_count":310},{"id":"2309.10691","title":"MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback","created":"2023-09-19","cited_by_count":297},{"id":"2402.00157","title":"Large Language Models for Mathematical Reasoning: Progresses and Challenges","created":"2024-01-31","cited_by_count":284},{"id":"2401.01313","title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","created":"2024-01-02","cited_by_count":269},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261},{"id":"2305.14078","title":"Large Language Models as Commonsense Knowledge for Large-Scale Task Planning","created":"2023-05-23","cited_by_count":231},{"id":"2305.14909","title":"Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning","created":"2023-05-24","cited_by_count":207},{"id":"2305.16653","title":"AdaPlanner: Adaptive Planning from Feedback with Language Models","created":"2023-05-26","cited_by_count":196},{"id":"2307.04738","title":"RoCo: Dialectic Multi-Robot Collaboration with Large Language Models","created":"2023-07-10","cited_by_count":172},{"id":"1909.05398","title":"Interactive Fiction Games: A Colossal Adventure","created":"2019-09-11","cited_by_count":168},{"id":"2310.12921","title":"Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning","created":"2023-10-19","cited_by_count":165},{"id":"2309.11489","title":"Text2Reward: Reward Shaping with Language Models for Reinforcement Learning","created":"2023-09-20","cited_by_count":160},{"id":"2309.10062","title":"SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models","created":"2023-09-18","cited_by_count":153},{"id":"2306.05836","title":"Can Large Language Models Infer Causation from Correlation?","created":"2023-06-09","cited_by_count":146},{"id":"2402.08115","title":"On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks","created":"2024-02-12","cited_by_count":142},{"id":"2303.06247","title":"Task and Motion Planning with Large Language Models for Object Rearrangement","created":"2023-03-10","cited_by_count":141},{"id":"2302.05128","title":"Translating Natural Language to Planning Goals with Large-Language Models","created":"2023-02-10","cited_by_count":133},{"id":"2306.06531","title":"AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers","created":"2023-06-10","cited_by_count":113},{"id":"2406.03689","title":"Evaluating the World Model Implicit in a Generative Model","created":"2024-06-06","cited_by_count":113},{"id":"2003.05161","title":"A Benchmark for Systematic Generalization in Grounded Language Understanding","created":"2020-03-11","cited_by_count":108},{"id":"2405.04776","title":"Chain of Thoughtlessness? An Analysis of CoT in Planning","created":"2024-05-08","cited_by_count":103},{"id":"2409.13373","title":"LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench","created":"2024-09-20","cited_by_count":94},{"id":"2402.10877","title":"Robust agents learn causal world models","created":"2024-02-16","cited_by_count":81},{"id":"2312.09187","title":"Vision-Language Models as a Source of Rewards","created":"2023-12-14","cited_by_count":66},{"id":"2403.11552","title":"LLM3:Large Language Model-based Task and Motion Planning with Motion Failure Reasoning","created":"2024-03-18","cited_by_count":63},{"id":"2312.09238","title":"Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft","created":"2023-12-14","cited_by_count":61},{"id":"2305.07766","title":"NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models","created":"2023-05-12","cited_by_count":59},{"id":"2310.03249","title":"Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning","created":"2023-10-05","cited_by_count":49},{"id":"2402.10890","title":"When is Tree Search Useful for LLM Planning? It Depends on the Discriminator","created":"2024-02-16","cited_by_count":47},{"id":"2410.02193","title":"Guiding Long-Horizon Task and Motion Planning with Vision Language Models","created":"2024-10-03","cited_by_count":47},{"id":"2310.04276","title":"From task structures to world models: What do LLMs know?","created":"2023-10-06","cited_by_count":46},{"id":"2404.00210","title":"VLM-Social-Nav: Socially Aware Robot Navigation through Scoring using Vision-Language Models","created":"2024-03-30","cited_by_count":46},{"id":"2407.14414","title":"System-1.x: Learning to Balance Fast and Slow Planning with Language Models","created":"2024-07-19","cited_by_count":35},{"id":"2410.12112","title":"Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming","created":"2024-10-15","cited_by_count":35},{"id":"2402.06665","title":"The Essential Role of Causality in Foundation World Models for Embodied AI","created":"2024-02-06","cited_by_count":32},{"id":"2502.05227","title":"Robotouille: An Asynchronous Planning Benchmark for LLM Agents","created":"2025-02-06","cited_by_count":32},{"id":"2309.09182","title":"Optimal Scene Graph Planning with Large Language Model Guidance","created":"2023-09-17","cited_by_count":27},{"id":"2402.04210","title":"Task Success is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviors","created":"2024-02-06","cited_by_count":25},{"id":"2304.08587","title":"Grounding Classical Task Planners via Vision-Language Models","created":"2023-04-17","cited_by_count":23},{"id":"2408.06318","title":"Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Example","created":"2024-08-12","cited_by_count":22},{"id":"2405.13966","title":"On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models","created":"2024-05-22","cited_by_count":17},{"id":"2410.03864","title":"DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search","created":"2024-10-04","cited_by_count":17},{"id":"2402.07876","title":"Policy Improvement using Language Feedback Models","created":"2024-02-12","cited_by_count":16},{"id":"2404.07751","title":"Generating consistent PDDL domains with Large Language Models","created":"2024-04-11","cited_by_count":15},{"id":"2405.19793","title":"PDDLEGO: Iterative Planning in Textual Environments","created":"2024-05-30","cited_by_count":14},{"id":"2402.17717","title":"AmbigNLG: Addressing Task Ambiguity in Instruction for NLG","created":"2024-02-27","cited_by_count":10},{"id":"2406.10540","title":"Generating and Evolving Reward Functions for Highway Driving with Large Language Models","created":"2024-06-15","cited_by_count":8},{"id":"2406.12000","title":"Look Further Ahead: Testing the Limits of GPT-4 in Path Planning","created":"2024-06-17","cited_by_count":7},{"id":"2406.10479","title":"Unlocking Large Language Model's Planning Capabilities with Maximum Diversity Fine-tuning","created":"2024-06-15","cited_by_count":6},{"id":"2411.18711","title":"Evaluating Vision-Language Models as Evaluators in Path Planning","created":"2024-11-27","cited_by_count":6}],"next_cursor":null}