TextCraft

The 'TextCraft' dataset/benchmark contains a collection of text-based environments used to evaluate the performance of language models in long-term planning and reasoning tasks.

Papers using TextCraft (4)

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade2026SCOPE: Language Models as One-Time Teacher for Hierarchical Planning in Text Environments2025Reflect before Act: Proactive Error Correction in Language Models2025StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking2024