{"total":125,"rows":[{"id":"2401.13178","title":"AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents","created":"2024-01-24","cited_by_count":339,"area":"agents"},{"id":"2409.00138","title":"PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action","created":"2024-08-29","cited_by_count":171,"area":null},{"id":"2404.11584","title":"The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey","created":"2024-04-17","cited_by_count":168,"area":"agents"},{"id":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146,"area":"lr"},{"id":"2402.15116","title":"Large Multimodal Agents: A Survey","created":"2024-02-23","cited_by_count":105,"area":"lr"},{"id":"2408.06327","title":"VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents","created":"2024-08-12","cited_by_count":103,"area":"mllm"},{"id":"2406.06613","title":"GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents","created":"2024-06-07","cited_by_count":95,"area":"lr"},{"id":"2402.17574","title":"Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization","created":"2024-02-27","cited_by_count":94,"area":"wm"},{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83,"area":null},{"id":"2410.15164","title":"SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation","created":"2024-10-19","cited_by_count":81,"area":"agents"},{"id":"2403.15371","title":"Can large language models explore in-context?","created":"2024-03-22","cited_by_count":76,"area":null},{"id":"2408.11824","title":"AppAgent v2: Advanced Agent for Flexible Mobile Interactions","created":"2024-08-05","cited_by_count":68,"area":"agents"},{"id":"2403.11807","title":"How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments","created":"2024-03-18","cited_by_count":67,"area":"agents"},{"id":"2402.06596","title":"Understanding the Weakness of Large Language Model Agents within a Complex Android Environment","created":"2024-02-09","cited_by_count":60,"area":"agents"},{"id":"2311.08562","title":"MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration","created":"2023-11-14","cited_by_count":57,"area":"agents"},{"id":"2505.15146","title":"lmgame-Bench: How Good are LLMs at Playing Games?","created":"2025-05-21","cited_by_count":55,"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":"2503.02268","title":"AppAgentX: Evolving GUI Agents as Proficient Smartphone Users","created":"2025-03-04","cited_by_count":46,"area":"agents"},{"id":"2409.00557","title":"Learning to Ask: When LLM Agents Meet Unclear Instruction","created":"2024-08-31","cited_by_count":42,"area":"agents"},{"id":"2406.14884","title":"FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents","created":"2024-06-21","cited_by_count":40,"area":"agents"},{"id":"2402.16499","title":"LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments","created":"2024-02-26","cited_by_count":36,"area":"agents"},{"id":"2406.05720","title":"VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft","created":"2024-06-09","cited_by_count":35,"area":null},{"id":"2504.18875","title":"Generative to Agentic AI: Survey, Conceptualization, and Challenges","created":"2025-04-26","cited_by_count":33,"area":"agents"},{"id":"2506.03610","title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","created":"2025-06-04","cited_by_count":31,"area":"agents"},{"id":"2410.05362","title":"LLMs Are In-Context Bandit Reinforcement Learners","created":"2024-10-07","cited_by_count":29,"area":null},{"id":"2505.13426","title":"G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning","created":"2025-05-19","cited_by_count":29,"area":"lr"},{"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":"2406.00092","title":"Heads, Tails, and AI Fails: LLMs, Randomness, and Human Judgments","created":"2024-05-31","cited_by_count":26,"area":null},{"id":"2503.23064","title":"VGRP-Bench: Visual Grid Reasoning Puzzle Benchmark for Large Vision-Language Models","created":"2025-03-29","cited_by_count":26,"area":"lr"},{"id":"2402.05733","title":"TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation","created":"2024-02-08","cited_by_count":23,"area":"agents"},{"id":"2503.06047","title":"DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM-based Agents in Complex Decision-Making Environments","created":"2025-03-08","cited_by_count":23,"area":"agents"},{"id":"2403.10249","title":"A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges","created":"2024-03-15","cited_by_count":22,"area":null},{"id":"2404.17833","title":"Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs","created":"2024-04-27","cited_by_count":22,"area":"agents"},{"id":"2407.07796","title":"Evaluating Large Language Models with Grid-Based Game Competitions: An Extensible LLM Benchmark and