LLM-in-Sandbox Elicits General Agentic Intelligence

• URL: http://arxiv.org/abs/2601.16206v1
• Date: Thu, 22 Jan 2026 18:57:09 GMT
• Title: LLM-in-Sandbox Elicits General Agentic Intelligence
• Authors: Daixuan Cheng, Shaohan Huang, Yuxian Gu, Huatong Song, Guoxin Chen, Li Dong, Wayne Xin Zhao, Ji-Rong Wen, Furu Wei,
• Abstract summary: We introduce LLM-in-Sandbox, enabling LLMs to explore within a code sandbox (i.e., a virtual computer) to elicit general intelligence in non-code domains.<n>We show that strong LLMs, without additional training, exhibit generalization capabilities to leverage the code sandbox for non-code tasks.<n>Experiments demonstrate that LLM-in-Sandbox, in both training-free and post-trained settings, achieves robust generalization spanning mathematics, physics, chemistry, biomedicine, long-context understanding, and instruction following.
• Score: 142.7174116109795
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce LLM-in-Sandbox, enabling LLMs to explore within a code sandbox (i.e., a virtual computer), to elicit general intelligence in non-code domains. We first demonstrate that strong LLMs, without additional training, exhibit generalization capabilities to leverage the code sandbox for non-code tasks. For example, LLMs spontaneously access external resources to acquire new knowledge, leverage the file system to handle long contexts, and execute scripts to satisfy formatting requirements. We further show that these agentic capabilities can be enhanced through LLM-in-Sandbox Reinforcement Learning (LLM-in-Sandbox-RL), which uses only non-agentic data to train models for sandbox exploration. Experiments demonstrate that LLM-in-Sandbox, in both training-free and post-trained settings, achieves robust generalization spanning mathematics, physics, chemistry, biomedicine, long-context understanding, and instruction following. Finally, we analyze LLM-in-Sandbox's efficiency from computational and system perspectives, and open-source it as a Python package to facilitate real-world deployment.

Related papers

• LLM Enhancer: Merged Approach using Vector Embedding for Reducing Large Language Model Hallucinations with External Knowledge [0.0]
  Large Language Models (LLMs) have demonstrated the capability to generate human like, natural responses across a range of tasks.<n>This paper introduces the LLM ENHANCER system, designed to integrate multiple online sources such as Google, Wikipedia, and DuckDuckGo to enhance data accuracy.
  arXiv  Detail & Related papers  (2025-04-29T19:27:04Z)
• Multi-Programming Language Sandbox for LLMs [78.99934332554963]
  out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs) It can automatically identify the programming language of the code, compiling and executing it within an isolated sub-sandbox to ensure safety and stability.
  arXiv  Detail & Related papers  (2024-10-30T14:46:43Z)
• ST-LLM: Large Language Models Are Effective Temporal Learners [58.79456373423189]
  Large Language Models (LLMs) have showcased impressive capabilities in text comprehension and generation. How to effectively encode and understand videos in video-based dialogue systems remains to be solved. We propose ST-LLM, an effective video-LLM baseline with spatial-temporal sequence modeling inside LLM.
  arXiv  Detail & Related papers  (2024-03-30T10:11:26Z)
• If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents [81.60906807941188]
  Large language models (LLMs) are trained on a combination of natural language and formal language (code) Code translates high-level goals into executable steps, featuring standard syntax, logical consistency, abstraction, and modularity.
  arXiv  Detail & Related papers  (2024-01-01T16:51:20Z)
• Video Understanding with Large Language Models: A Survey [107.7736911322462]
  Given the remarkable capabilities of large language models (LLMs) in language and multimodal tasks, this survey provides a detailed overview of recent advancements in video understanding.<n>The emergent capabilities Vid-LLMs are surprisingly advanced, particularly their ability for open-ended multi-granularity reasoning.<n>This survey presents a comprehensive study of the tasks, datasets, benchmarks, and evaluation methodologies for Vid-LLMs.
  arXiv  Detail & Related papers  (2023-12-29T01:56:17Z)
• Towards Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs [72.49064988035126]
  We propose an approach called MKS2, aimed at enhancing multimodal large language models (MLLMs) Specifically, we introduce the Modular Visual Memory, a component integrated into the internal blocks of LLMs, designed to store open-world visual information efficiently. Our experiments demonstrate that MKS2 substantially augments the reasoning capabilities of LLMs in contexts necessitating physical or commonsense knowledge.
  arXiv  Detail & Related papers  (2023-11-27T12:29:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.