{"total":151,"rows":[{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2404.11018","title":"Many-Shot In-Context Learning","created":"2024-04-17","cited_by_count":206,"area":null},{"id":"2403.06963","title":"The pitfalls of next-token prediction","created":"2024-03-11","cited_by_count":160,"area":null},{"id":"2406.04520","title":"NATURAL PLAN: Benchmarking LLMs on Natural Language Planning","created":"2024-06-06","cited_by_count":128,"area":null},{"id":"2310.08118","title":"Can Large Language Models Really Improve by Self-critiquing Their Own Plans?","created":"2023-10-12","cited_by_count":108,"area":null},{"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,"area":null},{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83,"area":null},{"id":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80,"area":null},{"id":"2406.06485","title":"Can Language Models Serve as Text-Based World Simulators?","created":"2024-06-10","cited_by_count":52,"area":null},{"id":"2310.15959","title":"NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes","created":"2023-10-24","cited_by_count":48,"area":null},{"id":"2311.05965","title":"Large Language Models are Zero Shot Hypothesis Proposers","created":"2023-11-10","cited_by_count":45,"area":null},{"id":"2310.07263","title":"CoPAL: Corrective Planning of Robot Actions with Large Language Models","created":"2023-10-11","cited_by_count":40,"area":null},{"id":"2412.10999","title":"Cocoa: Co-Planning and Co-Execution with AI Agents","created":"2024-12-14","cited_by_count":39,"area":null},{"id":"2404.03647","title":"Capabilities of Large Language Models in Control Engineering: A Benchmark Study on GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra","created":"2024-04-04","cited_by_count":37,"area":null},{"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,"area":null},{"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,"area":null},{"id":"2407.08940","title":"Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation","created":"2024-07-12","cited_by_count":34,"area":null},{"id":"2407.03321","title":"Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages","created":"2024-07-03","cited_by_count":33,"area":null},{"id":"2407.14962","title":"Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectives","created":"2024-07-20","cited_by_count":30,"area":null},{"id":"2504.15266","title":"Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction","created":"2025-04-21","cited_by_count":29,"area":null},{"id":"2407.09886","title":"Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation","created":"2024-07-13","cited_by_count":27,"area":null},{"id":"2310.01468","title":"Probing the Multi-turn Planning Capabilities of LLMs via 20 Question Games","created":"2023-10-02","cited_by_count":24,"area":null},{"id":"2311.09830","title":"Automating the Generation of Prompts for LLM-based Action Choice in PDDL Planning","created":"2023-11-16","cited_by_count":24,"area":null},{"id":"2405.13245","title":"A Survey of Robotic Language Grounding: Tradeoffs between Symbols and Embeddings","created":"2024-05-21","cited_by_count":24,"area":null},{"id":"2405.13551","title":"Large Language Models are Effective Priors for Causal Graph Discovery","created":"2024-05-22","cited_by_count":24,"area":null},{"id":"2406.08824","title":"LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions","created":"2024-06-13","cited_by_count":22,"area":null},{"id":"2309.10092","title":"Conformal Temporal Logic Planning using Large Language Models","created":"2023-09-18","cited_by_count":21,"area":null},{"id":"2502.17898","title":"VeriPlan: Integrating Formal Verification and LLMs into End-User Planning","created":"2025-02-25","cited_by_count":20,"area":null},{"id":"2401.11506","title":"Enhancing Recommendation Diversity by Re-ranking with Large Language Models","created":"2024-01-21","cited_by_count":19,"area":null},{"id":"2406.13094","title":"Exploring and Benchmarking the Planning Capabilities of Large Language Models","created":"2024-06-18","cited_by_count":19,"area":null},{"id":"2405.09220","title":"ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Models","created":"2024-05-15","cited_by_count":18,"area":null},{"id":"2503.18809","title":"Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code","created":"2025-03-24","cited_by_count":18,"area":null},{"id":"2602.11865","title":"Intelligent AI Delegation","created":"2026-02-12","cited_by_count":18,"area":null},{"id":"2410.02162","title":"Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1","created":"2024-10-03","cited_by_count":17,"area":null},{"id":"2409.15915","title":"Planning in the Dark: LLM-Symbolic Planning Pipeline without Experts","created":"2024-09-24","cited_by_count":16,"area":null},{"id":"2504.01002","title":"Token embeddings violate the manifold hypothesis","created":"2025-04-01","cited_by_count":16,"area":null},{"id":"2403.00092","title":"PROC2PDDL: