Scholarlink

Abstract <p>Safe reinforcement learning under natural language instructions remains challenging. Current benchmarks are limited by providing only safety constraints in natural language while using structured goal representations, and by focusing on simple navigation tasks in static environments. We introduce <b>Caged CrafText</b>, the first benchmark where both task objectives and safety constraints are specified entirely through natural language. Our benchmark features complex, long-horizon tasks requiring reasoning in dynamic environments, and is structured around two dataset levels: the Main dataset, designed to evaluate language understanding and safe exploration capabilities across aggregated constraint types, and the Debug dataset, which enables detailed diagnosis of specific failure modes in individual constraint scenarios. Evaluation of existing safety approaches reveals their insufficient safe exploration capability, highlighting the need for improved methods capable of handling complex language-guided constraints. Our experiments also demonstrate that while Large Language Model(LLM) agents show promising reasoning capabilities, they suffer from grounding issues that lead to frequent constraint violations.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Caged CrafText: Language-Grounded Safety Constraints for Multimodal Reinforcement Learning in CrafText

  • 期刊论文

  • 发表日期：

    2026年3月26日

查看全文
  • G. Gorbov,
  • D. Lukashevsky,
  • A. Skrynnik,
  • A. Panov

摘要

Abstract

Safe reinforcement learning under natural language instructions remains challenging. Current benchmarks are limited by providing only safety constraints in natural language while using structured goal representations, and by focusing on simple navigation tasks in static environments. We introduce Caged CrafText, the first benchmark where both task objectives and safety constraints are specified entirely through natural language. Our benchmark features complex, long-horizon tasks requiring reasoning in dynamic environments, and is structured around two dataset levels: the Main dataset, designed to evaluate language understanding and safe exploration capabilities across aggregated constraint types, and the Debug dataset, which enables detailed diagnosis of specific failure modes in individual constraint scenarios. Evaluation of existing safety approaches reveals their insufficient safe exploration capability, highlighting the need for improved methods capable of handling complex language-guided constraints. Our experiments also demonstrate that while Large Language Model(LLM) agents show promising reasoning capabilities, they suffer from grounding issues that lead to frequent constraint violations.