paper-with-me

홈 › Papers

Retrieval-Augmented Code Generation for Situated Action Generation: A Case Study on Minecraft

2024-06-25 · Chalamalasetti Kranti, Sherzod Hakimov, David Schlangen

In the Minecraft Collaborative Building Task, two players collaborate: an Architect (A) provides instructions to a Builder (B) to assemble a specified structure using 3D blocks. In this work, we investigate the use of large language models (LLMs) to predict the sequence of actions taken by the Builder. Leveraging LLMs' in-context learning abilities, we use few-shot prompting techniques, that significantly improve performance over baseline methods. Additionally, we present a detailed analysis of the gaps in performance for future work

📄 PDF Abstract BibTeX arXiv:2406.17553

Code (0)

등록된 구현이 없습니다.

Tasks

Action GenerationCode GenerationIn-Context LearningMinecraftRetrieval

Similar Papers 제목 키워드 기반

SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension

2025-08-03 · Junjie Wu, Jiangnan Li, Yuqing Li, Lemao Liu 외 arxiv

Retrieval-augmented generation (RAG) over long documents typically involves splitting the text into smaller chunks, which serve as the basic units for retrieval. However, due to dependencies across the original document,…

Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation

2024-06-01 · Zijie Zhong, Hanwen Liu, Xiaoya Cui, Xiaofan Zhang 외

Integrating information from various reference databases is a major challenge for Retrieval-Augmented Generation (RAG) systems because each knowledge source adopts a unique data structure and follows different convention…

ChunkingRAGRetrievalRetrieval-augmented Generation

Learning to Embed Multi-Modal Contexts for Situated Conversational Agents

2022-01-16 · ACL ARR January 2022 1 · Anonymous

The Situated Interactive Multi-Modal Conversations (SIMMC) 2.0 aims to create virtual shopping assistants that can accept complex multi-modal inputs, i.e. visual appearances of objects and user utterances. It consists of…

coreference-resolutionCoreference ResolutionDecoderdialog state tracking+2

Learning to Embed Multi-Modal Contexts for Situated Conversational Agents

2022-07-01 · Findings (NAACL) 2022 7 · Haeju Lee, Oh Joon Kwon, Yunseon Choi, Minho Park 외

The Situated Interactive Multi-Modal Conversations (SIMMC) 2.0 aims to create virtual shopping assistants that can accept complex multi-modal inputs, i.e. visual appearances of objects and user utterances. It consists of…

coreference-resolutionCoreference ResolutionDecoderdialog state tracking+3

ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement

2025-04-29 · Manish Bhattarai, Miguel Cordova, Javier Santos, Dan O'Malley

In supercomputing, efficient and optimized code generation is essential to leverage high-performance systems effectively. We propose Agentic Retrieval-Augmented Code Synthesis (ARCS), an advanced framework for accurate, …

Code GenerationHumanEvalRAGRetrieval+2