EscapeBench: Pushing Language Models to Think Outside the Box

ACL ARR 2024 December Submission779 Authors

Abstract:

Language model agents excel in long-session planning and reasoning, but existing benchmarks primarily focus on goal-oriented tasks with explicit objectives, neglecting creative adaptation in unfamiliar environments. To address this, we introduce EscapeBench—a benchmark suite of room escape game environments designed to challenge agents with creative reasoning, unconventional tool use, and iterative problem-solving to uncover implicit goals.
Our results show that current LM models, despite employing working memory and Chain-of-Thought reasoning, achieve only 15% average progress without hints, highlighting their limitations in creativity. To bridge this gap, we propose EscapeAgent, a framework designed to enhance creative reasoning through Foresight (innovative tool use) and Reflection (identifying unsolved tasks). Experiments show that EscapeAgent can execute action chains over 1,000 steps while maintaining logical coherence. It navigates and completes games with up to 40% fewer steps and hints, performs robustly across difficulty levels, and achieves higher action success rates with more efficient and innovative puzzle-solving strategies.

Paper Type: Long

Research Area: Resources and Evaluation

Research Area Keywords: Agent Creativity, Model Evaluation, Benchmarking Environment

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources, Data analysis

Languages Studied: English

Submission Number: 779