Open-Domain Planning Representations from Texts","created":"2024-02-29","cited_by_count":15,"area":null},{"id":"2506.21521","title":"Potemkin Understanding in Large Language Models","created":"2025-06-26","cited_by_count":15,"area":null},{"id":"2405.19793","title":"PDDLEGO: Iterative Planning in Textual Environments","created":"2024-05-30","cited_by_count":14,"area":null},{"id":"2410.18819","title":"From Imitation to Introspection: Probing Self-Consciousness in Language Models","created":"2024-10-24","cited_by_count":14,"area":null},{"id":"2405.19740","title":"PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant Perturbations","created":"2024-05-30","cited_by_count":13,"area":null},{"id":"2409.06762","title":"Generative Hierarchical Materials Search","created":"2024-09-10","cited_by_count":13,"area":null},{"id":"2410.14682","title":"ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models","created":"2024-10-02","cited_by_count":13,"area":null},{"id":"2308.07902","title":"Through the Lens of Core Competency: Survey on Evaluation of Large Language Models","created":"2023-08-15","cited_by_count":12,"area":null},{"id":"2402.17531","title":"Nissist: An Incident Mitigation Copilot based on Troubleshooting Guides","created":"2024-02-27","cited_by_count":12,"area":null},{"id":"2404.00614","title":"Learning to Plan for Language Modeling from Unlabeled Data","created":"2024-03-31","cited_by_count":12,"area":null},{"id":"2404.05449","title":"RoT: Enhancing Large Language Models with Reflection on Search Trees","created":"2024-04-08","cited_by_count":12,"area":null},{"id":"2401.11052","title":"Mining experimental data from Materials Science literature with Large Language Models: an evaluation study","created":"2024-01-19","cited_by_count":11,"area":null},{"id":"2403.05766","title":"FLAP: Flow-Adhering Planning with Constrained Decoding in LLMs","created":"2024-03-09","cited_by_count":11,"area":null},{"id":"2406.01917","title":"GOMAA-Geo: GOal Modality Agnostic Active Geo-localization","created":"2024-06-04","cited_by_count":11,"area":null},{"id":"2409.14907","title":"Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarization","created":"2024-09-23","cited_by_count":11,"area":null},{"id":"2412.10675","title":"Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation","created":"2024-12-14","cited_by_count":11,"area":null},{"id":"2501.11739","title":"Episodic memory in AI agents poses risks that should be studied and mitigated","created":"2025-01-20","cited_by_count":11,"area":null},{"id":"2407.13729","title":"Baba Is AI: Break the Rules to Beat the Benchmark","created":"2024-07-18","cited_by_count":10,"area":null},{"id":"2504.04578","title":"Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification","created":"2025-04-06","cited_by_count":9,"area":null},{"id":"2405.15194","title":"Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning","created":"2024-05-24","cited_by_count":8,"area":null},{"id":"2406.02791","title":"Language Models can Infer Action Semantics for Symbolic Planners from Environment Feedback","created":"2024-06-04","cited_by_count":8,"area":null},{"id":"2409.13994","title":"Contrastive Learning for Knowledge-Based Question Generation in Large Language Models","created":"2024-09-21","cited_by_count":8,"area":null},{"id":"2410.13779","title":"The Mystery of the Pathological Path-star Task for Language Models","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2407.10735","title":"Transforming Agency. On the mode of existence of Large Language Models","created":"2024-07-15","cited_by_count":7,"area":null},{"id":"2410.18077","title":"ALTA: Compiler-Based Analysis of Transformers","created":"2024-10-23","cited_by_count":7,"area":null},{"id":"2505.01009","title":"Improving Large Language Model Planning with Action Sequence Similarity","created":"2025-05-02","cited_by_count":7,"area":null},{"id":"2508.13876","title":"Improved Generalized Planning with LLMs through Strategy Refinement and Reflection","created":"2025-08-19","cited_by_count":7,"area":null},{"id":"2511.09378","title":"Frontier Large Language Models Rival State-of-the-Art Planners","created":"2025-11-12","cited_by_count":7,"area":null},{"id":"2512.24103","title":"Enhancing LLM Planning Capabilities through Intrinsic Self-Critique","created":"2025-12-30","cited_by_count":7,"area":null},{"id":"2403.06063","title":"Target-constrained Bidirectional Planning for Generation of Target-oriented Proactive Dialogue","created":"2024-03-10","cited_by_count":6,"area":null},{"id":"2404.18311","title":"Towards Incremental Learning in Large Language Models: A Critical Review","created":"2024-04-28","cited_by_count":6,"area":null},{"id":"2407.19630","title":"LLMs' Understanding of Natural Language Revealed","created":"2024-07-29","cited_by_count":6,"area":null},{"id":"2409.18475","title":"Data Analysis in the Era of