{"total":179,"rows":[{"id":"2412.14161","title":"TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks","created":"2024-12-18","cited_by_count":326,"area":"agents"},{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219,"area":null},{"id":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146,"area":"lr"},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143,"area":"lr"},{"id":"2410.14157","title":"Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning","created":"2024-10-18","cited_by_count":135,"area":"lr"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2410.21333","title":"Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse","created":"2024-10-27","cited_by_count":109,"area":"lr"},{"id":"2501.08603","title":"Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design","created":"2025-01-15","cited_by_count":109,"area":"lr"},{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"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":"2408.00764","title":"AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation","created":"2024-08-01","cited_by_count":83,"area":"lr"},{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83,"area":null},{"id":"2403.04121","title":"Can Large Language Models Reason and Plan?","created":"2024-03-07","cited_by_count":82,"area":"lr"},{"id":"2407.13032","title":"Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems","created":"2024-07-17","cited_by_count":81,"area":"agents"},{"id":"2509.09677","title":"The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs","created":"2025-09-11","cited_by_count":64,"area":null},{"id":"2406.13605","title":"Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?","created":"2024-06-19","cited_by_count":63,"area":null},{"id":"2502.01390","title":"Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistant","created":"2025-02-03","cited_by_count":54,"area":"agents"},{"id":"2411.17501","title":"The Limits of Inference Scaling Through Resampling","created":"2024-11-26","cited_by_count":53,"area":null},{"id":"2402.15487","title":"RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation","created":"2024-02-23","cited_by_count":48,"area":null},{"id":"2404.11891","title":"Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Tools","created":"2024-04-18","cited_by_count":47,"area":null},{"id":"2407.01863","title":"VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs","created":"2024-07-02","cited_by_count":47,"area":"lr"},{"id":"2503.18971","title":"LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models","created":"2025-03-22","cited_by_count":38,"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":"2402.13610","title":"Data-driven Discovery with Large Generative Models","created":"2024-02-21","cited_by_count":34,"area":null},{"id":"2406.05673","title":"Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples","created":"2024-06-09","cited_by_count":30,"area":"lr"},{"id":"2410.04223","title":"Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning","created":"2024-10-05","cited_by_count":29,"area":"mllm"},{"id":"2402.06529","title":"Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity","created":"2024-02-09","cited_by_count":27,"area":"lr"},{"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,"area":"agents"},{"id":"2410.03524","title":"Steering Large Language Models between Code Execution and Textual Reasoning","created":"2024-10-04","cited_by_count":24,"area":"lr"},{"id":"2503.13502","title":"Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2405.05885","title":"VLM-Auto: VLM-based Autonomous Driving Assistant with Human-like Behavior and Understanding for Complex Road Scenes","created":"2024-05-09","cited_by_count":23,"area":"driving"},{"id":"2407.00994","title":"LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentation","created":"2024-07-01","cited_by_count":23,"area":null},{"id":"2403.10779","title":"LLM-based Conversational AI Therapist for Daily Functioning Screening and Psychotherapeutic Intervention via Everyday Smart Devices","created":"2024-03-16","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":"2406.05572","title":"Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfaction","created":"2024-06-08","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":"2412.04703","title":"Transformers Struggle to Learn to Search","created":"2024-12-06","cited_by_count":19,"area":null},{"id":"2404.04251","title":"Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)","created":"2024-04-05","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":"2405.13966","title":"On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models","created":"2024-05-22","cited_by_count":17,"area":"lr"},{"id":"2406.10196","title":"TRIP-PAL: Travel Planning with Guarantees by Combining Large Language Models and Automated Planners","created":"2024-06-14","cited_by_count":17,"area":null},{"id":"2408.10635","title":"Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search","created":"2024-08-20","cited_by_count":17,"area":"synth"},{"id":"2410.02110","title":"Can LLMs Reliably Simulate Human Learner Actions? A Simulation Authoring Framework for Open-Ended Learning Environments","created":"2024-10-03","cited_by_count":17,"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":"2504.11844","title":"Evaluating the Goal-Directedness of Large Language Models","created":"2025-04-16","cited_by_count":16,"area":null},{"id":"2505.21981","title":"Learning Compositional Behaviors from Demonstration and Language","created":"2025-05-28","cited_by_count":15,"area":"offlinerl"},{"id":"2405.16661","title":"RLSF: Fine-tuning LLMs via Symbolic Feedback","created":"2024-05-26","cited_by_count":14,"area":"alignment"},{"id":"2504.03930","title":"Have Large Language Models Learned to Reason? A Characterization via 3-SAT Phase Transition","created":"2025-04-04","cited_by_count":14,"area":"lr"},{"id":"2507.11662","title":"Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification","created":"2025-07-15","cited_by_count":14,"area":"lr"},{"id":"2411.14491","title":"A Survey on Human-Centric LLMs","created":"2024-11-20","cited_by_count":13,"area":null},{"id":"2509.20988","title":"AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search","created":"2025-09-25","cited_by_count":13,"area":null},{"id":"2502.15797","title":"OCCULT: Evaluating Large Language Models for Offensive Cyber Operation Capabilities","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2408.07461","title":"Problem Solving Through