{"total":54,"rows":[{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242,"area":"agents"},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212,"area":"agents"},{"id":"2307.04738","title":"RoCo: Dialectic Multi-Robot Collaboration with Large Language Models","created":"2023-07-10","cited_by_count":172,"area":null},{"id":"2402.12348","title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","created":"2024-02-19","cited_by_count":120,"area":"lr"},{"id":"2404.02039","title":"A Survey on Large Language Model-Based Game Agents","created":"2024-04-02","cited_by_count":112,"area":"agents"},{"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":"2412.03563","title":"From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents","created":"2024-12-04","cited_by_count":82,"area":"agents"},{"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,"area":"lr"},{"id":"2311.01677","title":"DialogBench: Evaluating LLMs as Human-like Dialogue Systems","created":"2023-11-03","cited_by_count":31,"area":null},{"id":"2404.06411","title":"AgentQuest: A Modular Benchmark Framework to Measure Progress and Improve LLM Agents","created":"2024-04-09","cited_by_count":28,"area":"agents"},{"id":"2504.11442","title":"TextArena","created":"2025-04-15","cited_by_count":27,"area":null},{"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":"2408.01417","title":"Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs","created":"2024-08-02","cited_by_count":18,"area":"mllm"},{"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":"2405.05688","title":"Evaluating Dialect Robustness of Language Models via Conversation Understanding","created":"2024-05-09","cited_by_count":14,"area":null},{"id":"2502.14359","title":"Triangulating LLM Progress through Benchmarks, Games, and Cognitive Tests","created":"2025-02-20","cited_by_count":12,"area":null},{"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":"2509.03805","title":"Measuring How (Not Just Whether) VLMs Build Common Ground","created":"2025-09-04","cited_by_count":8,"area":"lr"},{"id":"2601.08462","title":"M3-BENCH: Process-Aware Evaluation of LLM Agents' Social Behaviors in Mixed-Motive Games","created":"2026-01-13","cited_by_count":8,"area":"agents"},{"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":"2510.24023","title":"Success and Cost Elicit Convention Formation for Efficient Communication","created":"2025-10-28","cited_by_count":7,"area":null},{"id":"2409.00358","title":"Predicting the Target Word of Game-playing Conversations using a Low-Rank Dialect Adapter for Decoder Models","created":"2024-08-31","cited_by_count":6,"area":null},{"id":"2505.05445","title":"clem:todd: A Framework for the Systematic Benchmarking of LLM-Based Task-Oriented Dialogue System Realisations","created":"2025-05-08","cited_by_count":4,"area":null},{"id":"2406.14035","title":"Using Game Play to Investigate Multimodal and Conversational Grounding in Large Multimodal Models","created":"2024-06-20","cited_by_count":3,"area":"mllm"},{"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":"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":"2605.17829","title":"Interactive Evaluation Requires a Design Science","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2409.11041","title":"Towards No-Code Programming of Cobots: Experiments with Code Synthesis by Large Code Models for Conversational Programming","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2504.08590","title":"Playpen: An Environment for Exploring Learning Through Conversational Interaction","created":"2025-04-11","cited_by_count":2,"area":"alignment"},{"id":"2509.17192","title":"Shall We Play a Game? Language Models for Open-ended Wargames","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2510.13271","title":"Do You Get the Hint? Benchmarking LLMs on the Board Game Concept","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2502.11707","title":"Ad-hoc Concept Forming in the Game Codenames as a Means for Evaluating Large Language Models","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2502.11733","title":"Plant in Cupboard, Orange on Rably, Inat Aphone. Benchmarking Incremental Learning of Situation and Language Model using a Text-Simulated Situated Environment","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2509.17694","title":"Evaluating LLM-Generated Versus Human-Authored Responses in Role-Play Dialogues","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2510.19892","title":"Can They Dixit? Yes they Can! Dixit as a Playground for Multimodal Language Model Capabilities","created":"2025-10-22","cited_by_count":1,"area":"mllm"},{"id":"2601.10809","title":"A Concise Agent is Less Expert: Revealing Side Effects of Using Style Features on Conversational Agents","created":"2026-01-15","cited_by_count":1,"area":"agents"},{"id":"2310.11249","title":"Leveraging Large Language Model for Automatic Evolving of Industrial Data-Centric R&D Cycle","created":"2023-10-17","cited_by_count":0,"area":null},{"id":"2310.18038","title":"On General Language Understanding","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2406.14051","title":"How Many Parameters Does it Take to Change a Light Bulb? Evaluating Performance in Self-Play of Conversational Games as a Function of Model Characteristics","created":"2024-06-20","cited_by_count":0,"area":"synth"},{"id":"2409.11112","title":"Strategic Insights in Human and Large Language Model Tactics at Word Guessing Games","created":"2024-09-17","cited_by_count":0,"area":null},{"id":"2510.21306","title":"PARL: Prompt-based Agents for Reinforcement Learning","created":"2025-10-24","cited_by_count":0,"area":"lr"},{"id":"2510.27163","title":"MARIA: A Framework for Marginal Risk Assessment without Ground Truth in AI Systems","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2606.01901","title":"The Image Reconstruction Game: Drawing Common Ground Through Iterative Multimodal Dialogue","created":"2026-06-01","cited_by_count":0,"area":"mllm"},{"id":"2606.19338","title":"Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games","created":"2026-06-17","cited_by_count":0,"area":"mllm"},{"id":"2608.01395","title":"Language Equality has a Price: A Systematic Investigation of Multi-turn LLM Performance for EU-24+","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.03388","title":"Don't Let Me Ask for It: LLMs Show Deficiencies in Active Multi-Turn Information Acquisition for Abductive Inference","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2608.23969","title":"Investigating Knowledge Transfer Across Interactive Dialogue Games","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.27672","title":"First Make It Playable, Then Make It Good: Staged Interaction Learning for Small Dialogue-Game Agents","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2608.28458","title":"Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training Recipe for Small-Model Dialogue Game Agents","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.18736","title":"Clueing up LLMs with Tool-Augmented Deductive Reasoning","created":"2026-09-16","cited_by_count":0,"area":"lr"},{"id":"2610.13703","title":"A Baseline Assessment for the Agentic Web Technology Stack","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.19213","title":"PREFER: From Player Experience to Personalized Game Refinement","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}