paper-with-me

Papers

A Data Source for Reasoning Embodied Agents

2023-09-14 · Jack Lanchantin, Sainbayar Sukhbaatar, Gabriel Synnaeve, Yuxuan Sun, Kavya Srinet, Arthur Szlam

Recent progress in using machine learning models for reasoning tasks has been driven by novel model architectures, large-scale pre-training protocols, and dedicated reasoning datasets for fine-tuning. In this work, to further pursue these advances, we introduce a new data generator for machine reasoning that integrates with an embodied agent. The generated data consists of templated text queries and answers, matched with world-states encoded into a database. The world-states are a result of both world dynamics and the actions of the agent. We show the results of several baseline models on instantiations of train sets. These include pre-trained language models fine-tuned on a text-formatted representation of the database, and graph-structured Transformers operating on a knowledge-graph representation of the database. We find that these models can answer some questions about the world-state, but struggle with others. These results hint at new research directions in designing neural reasoning models and database representations. Code to generate the data will be released at github.com/facebookresearch/neuralmemory

📄 PDF Abstract BibTeX arXiv:2309.07974

Code (1)

facebookresearch/neuralmemory 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

HINT An unsupervised approach for identifying Hierarchical Information Threads by analysing the network of related articles in a collection. In particular, HINT leverages article…

Similar Papers 제목 키워드 기반

When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making

2026-03-17 · Jun Liu, Pu Zhao, Zhenglun Kong, Xuan Shen 외 arxiv

Embodied robotic systems increasingly rely on large language model (LLM)-based agents to support high-level reasoning, planning, and decision-making during interactions with the environment. However, invoking LLM reasoni…

Reinforcement Learning

Guava: An Effective and Universal Harness for Embodied Manipulation

2026-06-16 · Haowen Liu, Xirui Li, Shaoxiong Yao, Peng Shi 외 arxiv

Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents. Harnessing models through embodied tools use offers a promising alternative to end-to-end vision-languag…

HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents

2026-04-08 · Tencent Robotics X, HY Vision Team, :, Xumin Yu 외 arxiv

We introduce HY-Embodied-0.5, a family of foundation models specifically designed for real-world embodied agents. To bridge the gap between general Vision-Language Models (VLMs) and the demands of embodied agents, our mo…

Spatial Reasoning

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

2025-02-13 · Rui Yang, Hanyang Chen, Junyu Zhang, Mark Zhao 외

Leveraging Multi-modal Large Language Models (MLLMs) to create embodied agents offers a promising avenue for tackling real-world tasks. While language-centric embodied agents have garnered substantial attention, MLLM-bas…

Benchmarking

Software Engineering Agents for Embodied Controller Generation : A Study in Minigrid Environments

2025-10-24 · Timothé Boulet, Xavier Hinaut, Clément Moulin-Frier arxiv

Software Engineering Agents (SWE-Agents) have proven effective for traditional software engineering tasks with accessible codebases, but their performance for embodied tasks requiring well-designed information discovery …