Multi-Agent LLMs
LLM: Large Language Model
Overview
Multi-agent large language models study how multiple language-model-powered agents can divide work, communicate, use tools, and combine their decisions. Common approaches assign specialized roles, use debate or verification, route tasks adaptively, and maintain shared memory; newer systems also learn communication protocols or exchange compressed internal representations. Applications range from reasoning and software development to clinical support, scientific discovery, social simulation, and strategic games. A central tension is that collaboration can improve performance but also adds cost and can spread errors, bias, or unsafe behavior, while benchmarks still struggle to measure reliable long-horizon coordination.
Latest papers
324 papers33 papers in the last four weeks, up 14% on the four weeks before. 0.2% of all new papers.