paper-with-me

Papers

MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration

2023-11-14 · Lin Xu, Zhiyuan Hu, Daquan Zhou, Hongyu Ren, Zhen Dong, Kurt Keutzer, See Kiong Ng, Jiashi Feng

Large Language Models (LLMs) have significantly advanced natural language processing, demonstrating exceptional reasoning, tool usage, and memory capabilities. As their applications expand into multi-agent environments, there arises a need for a comprehensive evaluation framework that captures LLMs' reasoning, planning, collaboration, and other social abilities. This work introduces a novel competition-based benchmark framework specifically designed to assess LLMs within multi-agent settings, providing quantitative metrics to evaluate their judgment, reasoning, deception, self-awareness, cooperation, coordination, and rationality. We utilize two social deduction games alongside three game-theory scenarios to create diverse environments. Our frame is fortified with the probabilistic graphic modeling (PGM) method, enhancing the LLMs' capabilities in navigating complex social and cognitive dimensions. We evaluate seven LLMs, quantitatively highlighting a significant capability gap of over threefold between the strongest, GPT o1, and the weakest, Llama-2-70B. It also confirms that our PGM enhancement boosts the abilities of all selected models by an average of 37%. Our data and code can be found here https://github.com/cathyxl/MAgIC.

📄 PDF Abstract BibTeX arXiv:2311.08562

Code (1)

cathyxl/magic 공식 구현

Tasks

BenchmarkingLanguage ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Black Magic Investigation Made Simple: Monte Carlo Simulations and Historical Back Testing of Momentum Cross-Over Strategies Using FRACTI Patterns

2018-08-23

To promote economic stability, finance should be studied as a hard science, where scientific methods apply. When a trading strategy is proposed, the underlying model should be transparent and defined robustly to allow ot…

MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents

2024-12-11 · Yun Xing, Nhat Chung, Jie Zhang, Yue Cao 외

Physical adversarial attacks in driving scenarios can expose critical vulnerabilities in visual perception models. However, developing such attacks remains challenging due to diverse real-world backgrounds and the requir…

object-detectionObject DetectionPrompt EngineeringScene Understanding

Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation

2025-08-12 · Weibin Liao, Tianlong Wang, Yinghao Zhu, Yasha Wang 외 arxiv

Medical Lay Language Generation (MLLG) plays a vital role in improving the accessibility of complex scientific content for broader audiences. Recent literature to MLLG commonly employ parameter-efficient fine-tuning meth…

parameter-efficient fine-tuning

Toward Geometric Deep SLAM

2017-07-24 · Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich

We present a point tracking system powered by two deep convolutional neural networks. The first network, MagicPoint, operates on single images and extracts salient 2D points. The extracted points are "SLAM-ready" because…

CPUPoint Tracking

Detecting Spells in Fantasy Literature with a Transformer Based Artificial Intelligence

2023-08-07 · Marcel Moravek, Alexander Zender, Andreas Müller

Transformer architectures and models have made significant progress in language-based tasks. In this area, is BERT one of the most widely used and freely available transformer architecture. In our work, we use BERT for c…

token-classificationToken Classification