Grounding Large Language Models In Embodied Environment With Imperfect World Models
원문 초록
Despite a widespread success in various applications, large language models (LLMs) often stumble when tackling basic physical reasoning or executing robotics tasks, due to a lack of direct experience with the physical nuances of the real world. To address these issues, we propose a Grounding Large language model with Imperfect world MOdel (GLIMO), which utilizes proxy world models such as simulators to collect and synthesize trining data. GLIMO incorporates an LLM agent-based data generator to automatically create high-quality and diverse instruction datasets. The generator includes an iterative self-refining module for temporally consistent experience sampling, a diverse set of question-answering instruction seeds, and a retrieval-augmented generation module for reflecting on prior experiences. Comprehensive experiments show that our approach improve the performance of strong open-source LLMs like LLaMA-3 with a performance boost of 2.04 $\times$, 1.54 $\times$, and 1.82 $\times$ across three different benchmarks, respectively. The performance is able to compete with or surpass their larger counterparts such as GPT-4.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
RMIT-ADM+S at the SIGIR 2025 LiveRAG Challenge
OpenTable-R1: A Reinforcement Learning Augmented Tool Agent for Open-Domain Table Question Answering
Large Language Model Agent for Modular Task Execution in Drug Discovery
Enterprise Large Language Model Evaluation Benchmark
From RAG to Agentic: Validating Islamic-Medicine Responses with LLM Agents
Parameter Efficient Fine Tuning Llama 3.1 for Answering Arabic Legal Questions: A Case Study on Jordanian Laws
토론
이 논문과 연결된 포럼 글이 아직 없습니다.