{"total":25,"rows":[{"id":"2307.04738","title":"RoCo: Dialectic Multi-Robot Collaboration with Large Language Models","created":"2023-07-10","cited_by_count":172,"area":null},{"id":"2311.01677","title":"DialogBench: Evaluating LLMs as Human-like Dialogue Systems","created":"2023-11-03","cited_by_count":31,"area":null},{"id":"2504.11442","title":"TextArena","created":"2025-04-15","cited_by_count":27,"area":null},{"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":"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":"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":"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":"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":"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":"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":"2510.27163","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":"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":"2608.23969","title":"Investigating Knowledge Transfer Across Interactive Dialogue Games","created":"2026-08-25","cited_by_count":0,"area":null},{"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":"2610.19213","title":"PREFER: From Player Experience to Personalized Game Refinement","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}