paper-with-me

홈 › Papers

WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment

2024-02-19 · Hao Tang, Darren Key, Kevin Ellis

We give a model-based agent that builds a Python program representing its knowledge of the world based on its interactions with the environment. The world model tries to explain its interactions, while also being optimistic about what reward it can achieve. We define this optimism as a logical constraint between a program and a planner. We study our agent on gridworlds, and on task planning, finding our approach is more sample-efficient compared to deep RL, more compute-efficient compared to ReAct-style agents, and that it can transfer its knowledge across environments by editing its code.

📄 PDF Abstract BibTeX arXiv:2402.12275

Code (0)

등록된 구현이 없습니다.

Tasks

Program SynthesisTask Planning

Similar Papers 제목 키워드 기반

WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis

2026-06-01 · Shuo Lu, Yinuo Xu, Kecheng Yu, Siru Jiang 외 arxiv

Large language models (LLMs) are increasingly asked not only to write static interfaces, but to construct executable interactive worlds from natural language. Browser-native 3D, commonly built with Three.js, is a natural…

Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents

2026-01-31 · Zergham Ahmed, Kazuki Irie, Joshua B. Tenenbaum, Christopher J. Bates 외 arxiv

Humans learn abstractions and use them to plan efficiently to quickly generalize across tasks -- an ability that remains challenging for state-of-the-art large language model (LLM) agents and deep reinforcement learning …

Reinforcement Learning

Creative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writers

2022-11-09 · Daphne Ippolito, Ann Yuan, Andy Coenen, Sehmon Burnam

Recent developments in natural language generation (NLG) using neural language models have brought us closer than ever to the goal of building AI-powered creative writing tools. However, most prior work on human-AI colla…

Text Generation

ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm

2026-07-11 · Kefan Song, Yanjun Qi arxiv

Autonomous CLI agents can now execute hundreds of actions across multi-hour sessions: writing code, executing shell commands, browsing the web, and managing cloud infrastructure, all with minimal human oversight. Does gr…

Contrastive Masked Autoencoders for Character-Level Open-Set Writer Identification

2025-01-21 · Xiaowei Jiang, Wenhao Ma, Yiqun Duan, Thomas Do 외

In the realm of digital forensics and document authentication, writer identification plays a crucial role in determining the authors of documents based on handwriting styles. The primary challenge in writer-id is the "op…

Contrastive LearningRepresentation Learning