Society of Mind and Multi-Agent Debate
Minsky's 1986 premise — intelligence is a society of specialists — gets rediscovered every decade. In 2023 Du et al. turned it into a concrete algorithm: multiple LLM instances propose answers, read each other's answers, critique, and update. Over N rounds they converge on a consensus that beats zero-shot CoT and reflection on six reasoning and factuality tasks. Two findings matter: both multiple agents and multiple rounds contribute independently. The society beats a single-agent monologue; the multi-round exchange beats one-shot voting. Self-consistency — sample one model many times and take the majority answer — is the cheapest reasoning improvement you can bolt on. It works, but it saturates fast. You can double your samples and not see another meaningful jump. Debate breaks the saturation. Instead of N independent samples from one model, N agents read each other's reasoning and revise. The correlation between samples drops (they are no longer i.i.d.), and the convergence point is often correct where i.i.d. voting was confidently wrong. From arXiv:2305.14325 (ICML 2024): Each of N agents produces an initial answer to the question. For round r = 2..R: each agent is shown the other agents' round r-1 answers and asked "considering these, give your updated answer.". After R rounds, majority-vote the final answers. The paper tests on MMLU, GSM8K, biographies, MATH, and factuality benchmarks. Debate…
Society of Mind and Multi-Agent Debate: Minsky's 1986 premise — intelligence is a society of specialists — gets rediscovered every decade. In 2023 Du et al.…
This free lesson is part of the AI Engineering from Scratch curriculum. Read the full explanation, run the lesson code, and verify the result in the interactive reader or from the repository source.
Browse the complete course catalog or open this lesson on GitHub.