Leaderboard","created":"2024-07-10","cited_by_count":22,"area":null},{"id":"2505.16120","title":"LLM-Powered AI Agent Systems and Their Applications in Industry","created":"2025-05-22","cited_by_count":22,"area":"agents"},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"id":"2503.02358","title":"Are Large Vision Language Models Good Game Players?","created":"2025-03-04","cited_by_count":19,"area":"mllm"},{"id":"2602.07055","title":"Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?","created":"2026-02-04","cited_by_count":19,"area":null},{"id":"2502.09053","title":"Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers","created":"2025-02-13","cited_by_count":16,"area":null},{"id":"2406.18872","title":"Efficacy of Language Model Self-Play in Non-Zero-Sum Games","created":"2024-06-27","cited_by_count":15,"area":"synth"},{"id":"2404.11483","title":"AgentKit: Structured LLM Reasoning with Dynamic Graphs","created":"2024-04-17","cited_by_count":13,"area":"lr"},{"id":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"id":"2404.04363","title":"Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs","created":"2024-04-05","cited_by_count":12,"area":"diffusion"},{"id":"2405.18208","title":"A Human-Like Reasoning Framework for Multi-Phases Planning Task with Large Language Models","created":"2024-05-28","cited_by_count":12,"area":"lr"},{"id":"2410.06555","title":"ING-VP: MLLMs cannot Play Easy Vision-based Games Yet","created":"2024-10-09","cited_by_count":11,"area":"mllm"},{"id":"2411.18983","title":"SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing","created":"2024-11-28","cited_by_count":11,"area":null},{"id":"2505.00049","title":"Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications","created":"2025-04-30","cited_by_count":10,"area":"agents"},{"id":"2509.16330","title":"Generalizability of Large Language Model-Based Agents: A Comprehensive Survey","created":"2025-09-19","cited_by_count":10,"area":"agents"},{"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,"area":null},{"id":"2508.08501","title":"GVGAI-LLM: Evaluating Large Language Model Agents with Infinite Games","created":"2025-08-11","cited_by_count":9,"area":"agents"},{"id":"2511.01527","title":"TPS-Bench: Evaluating AI Agents' Tool Planning \\& Scheduling Abilities in Compounding Tasks","created":"2025-11-03","cited_by_count":9,"area":"agents"},{"id":"2405.20859","title":"clembench-2024: A Challenging, Dynamic, Complementary, Multilingual Benchmark and Underlying Flexible Framework for LLMs as Multi-Action Agents","created":"2024-05-31","cited_by_count":8,"area":"agents"},{"id":"2502.00225","title":"Should You Use Your Large Language Model to Explore or Exploit?","created":"2025-01-31","cited_by_count":8,"area":null},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2409.04475","title":"Revolutionizing Database Q&A with Large Language Models: Comprehensive Benchmark and Evaluation","created":"2024-09-05","cited_by_count":7,"area":null},{"id":"2502.00728","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2504.14773","title":"PLANET: A Collection of Benchmarks for Evaluating LLMs' Planning Capabilities","created":"2025-04-21","cited_by_count":7,"area":"agents"},{"id":"2506.02896","title":"FlySearch: Exploring how vision-language models explore","created":"2025-06-03","cited_by_count":7,"area":"mllm"},{"id":"2506.14512","title":"SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks","created":"2025-06-17","cited_by_count":7,"area":"lr"},{"id":"2509.14221","title":"GEM-Bench: A Benchmark for Ad-Injected Response Generation within Generative Engine Marketing","created":"2025-09-17","cited_by_count":7,"area":null},{"id":"2512.23676","title":"Web World Models","created":"2025-12-29","cited_by_count":7,"area":"wm"},{"id":"2410.13691","title":"Jailbreaking LLM-Controlled Robots","created":"2024-10-17","cited_by_count":6,"area":"safety"},{"id":"2412.13549","title":"EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents","created":"2024-12-18","cited_by_count":6,"area":"agents"},{"id":"2508.05338","title":"The Term 'Agent' Has Been Diluted Beyond Utility and Requires Redefinition","created":"2025-08-07","cited_by_count":6,"area":"agents"},{"id":"2508.12782","title":"HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds","created":"2025-08-18","cited_by_count":6,"area":"lr"},{"id":"2606.18543","title":"CEO-Bench: Can Agents Play the Long Game?","created":"2026-06-16","cited_by_count":6,"area":"agents"},{"id":"2402.07744","title":"Towards Unified Alignment Between Agents, Humans, and Environment","created":"2024-02-12","cited_by_count":5,"area":"agents"},{"id":"2503.10673","title":"ZeroSumEval: An Extensible Framework For Scaling LLM Evaluation with Inter-Model