Generative AI","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2411.06490","title":"Hermes: A Large Language Model Framework on the Journey to Autonomous Networks","created":"2024-11-10","cited_by_count":6,"area":null},{"id":"2509.23186","title":"Understanding and Enhancing the Planning Capability of Language Models via Multi-Token Prediction","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2605.26525","title":"ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation","created":"2026-05-26","cited_by_count":6,"area":null},{"id":"2410.19727","title":"FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning","created":"2024-10-25","cited_by_count":5,"area":null},{"id":"2505.19806","title":"Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2509.11118","title":"We Argue to Agree: Towards Personality-Driven Argumentation-Based Negotiation Dialogue Systems for Tourism","created":"2025-09-14","cited_by_count":5,"area":null},{"id":"2509.12273","title":"LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences","created":"2025-09-14","cited_by_count":5,"area":null},{"id":"2604.18463","title":"Using large language models for embodied planning introduces systematic safety risks","created":"2026-04-20","cited_by_count":5,"area":null},{"id":"2502.18387","title":"How Far are LLMs from Real Search? A Comprehensive Study on Efficiency, Completeness, and Inherent Capabilities","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2503.08084","title":"Instruction-Augmented Long-Horizon Planning: Embedding Grounding Mechanisms in Embodied Mobile Manipulation","created":"2025-03-11","cited_by_count":4,"area":null},{"id":"2504.10418","title":"CliniChat: A Multi-Source Knowledge-Driven Framework for Clinical Interview Dialogue Reconstruction and Evaluation","created":"2025-04-14","cited_by_count":4,"area":null},{"id":"2505.24306","title":"GridRoute: A Benchmark for LLM-Based Route Planning with Cardinal Movement in Grid Environments","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2509.22613","title":"Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2511.00130","title":"A Comparative Analysis of LLM Adaptation: SFT, LoRA, and ICL in Data-Scarce Scenarios","created":"2025-10-31","cited_by_count":4,"area":null},{"id":"2403.03167","title":"PARADISE: Evaluating Implicit Planning Skills of Language Models with Procedural Warnings and Tips Dataset","created":"2024-03-05","cited_by_count":3,"area":null},{"id":"2404.04292","title":"Conversational Disease Diagnosis via External Planner-Controlled Large Language Models","created":"2024-04-04","cited_by_count":3,"area":null},{"id":"2406.09891","title":"Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming","created":"2024-06-14","cited_by_count":3,"area":null},{"id":"2409.17655","title":"AssistantX: An LLM-Powered Proactive Assistant in Collaborative Human-Populated Environment","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2501.18291","title":"CueTip: An Interactive and Explainable Physics-aware Pool Assistant","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2503.10542","title":"Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2505.01479","title":"Deliberate Planning in Language Models with Symbolic Representation","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2505.14763","title":"Unifying Inference-Time Planning Language Generation","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2402.06608","title":"TIC: Translate-Infer-Compile for accurate \"text to plan\" using LLMs and Logical Representations","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2402.07234","title":"CPSDBench: A Large Language Model Evaluation Benchmark and Baseline for Chinese Public Security Domain","created":"2024-02-11","cited_by_count":2,"area":null},{"id":"2406.14473","title":"Data-Centric AI in the Age of Large Language Models","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2407.04899","title":"Algorithmic Language Models with Neurally Compiled Libraries","created":"2024-07-06","cited_by_count":2,"area":null},{"id":"2410.08898","title":"Low-Dimension-to-High-Dimension Generalization And Its Implications for Length Generalization","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2412.15349","title":"Adaptive Urban Planning: A Hybrid Framework for Balanced City Development","created":"2024-12-19","cited_by_count":2,"area":null},{"id":"2506.11380","title":"Enhance Multimodal Consistency and Coherence for Text-Image Plan Generation","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2508.18515","title":"Weisfeiler-Leman Features for Planning: A 1,000,000 Sample Size Hyperparameter Study","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2603.03704","title":"Large-Language-Model-Guided State Estimation for Partially Observable Task and Motion Planning","created":"2026-03-04","cited_by_count":2,"area":null}],"next_cursor":"100"}