HackerPapers

arXiv:2402.05120cs.CL

More Agents Is All You Need

Junyou Li, Qin Zhang, Yangbin Yu, Qiang Fu, Deheng Ye

Abstract

We find that, simply via a sampling-and-voting method, the performance of large language models (LLMs) scales with the number of agents instantiated. Also, this method, termed as Agent Forest, is orthogonal to existing complicated methods to further enhance LLMs, while the degree of enhancement is correlated to the task difficulty. We conduct comprehensive experiments on a wide range of LLM benchmarks to verify the presence of our finding, and to study the properties that can facilitate its occurrence. Our code is publicly available at: https://github.com/MoreAgentsIsAllYouNeed/AgentForest

arXiv comments
Published at Transactions on Machine Learning Research (TMLR)
Journal reference
DOI
Subjects
cs.CLComputation and Language cs.AIArtificial Intelligence cs.LGMachine Learning

On Hacker News

Linked by 5 identifiable commenters in 6 comments across 5 threads, from Mar 2024 to Jan 2025. Found in 3 HN submissions from Feb 2024 to Apr 2024. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments5 threads

  1. Agents Are Not Enough 1 comment

    • "More Agents is all you need" https://arxiv.org/abs/2402.05120 I could not find a "Agents considered harmful" related to AI, but there is this one: "AgentHarm: A benchmark for measuring harmfulness of LLM agents" https://arxiv.org/pdf/2410.09024 This "Agents considered harmful"…

      TaurenHunterView on HNParent context

  2. Learning to Reason with LLMs 2 comments

    • This power law behavior of test-time improvement seems to be pretty ubiquitous now. In more agents is all you need [1], they start to see this as a function of ensemble size. It also shows up in: Large Language Monkeys: Scaling Inference Compute with Repeated Sampling [2] I…

      bluecoconutView on HNParent context

    • Some other follow up reflections 1. I wish that Y-axes would switch to be logit instead of linear, to help see power-law scaling on these 0->1 measures. In this case, 20% -> 80% it doesn't really matter, but for other papers (eg. [2] below) it would help see this powerlaw…

      bluecoconutView on HNParent context

  3. AI agents but they're working in big tech 1 comment

    • "Research shows that AI systems with 30+ agents out-performs a simple LLM call in practically any task (see More Agents Is All You Need), reducing hallucinations and improving accuracy." Has anyone heard of that actually playing out practically in real-world applications? This…

      simonwView on HNParent context

  4. Storm: LLM system that researches a topic and generates full-length wiki article 1 comment

    • This method has actually been proven effective at increasing reliability / decreasing hallucinations [1] 1 - https://arxiv.org/abs/2402.05120

      pksebbenView on HNParent context

  5. Claude 3 beats GPT-4 on Aider's code editing benchmark 1 comment

    • I don't care about Opus, it's way overpriced if not through the web interface. Sonnet and Haiku are absolute achievements for the speed/cost though. I recently read research that demonstrated that having multiple AIs answer a question then treating their answers as votes to…

      CuriouslyCView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.