Competition","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2504.12562","title":"ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition","created":"2025-04-17","cited_by_count":5,"area":null},{"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":"2509.12718","title":"EvoEmpirBench: Dynamic Spatial Reasoning with Agent-ExpVer","created":"2025-09-16","cited_by_count":5,"area":"lr"},{"id":"2510.06475","title":"PuzzlePlex: Benchmarking Foundation Models on Reasoning and Planning with Puzzles","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2407.03964","title":"Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2407.07778","title":"WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment","created":"2024-07-10","cited_by_count":4,"area":"lr"},{"id":"2407.12734","title":"A LLM Benchmark based on the Minecraft Builder Dialog Agent Task","created":"2024-07-17","cited_by_count":4,"area":"agents"},{"id":"2505.10543","title":"Reasoning Capabilities of Large Language Models on Dynamic Tasks","created":"2025-05-15","cited_by_count":4,"area":"lr"},{"id":"2506.00739","title":"DefenderBench: A Toolkit for Evaluating Language Agents in Cybersecurity Environments","created":"2025-05-31","cited_by_count":4,"area":"agents"},{"id":"2508.16821","title":"PuzzleJAX: A Benchmark for Reasoning and Learning","created":"2025-08-22","cited_by_count":4,"area":"lr"},{"id":"2509.16610","title":"LLMsPark: A Benchmark for Evaluating Large Language Models in Strategic Gaming Contexts","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2510.10930","title":"Evaluating Language Models' Evaluations of Games","created":"2025-10-13","cited_by_count":4,"area":"lr"},{"id":"2602.05048","title":"MINT: Minimal Information Neuro-Symbolic Tree for Objective-Driven Knowledge-Gap Reasoning and Active Elicitation","created":"2026-02-04","cited_by_count":4,"area":"lr"},{"id":"2606.09826","title":"OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics","created":"2026-06-08","cited_by_count":4,"area":"agents"},{"id":"2406.11012","title":"Connecting the Dots: Evaluating Abstract Reasoning Capabilities of LLMs Using the New York Times Connections Word Game","created":"2024-06-16","cited_by_count":3,"area":"lr"},{"id":"2505.09396","title":"The Influence of Human-inspired Agentic Sophistication in LLM-driven Strategic Reasoners","created":"2025-05-14","cited_by_count":3,"area":"lr"},{"id":"2507.08491","title":"A Third Paradigm for LLM Evaluation: Dialogue Game-Based Evaluation using clembench","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2509.01052","title":"FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games","created":"2025-09-01","cited_by_count":3,"area":"agents"},{"id":"2509.24923","title":"When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2601.09503","title":"What Do LLM Agents Know About Their World? Task2Quiz: A Paradigm for Studying Environment Understanding","created":"2026-01-14","cited_by_count":3,"area":"agents"},{"id":"2605.09965","title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2411.12828","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","created":"2024-11-19","cited_by_count":2,"area":"agents"},{"id":"2504.08590","title":"Playpen: An Environment for Exploring Learning Through Conversational Interaction","created":"2025-04-11","cited_by_count":2,"area":"alignment"},{"id":"2505.12135","title":"LLM-BabyBench: Can Language Models Plan in Worlds They Can Simulate?","created":"2025-05-17","cited_by_count":2,"area":"agents"},{"id":"2510.08872","title":"GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfare","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2512.08104","title":"AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration","created":"2025-12-08","cited_by_count":2,"area":"agents"},{"id":"2603.20209","title":"Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2607.13705","title":"AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities","created":"2026-07-15","cited_by_count":2,"area":"agents"},{"id":"2607.29218","title":"MirrorCraft: Paired Evaluation under Hidden Rule Changes in Minecraft","created":"2026-07-31","cited_by_count":2,"area":"agents"},{"id":"2609.31473","title":"Game Arena: Strategic LLM Evaluation in Competitive Environments","created":"2026-09-25","cited_by_count":2,"area":null},{"id":"2410.18529","title":"Instructional Text Across Disciplines: A Survey of Representations, Downstream Tasks, and Open Challenges Toward Capable AI Agents","created":"2024-10-24","cited_by_count":1,"area":"agents"},{"id":"2501.08925","title":"Disentangling Exploration of Large Language Models by Optimal Exploitation","created":"2025-01-15","cited_by_count":1,"area":null}],"next_cursor":"100"}