MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration
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.
Code (1)
Tasks
BenchmarkingLanguage ModelingLanguage ModellingLarge Language ModelMethods 이 논문이 사용한 방법론
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
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
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 UnderstandingMagical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation
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-tuningToward Geometric Deep SLAM
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 TrackingDetecting Spells in Fantasy Literature with a Transformer Based Artificial Intelligence
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