More Agents Is All You Need · HackerPapers discussions

More Agents Is All You Need — mentioned by TaurenHunter

Thu, 09 Jan 2025 16:36:36 GMT

"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" is not AI-related: https://www.scribd.com/document/361564026/Math-works-09

Paper and discussion history. A mention is not an endorsement.

More Agents Is All You Need — mentioned by bluecoconut

Thu, 12 Sep 2024 19:15:27 GMT

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 behavior much better. 2. The power law behavior of inference compute seems to be showing up now in multiple ways. Both in ensembles [1,2], as well as in o1 now. If this is purely on decoding self-reflection tokens, this has a "limit" to its scaling in a way, only as long as the context length. I think this implies (and I am…

Paper and discussion history. A mention is not an endorsement.

More Agents Is All You Need — mentioned by bluecoconut

Thu, 12 Sep 2024 17:54:50 GMT

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 sorta wish everyone would plot their y-axis with logit y-axis, rather than 0->100 accuracy (including the openai post), to help show the power-law behavior. This is especially important when talking about incremental gains in the ~90->95, 95->99%. When the values (like the open ai post) are between 20->80, logit and linear…

Paper and discussion history. A mention is not an endorsement.

More Agents Is All You Need — mentioned by simonw

Tue, 06 Aug 2024 20:22:42 GMT

"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 article links to the paper about it - https://arxiv.org/abs/2402.05120 - but I've not heard from anyone who's implementing production systems successfully in that way. (I still don't actually know what an "agent" is, to be honest. I'm pretty sure there are dozens of conflicting definitions floating around out there by…

Paper and discussion history. A mention is not an endorsement.

More Agents Is All You Need — mentioned by pksebben

Thu, 11 Apr 2024 18:54:37 GMT

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

Paper and discussion history. A mention is not an endorsement.

More Agents Is All You Need — HN submission

Sat, 06 Apr 2024 21:25:50 GMT

More Agents Is All You Need: LLMs performance scales with the number of agents

288 points; 206 discussion replies on HN. Paper and source history. A submission is not an endorsement.

More Agents Is All You Need — mentioned by CuriouslyC

Wed, 27 Mar 2024 14:10:04 GMT

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 select the correct answer significantly improves question answering performance (https://arxiv.org/pdf/2402.05120.pdf), and while this approach isn't really cost effective or fast enough in most cases, I think with Claud 3 Haiku it might just work, as you can have it answer a question 10 times for the cost of a single…

Paper and discussion history. A mention is not an endorsement.

More Agents Is All You Need — HN submission

Fri, 23 Feb 2024 14:48:23 GMT

More Agents Is All You Need

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

More Agents Is All You Need — HN submission

Sun, 18 Feb 2024 22:10:20 GMT

More Agents Is All You Need

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.