Human-AI Preference-Based Cooperation","created":"2024-08-14","cited_by_count":11,"area":null},{"id":"2501.00296","title":"From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models","created":"2024-12-31","cited_by_count":11,"area":"wm"},{"id":"2501.00539","title":"MCP-Solver: Integrating Language Models with Constraint Programming Systems","created":"2024-12-31","cited_by_count":10,"area":"agents"},{"id":"2507.00711","title":"Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectories","created":"2025-07-01","cited_by_count":10,"area":"lr"},{"id":"2502.06813","title":"Policy Guided Tree Search for Enhanced LLM Reasoning","created":"2025-02-04","cited_by_count":9,"area":"lr"},{"id":"2504.08148","title":"Orchestrating Agents and Data for Enterprise: A Blueprint Architecture for Compound AI","created":"2025-04-10","cited_by_count":9,"area":"agents"},{"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":"2410.07765","title":"GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2502.18641","title":"WhatELSE: Shaping Narrative Spaces at Configurable Level of Abstraction for AI-bridged Interactive Storytelling","created":"2025-02-25","cited_by_count":8,"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":"2409.13153","title":"Towards Efficient Neuro-Symbolic AI: From Workload Characterization to Hardware Architecture","created":"2024-09-20","cited_by_count":7,"area":null},{"id":"2502.02441","title":"LLMER: Crafting Interactive Extended Reality Worlds with JSON Data Generated by Large Language Models","created":"2025-02-04","cited_by_count":7,"area":null},{"id":"2503.09617","title":"Factorio Learning Environment","created":"2025-03-06","cited_by_count":7,"area":null},{"id":"2505.16477","title":"Advancing the Scientific Method with Large Language Models: From Hypothesis to Discovery","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2510.03469","title":"Bridging LLM Planning Agents and Formal Methods: A Case Study in Plan Verification","created":"2025-10-03","cited_by_count":7,"area":"agents"},{"id":"2512.23167","title":"SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search","created":"2025-12-29","cited_by_count":7,"area":"lr"},{"id":"2602.08253","title":"G-LNS: Generative Large Neighborhood Search for LLM-Based Automatic Heuristic Design","created":"2026-02-09","cited_by_count":7,"area":null},{"id":"2403.10795","title":"Can Large Language Models Solve Robot Routing?","created":"2024-03-16","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":"2406.10479","title":"Unlocking Large Language Model's Planning Capabilities with Maximum Diversity Fine-tuning","created":"2024-06-15","cited_by_count":6,"area":"lr"},{"id":"2409.13445","title":"Selective Exploration and Information Gathering in Search and Rescue Using Hierarchical Learning Guided by Natural Language Input","created":"2024-09-20","cited_by_count":6,"area":null},{"id":"2502.19295","title":"Complex LLM Planning via Automated Heuristics Discovery","created":"2025-02-26","cited_by_count":6,"area":null},{"id":"2506.19592","title":"Adaptive Domain Modeling with Language Models: A Multi-Agent Approach to Task Planning","created":"2025-06-24","cited_by_count":6,"area":"agents"},{"id":"2511.01912","title":"EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memory","created":"2025-11-01","cited_by_count":6,"area":"agents"},{"id":"2601.20164","title":"What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering","created":"2026-01-28","cited_by_count":6,"area":"mechinterp"},{"id":"2408.16081","title":"Towards Logically Sound Natural Language Reasoning with Logic-Enhanced Language Model Agents","created":"2024-08-28","cited_by_count":5,"area":"lr"},{"id":"2409.07489","title":"RAGent: Retrieval-based Access Control Policy Generation","created":"2024-09-08","cited_by_count":5,"area":null},{"id":"2410.03348","title":"Dolphin: A Programmable Framework for Scalable Neurosymbolic Learning","created":"2024-10-04","cited_by_count":5,"area":"lr"},{"id":"2505.14656","title":"Cost-Awareness in Tree-Search LLM Planning: A Systematic Study","created":"2025-05-20","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":"2510.03182","title":"Simulation to Rules: A Dual-VLM Framework for Formal Visual Planning","created":"2025-10-03","cited_by_count":5,"area":"mllm"},{"id":"2510.12979","title":"DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping","created":"2025-10-14","cited_by_count":5,"area":"lr"},{"id":"2512.09629","title":"End-to-end PDDL Planning with Hardcoded and Dynamic Agents","created":"2025-12-10","cited_by_count":5,"area":"agents"},{"id":"2512.11143","title":"Automated Penetration Testing with LLM Agents and Classical Planning","created":"2025-12-11","cited_by_count":5,"area":"agents"},{"id":"2407.14055","title":"Quantum Hamiltonian Embedding of Images for Data Reuploading Classifiers","created":"2024-07-19","cited_by_count":4,"area":null},{"id":"2412.02897","title":"MLD-EA: Check and Complete Narrative Coherence by Introducing Emotions and Actions","created":"2024-12-03","cited_by_count":4,"area":null},{"id":"2503.19647","title":"Show or Tell? Effectively prompting Vision-Language Models for semantic segmentation","created":"2025-03-25","cited_by_count":4,"area":"mllm"},{"id":"2506.06008","title":"Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2506.07062","title":"Prime the search: Using large language models for guiding geometric task and motion planning by warm-starting tree search","created":"2025-06-08","cited_by_count":4,"area":null},{"id":"2509.18661","title":"Agentic AutoSurvey: Let LLMs Survey LLMs","created":"2025-09-23","cited_by_count":4,"area":"agents"},{"id":"2510.00182","title":"A Systematic Study of Large Language Models for Task and Motion Planning With PDDLStream","created":"2025-09-30","cited_by_count":4,"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":"2408.00386","title":"What comes after transformers? -- A selective survey connecting ideas in deep learning","created":"2024-08-01","cited_by_count":3,"area":null},{"id":"2409.18037","title":"HARMONIC: A Framework for Explanatory Cognitive Robots","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2410.04721","title":"ACDC: Autoregressive Coherent Multimodal Generation using Diffusion Correction","created":"2024-10-07","cited_by_count":3,"area":"diffusion"},{"id":"2501.18291","title":"CueTip: An Interactive and Explainable Physics-aware Pool Assistant","created":"2025-01-30","cited_by_count":3,"area":null}],"next_cursor":"100"}