paper-with-me

Papers

Large Language Model (LLM) as a System of Multiple Expert Agents: An Approach to solve the Abstraction and Reasoning Corpus (ARC) Challenge

2023-10-08 · John Chong Min Tan, Mehul Motani

We attempt to solve the Abstraction and Reasoning Corpus (ARC) Challenge using Large Language Models (LLMs) as a system of multiple expert agents. Using the flexibility of LLMs to be prompted to do various novel tasks using zero-shot, few-shot, context-grounded prompting, we explore the feasibility of using LLMs to solve the ARC Challenge. We firstly convert the input image into multiple suitable text-based abstraction spaces. We then utilise the associative power of LLMs to derive the input-output relationship and map this to actions in the form of a working program, similar to Voyager / Ghost in the MineCraft. In addition, we use iterative environmental feedback in order to guide LLMs to solve the task. Our proposed approach achieves 50 solves out of 111 training set problems (45%) with just three abstraction spaces - grid, object and pixel - and we believe that with more abstraction spaces and learnable actions, we will be able to solve more.

📄 PDF Abstract BibTeX arXiv:2310.05146

Code (1)

tanchongmin/arc-challenge 공식 구현

Tasks

ARCLanguage ModelingLanguage ModellingLarge Language ModelMinecraft

Similar Papers 제목 키워드 기반

EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms

2024-06-20 · Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan 외

The rise of powerful large language models (LLMs) has spurred a new trend in building LLM-based autonomous agents for solving complex tasks, especially multi-agent systems. Despite the remarkable progress, we notice that…

Evolutionary Algorithms

How to Build AI Agents by Augmenting LLMs with Codified Human Expert Domain Knowledge? A Software Engineering Framework

2026-01-21 · Choro Ulan uulu, Mikhail Kulyabin, Iris Fuhrmann, Jan Joosten 외 arxiv

Critical domain knowledge typically resides with few experts, creating organizational bottlenecks in scalability and decision-making. Non-experts struggle to create effective visualizations, leading to suboptimal insight…

Code Generation

Large Language Model-Based Agents for Software Engineering: A Survey

2024-09-04 · Junwei Liu, Kaixin Wang, Yixuan Chen, Xin Peng 외

The recent advance in Large Language Models (LLMs) has shaped a new paradigm of AI agents, i.e., LLM-based agents. Compared to standalone LLMs, LLM-based agents substantially extend the versatility and expertise of LLMs …

AI AgentLanguage ModelingLanguage ModellingLarge Language Model+1

Diagnostics of cognitive failures in multi-agent expert systems using dynamic evaluation protocols and subsequent mutation of the processing context

2025-09-18 · Andrejs Sorstkins, Josh Bailey, Dr Alistair Baron arxiv

The rapid evolution of neural architectures - from multilayer perceptrons to large-scale Transformer-based models - has enabled language models (LLMs) to exhibit emergent agentic behaviours when equipped with memory, pla…

HedgeAgents: A Balanced-aware Multi-agent Financial Trading System

2025-02-17 · Xiangyu Li, Yawen Zeng, Xiaofen Xing, Jin Xu 외

As automated trading gains traction in the financial market, algorithmic investment strategies are increasingly prominent. While Large Language Models (LLMs) and Agent-based models exhibit promising potential in real-tim…