# Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning

arXiv: https://arxiv.org/abs/2309.01352 · HTML: https://mlsanity.com/paper/2309.01352/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 4 Sep 2023.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 17 of 17)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [ScienceWorld: Is your Agent Smarter than a 5th Grader?](https://mlsanity.com/paper/2203.07540/) (2022)
- [BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning](https://mlsanity.com/paper/1810.08272/) (2018)
- [Pre-Trained Language Models for Interactive Decision-Making](https://mlsanity.com/paper/2202.01771/) (2022)
- [Language Conditioned Imitation Learning over Unstructured Data](https://mlsanity.com/paper/2005.07648/) (2020)
- [Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning](https://mlsanity.com/paper/2302.02662/) (2023)
- [Learning to Understand Goal Specifications by Modelling Reward](https://mlsanity.com/paper/1806.01946/) (2018)
- [Gated-Attention Architectures for Task-Oriented Language Grounding](https://mlsanity.com/paper/1706.07230/) (2017)
- [Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning](https://mlsanity.com/paper/2011.00517/) (2020)
- [LISA: Learning Interpretable Skill Abstractions from Language](https://mlsanity.com/paper/2203.00054/) (2022)
- [CAPE: Corrective Actions from Precondition Errors using Large Language Models](https://mlsanity.com/paper/2211.09935/) (2022)
- [Grounding Hindsight Instructions in Multi-Goal Reinforcement Learning for Robotics](https://mlsanity.com/paper/2204.04308/) (2022)

## Built on by (most cited first, 9 of 9)

- [Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning](https://mlsanity.com/paper/2412.11120/) (2024)
- [Context Shift Reduction for Offline Meta-Reinforcement Learning](https://mlsanity.com/paper/2311.03695/) (2023)
- [Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2311.01075/) (2023)
- [Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies](https://mlsanity.com/paper/2402.03628/) (2024)
- [Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment](https://mlsanity.com/paper/2406.01103/) (2024)
- [Luban: Building Open-Ended Creative Agents via Autonomous Embodied Verification](https://mlsanity.com/paper/2405.15414/) (2024)
- [A Taxonomy of Architecture Options for Foundation Model-based Agents: Analysis and Decision Model](https://mlsanity.com/paper/2408.02920/) (2024)
- [A Hormetic Approach to the Value-Loading Problem: Preventing the Paperclip Apocalypse?](https://mlsanity.com/paper/2402.07462/) (2024)
- [Code Driven Planning with Domain-Adaptive Critic](https://mlsanity.com/paper/2509.19077/) (2025)

## Abstract (arXiv)

Large language models (LLMs) show their powerful automatic reasoning and planning capability with a wealth of semantic knowledge about the human world. However, the grounding problem still hinders the applications of LLMs in the real-world environment. Existing studies try to fine-tune the LLM or utilize pre-defined behavior APIs to bridge the LLMs and the environment, which not only costs huge human efforts to customize for every single task but also weakens the generality strengths of LLMs. To autonomously ground the LLM onto the environment, we proposed the Self-Driven Grounding (SDG) framework to automatically and progressively ground the LLM with self-driven skill learning. SDG first employs the LLM to propose the hypothesis of sub-goals to achieve tasks and then verify the feasibility of the hypothesis via interacting with the underlying environment. Once verified, SDG can then learn generalized skills with the guidance of these successfully grounded subgoals. These skills can be further utilized to accomplish more complex tasks which fail to pass the verification phase. Verified in the famous instruction following task set-BabyAI, SDG achieves comparable performance in the most challenging tasks compared with imitation learning methods that cost millions of demonstrations, proving the effectiveness of learned skills and showing the feasibility and efficiency of our framework.