Outstanding Papers
- Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games
- Wordcaster: A Gamified Speech-Based Reading Game for Young Learners Using Real-Time ASR
- Real-Time World Crafting: Generating Structured Game Behaviors from Natural Language with Large Language Models
- Model Fusion with Multi-LoRA Inference for Tool-Enhanced Game Dialogue Agents
Spotlight Papers
- Can They Dixit? Yes they Can! Dixit as a Playground for Multimodal Language Model Capabilities
- TextGames: Learning to Self-Play Text-Based Puzzle Games via Language Model Reasoning
- Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting
- FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games
- Efficient Tool-Calling Multi-Expert NPC Agent for Commonsense Persona-Grounded Dialogue
- VLM-Dixit: Investigating Multi-Modal Abductive Reasoning and Entailment Verification with VLMs in Dixit Gameplay
- Explore Branches the Story didn’t Narrate: An LLM Solution
Poster Papers
- WHAT-IF: Exploring Branching Narratives by Meta-Prompting Large Language Models
- CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures
- Memory-Augmented Language Models for Persistent Interactive Narratives
- Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents
- Design Techniques for LLM-Powered Interactive Storytelling: A Case Study of the Dramamancer System
- MATE: Explore the Reasoning Capability of LLMs in the Chess Testbed
- TRPG Game Mastering Using LLM-Based Multi-Agent System
- Two-Stage Tool-Enhanced NPC Dialogue for CPDC 2025: GPU-Track Submission to Task 1 and Task 2
- GenQuest: An LLM-based Text Adventure Game for Language Learners
- BaZi-Based Character Simulation Benchmark: Evaluating AI on Temporal and Persona Reasoning1
- Inference-Time Value Alignment in Offline Reinforcement Learning: Leveraging LLMs for Reward and Ethical Guidance
- LLM-Hanabi: Evaluating Multi-Agent Gameplays with Theory-of-Mind and Rationale Inference in Imperfect Information Collaboration Game
- Exploring Cooperative Behavior in LLMs with Game Theory
- Interactive AI NPCs Powered by LLMs: Technical Report for the CPDC Challenge 2025
- Does Reasoning Help LLM Agents Play Dungeons and Dragons? A Prompt Engineering Experiment
- Sarc7: Evaluating Sarcasm Detection and Generation with Seven Types and Emotion-Informed Techniques
- Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness
- DefenderBench: A Toolkit for Evaluating Language Agents in Cybersecurity Environments
- Evaluating LLM Story Generation through Large-scale Network Analysis of Social Structures
- ByteSized32Refactored: Towards an Extensible Interactive Text Games Corpus for LLM World Modeling and Evaluation
- On Generating Consistent and Attractive Promotional Introduction Text for Narrative Media Arts
- Deflanderization for Game Dialogue: Balancing Character Authenticity with Task Execution in LLM-based NPCs
- Beyond One World: Benchmarking Super Heros in Role-Playing Across Multiversal Contexts
- Rational Irrationality: Evaluating LLMs in Games with Strategic Behavior Discrepancies
- Shall We Play a Game? Language Models for Open-ended Wargames
- Iterative Prompt Engineering for NPC Dialogue Generation: CPDC 2025 API Track
-
Neither EMNLP nor the Wordplay Workshop is backing the metaphysics concepts; we see value of the work under the context of game generation and storytelling. ↩