{"total":44,"rows":[{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2304.11477","title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","created":"2023-04-22","cited_by_count":501,"area":null},{"id":"2310.07064","title":"Large Language Models can Learn Rules","created":"2023-10-10","cited_by_count":69,"area":null},{"id":"2308.12682","title":"SayCanPay: Heuristic Planning with Large Language Models using Learnable Domain Knowledge","created":"2023-08-24","cited_by_count":49,"area":null},{"id":"2310.12418","title":"The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions","created":"2023-10-19","cited_by_count":45,"area":null},{"id":"2306.07075","title":"Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergence","created":"2023-06-12","cited_by_count":42,"area":null},{"id":"2401.02500","title":"On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)","created":"2024-01-04","cited_by_count":40,"area":null},{"id":"2306.10512","title":"Position: AI Evaluation Should Learn from How We Test Humans","created":"2023-06-18","cited_by_count":36,"area":null},{"id":"2305.16151","title":"Understanding the Capabilities of Large Language Models for Automated Planning","created":"2023-05-25","cited_by_count":34,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2305.17590","title":"Integrating Action Knowledge and LLMs for Task Planning and Situation Handling in Open Worlds","created":"2023-05-27","cited_by_count":26,"area":null},{"id":"2308.16797","title":"Simple LLM Prompting is State-of-the-Art for Robust and Multilingual Dialogue Evaluation","created":"2023-08-31","cited_by_count":19,"area":null},{"id":"2509.16198","title":"RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation","created":"2025-09-19","cited_by_count":19,"area":null},{"id":"2409.19924","title":"On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability","created":"2024-09-30","cited_by_count":18,"area":null},{"id":"2412.09879","title":"On the Limit of Language Models as Planning Formalizers","created":"2024-12-13","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":"2402.16181","title":"How Can LLM Guide RL? A Value-Based Approach","created":"2024-02-25","cited_by_count":13,"area":null},{"id":"2305.15695","title":"Asking Before Acting: Gather Information in Embodied Decision Making with Language Models","created":"2023-05-25","cited_by_count":12,"area":null},{"id":"2311.03687","title":"Dissecting the Runtime Performance of the Training, Fine-tuning, and Inference of Large Language Models","created":"2023-11-07","cited_by_count":12,"area":null},{"id":"2312.10332","title":"ProTIP: Progressive Tool Retrieval Improves Planning","created":"2023-12-16","cited_by_count":12,"area":null},{"id":"2511.07678","title":"AIA Forecaster: Technical Report","created":"2025-11-10","cited_by_count":9,"area":null},{"id":"2303.04912","title":"Embodied Active Learning of Relational State Abstractions for Bilevel Planning","created":"2023-03-08","cited_by_count":8,"area":null},{"id":"2510.21329","title":"TripTide: A Benchmark for Adaptive Travel Planning under Disruptions","created":"2025-10-24","cited_by_count":8,"area":null},{"id":"2306.01295","title":"Egocentric Planning for Scalable Embodied Task Achievement","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2406.12000","title":"Look Further Ahead: Testing the Limits of GPT-4 in Path Planning","created":"2024-06-17","cited_by_count":7,"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":"2512.24103","title":"Enhancing LLM Planning Capabilities through Intrinsic Self-Critique","created":"2025-12-30","cited_by_count":7,"area":null},{"id":"2307.01540","title":"Learning to Prompt in the Classroom to Understand AI Limits: A pilot study","created":"2023-07-04","cited_by_count":6,"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":"2310.17140","title":"Symbolic Planning and Code Generation for Grounded Dialogue","created":"2023-10-26","cited_by_count":5,"area":null},{"id":"2402.11489","title":"What's the Plan? Evaluating and Developing Planning-Aware Techniques for Language Models","created":"2024-02-18","cited_by_count":4,"area":null},{"id":"2404.04540","title":"The Case for Developing a Foundation Model for Planning-like Tasks from Scratch","created":"2024-04-06","cited_by_count":3,"area":null},{"id":"2404.08424","title":"Comparing Apples to Oranges: LLM-powered Multimodal Intention Prediction in an Object Categorization Task","created":"2024-04-12","cited_by_count":3,"area":null},{"id":"2405.12147","title":"Eliciting Problem Specifications via Large Language Models","created":"2024-05-20","cited_by_count":2,"area":null},{"id":"2411.17912","title":"Can LLMs plan paths in the real world?","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2512.21775","title":"Compliance Rating Scheme: A Data Provenance Framework for Generative AI Datasets","created":"2025-12-25","cited_by_count":2,"area":null},{"id":"2311.04403","title":"Human-Centered Planning","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2402.15929","title":"Certifying Knowledge Comprehension in LLMs","created":"2024-02-24","cited_by_count":1,"area":null},{"id":"2505.13126","title":"Iterative Formalization and Planning in Partially Observable Environments","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2511.21591","title":"On the Limits of Innate Planning in Large Language Models","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2604.02910","title":"Analysis of Optimality of Large Language Models on Planning Problems","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2411.13008","title":"Evaluating LLMs Capabilities Towards Understanding Social Dynamics","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2412.03446","title":"From Words to Workflows: Automating Business Processes","created":"2024-12-04","cited_by_count":0,"area":null},{"id":"2601.02871","title":"SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection","created":"2026-01-06","cited_by_count":0,"area":null}],"next_cursor":null}