{"list":"other","total":90,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"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":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"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":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"2310.11324","title":"Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting","created":"2023-10-17","cited_by_count":817},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2305.03111","title":"Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs","created":"2023-05-04","cited_by_count":688},{"id":"2310.04406","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","created":"2023-10-06","cited_by_count":574},{"id":"2304.11477","title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","created":"2023-04-22","cited_by_count":501},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465},{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462},{"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":"2410.02736","title":"Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge","created":"2024-10-03","cited_by_count":368},{"id":"2210.01240","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","created":"2022-10-03","cited_by_count":337},{"id":"2305.15771","title":"On the Planning Abilities of Large Language Models : A Critical Investigation","created":"2023-05-25","cited_by_count":312},{"id":"2307.01928","title":"Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners","created":"2023-07-04","cited_by_count":308},{"id":"2310.05915","title":"FireAct: Toward Language Agent Fine-tuning","created":"2023-10-09","cited_by_count":256},{"id":"2305.14078","title":"Large Language Models as Commonsense Knowledge for Large-Scale Task Planning","created":"2023-05-23","cited_by_count":231},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"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":"2403.02502","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","created":"2024-03-04","cited_by_count":197},{"id":"2305.16653","title":"AdaPlanner: Adaptive Planning from Feedback with Language Models","created":"2023-05-26","cited_by_count":196},{"id":"2402.01817","title":"LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks","created":"2024-02-02","cited_by_count":179},{"id":"2311.05772","title":"ADaPT: As-Needed Decomposition and Planning with Language Models","created":"2023-11-08","cited_by_count":177},{"id":"2309.15091","title":"VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning","created":"2023-09-26","cited_by_count":141},{"id":"2309.12499","title":"CodePlan: Repository-level Coding using LLMs and Planning","created":"2023-09-21","cited_by_count":140},{"id":"2305.11014","title":"Generalized Planning in PDDL Domains with Pretrained Large Language Models","created":"2023-05-18","cited_by_count":139},{"id":"2406.04520","title":"NATURAL PLAN: Benchmarking LLMs on Natural Language Planning","created":"2024-06-06","cited_by_count":128},{"id":"2310.01557","title":"SmartPlay: A Benchmark for LLMs as Intelligent Agents","created":"2023-10-02","cited_by_count":125},{"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":"2310.13227","title":"ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search","created":"2023-10-20","cited_by_count":105},{"id":"2110.01517","title":"Skill Induction and Planning with Latent Language","created":"2021-10-04","cited_by_count":99},{"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":"2402.14083","title":"Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping","created":"2024-02-21","cited_by_count":90},{"id":"2403.04121","title":"Can Large Language Models Reason and Plan?","created":"2024-03-07","cited_by_count":82},{"id":"2411.00081","title":"PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks","created":"2024-10-31","cited_by_count":82},{"id":"2310.05746","title":"Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena","created":"2023-10-09","cited_by_count":78},{"id":"2308.13724","title":"ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning","created":"2023-08-26","cited_by_count":77},{"id":"1904.03396","title":"Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation","created":"2019-04-06","cited_by_count":75},{"id":"2408.13006","title":"Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates","created":"2024-08-23","cited_by_count":72},{"id":"2308.03427","title":"TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage","created":"2023-08-07","cited_by_count":55},{"id":"2410.15326","title":"A Survey of Uncertainty Estimation in LLMs: Theory Meets Practice","created":"2024-10-20","cited_by_count":55},{"id":"2402.15506","title":"AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning","created":"2024-02-23","cited_by_count":53},{"id":"2308.12682","title":"SayCanPay: Heuristic Planning with Large Language Models using Learnable Domain Knowledge","created":"2023-08-24","cited_by_count":49},{"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":"2305.05252","title":"Distilling Script Knowledge from Large Language Models for Constrained Language Planning","created":"2023-05-09","cited_by_count":45},{"id":"2310.10632","title":"BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology","created":"2023-10-16","cited_by_count":43},{"id":"2405.19119","title":"Can Graph Learning Improve Planning in LLM-based Agents?","created":"2024-05-29","cited_by_count":43},{"id":"2305.01795","title":"Multimodal Procedural Planning via Dual Text-Image Prompting","created":"2023-05-02","cited_by_count":40},{"id":"2303.08006","title":"Data-Efficient Learning of Natural Language to Linear Temporal Logic Translators for Robot Task Specification","created":"2023-03-09","cited_by_count":38},{"id":"2402.02805","title":"Graph-enhanced Large Language Models in Asynchronous Plan Reasoning","created":"2024-02-05","cited_by_count":37},{"id":"2009.14259","title":"Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions","created":"2020-09-29","cited_by_count":36},{"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":"2209.00465","title":"On Grounded Planning for Embodied Tasks with Language Models","created":"2022-08-29","cited_by_count":33},{"id":"2407.03321","title":"Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages","created":"2024-07-03","cited_by_count":33},{"id":"2404.11833","title":"Thought of Search: Planning with Language Models Through The Lens of Efficiency","created":"2024-04-18","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":"2310.12128","title":"DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning","created":"2023-10-18","cited_by_count":29},{"id":"2410.04223","title":"Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning","created":"2024-10-05","cited_by_count":29},{"id":"2402.08546","title":"Grounding LLMs For Robot Task Planning Using Closed-loop State Feedback","created":"2024-02-13","cited_by_count":25},{"id":"2312.09007","title":"LLMind: Orchestrating AI and IoT with LLM for Complex Task Execution","created":"2023-12-14","cited_by_count":24},{"id":"2406.04784","title":"SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals","created":"2024-06-07","cited_by_count":21},{"id":"2410.16456","title":"To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning","created":"2024-10-21","cited_by_count":21},{"id":"2406.05572","title":"Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfaction","created":"2024-06-08","cited_by_count":19},{"id":"2305.07716","title":"Learning to Reason over Scene Graphs: A Case Study of Finetuning GPT-2 into a Robot Language Model for Grounded Task Planning","created":"2023-05-12","cited_by_count":16},{"id":"2308.15299","title":"TaskLAMA: Probing the Complex Task Understanding of Language Models","created":"2023-08-29","cited_by_count":12},{"id":"2409.01806","title":"LASP: Surveying the State-of-the-Art in Large Language Model-Assisted AI Planning","created":"2024-09-03","cited_by_count":9},{"id":"2204.10420","title":"PG3: Policy-Guided Planning for Generalized Policy Generation","created":"2022-04-21","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":"2408.11326","title":"Automating Thought of Search: A Journey Towards Soundness and Completeness","created":"2024-08-21","cited_by_count":7},{"id":"2406.02903","title":"Open Grounded Planning: Challenges and Benchmark Construction","created":"2024-06-05","cited_by_count":4},{"id":"2407.07778","title":"WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment","created":"2024-07-10","cited_by_count":4},{"id":"2412.09666","title":"Systematic Analysis of LLM Contributions to Planning: Solver, Verifier, Heuristic","created":"2024-12-12","cited_by_count":3},{"id":"2412.06162","title":"Query-Efficient Planning with Language Models","created":"2024-12-09","cited_by_count":1}],"next_cursor":null}