English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large Language Models (LLMs) have marked a significant advancement in thefield of natural language processing, demonstrating exceptional capabilities inreasoning, tool usage, and memory. As their applications extend intomulti-agent environments, a need has arisen for a comprehensive evaluationframework that captures their abilities in reasoning, planning, collaboration,and more. This work introduces a novel benchmarking framework specificallytailored to assess LLMs within multi-agent settings, providing quantitativemetrics to evaluate their judgment, reasoning, deception, self-awareness,cooperation, coordination, and rationality. We utilize games such as Chameleonand Undercover, alongside game theory scenarios like Cost Sharing, Multi-playerPrisoner's Dilemma, and Public Good, to create diverse testing environments.Our framework is fortified with the Probabilistic Graphical Modeling (PGM)method, enhancing the LLMs' capabilities in navigating complex social andcognitive dimensions. The benchmark evaluates seven multi-agent systems poweredby different LLMs, quantitatively highlighting a significant capability gapover threefold between the strongest, GPT-4, and the weakest, Llama-2-70B. Italso confirms that our PGM enhancement boosts the inherent abilities of allselected models by 50% on average. Our codes are released herehttps://github.com/cathyxl/MAgIC.

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