programming.dev
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
cm0002@infosec.pub to Technology@lemmy.zipEnglish · 2 months ago

Solving a Million-Step LLM Task with Zero Errors

arxiv.org

external-link
message-square
0
link
fedilink
  • cross-posted to:
  • [email protected]
  • [email protected]
9
external-link

Solving a Million-Step LLM Task with Zero Errors

arxiv.org

cm0002@infosec.pub to Technology@lemmy.zipEnglish · 2 months ago
message-square
0
link
fedilink
  • cross-posted to:
  • [email protected]
  • [email protected]
LLMs have achieved remarkable breakthroughs in reasoning, insights, and tool use, but chaining these abilities into extended processes at the scale of those routinely executed by humans, organizations, and societies has remained out of reach. The models have a persistent error rate that prevents scale-up: for instance, recent experiments in the Towers of Hanoi benchmark domain showed that the process inevitably becomes derailed after at most a few hundred steps. Thus, although LLM research is often still benchmarked on tasks with relatively few dependent logical steps, there is increasing attention on the ability (or inability) of LLMs to perform long range tasks. This paper describes MAKER, the first system that successfully solves a task with over one million LLM steps with zero errors, and, in principle, scales far beyond this level. The approach relies on an extreme decomposition of a task into subtasks, each of which can be tackled by focused microagents. The high level of modularity resulting from the decomposition allows error correction to be applied at each step through an efficient multi-agent voting scheme. This combination of extreme decomposition and error correction makes scaling possible. Thus, the results suggest that instead of relying on continual improvement of current LLMs, massively decomposed agentic processes (MDAPs) may provide a way to efficiently solve problems at the level of organizations and societies.
alert-triangle
You must log in or # to comment.

Technology@lemmy.zip

technology@lemmy.zip

Subscribe from Remote Instance

Create a post
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: [email protected]

Which posts fit here?

Any news that are at least tangentially connected to the technology, social media platforms, informational technologies or tech policy.


Post guidelines

[Opinion] prefix

Opinion (op-ed) articles must use [Opinion] prefix before the title.


Rules

1. English only

Title and associated content has to be in English.

2. Use original link

Post URL should be the original link to the article (even if paywalled) and archived copies left in the body. It allows avoiding duplicate posts when cross-posting.

3. Respectful communication

All communication has to be respectful of differing opinions, viewpoints, and experiences.

4. Inclusivity

Everyone is welcome here regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, education, socio-economic status, nationality, personal appearance, race, caste, color, religion, or sexual identity and orientation.

5. Ad hominem attacks

Any kind of personal attacks are expressly forbidden. If you can’t argue your position without attacking a person’s character, you already lost the argument.

6. Off-topic tangents

Stay on topic. Keep it relevant.

7. Instance rules may apply

If something is not covered by community rules, but are against lemmy.zip instance rules, they will be enforced.


Companion communities

[email protected]
[email protected]


Icon attribution | Banner attribution


If someone is interested in moderating this community, message @[email protected].

Visibility: Public
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 361 users / day
  • 1.38K users / week
  • 3.08K users / month
  • 9.32K users / 6 months
  • 64 local subscribers
  • 6.43K subscribers
  • 6.49K Posts
  • 25.3K Comments
  • Modlog
  • mods:
  • BrikoX@lemmy.zip
  • BE: 0.19.13
  • Modlog
  • Legal
  • Instances
  • Docs
  • Code
  • join-lemmy.org