RSS

Agent-Struc­ture Problem

TagLast edit: 17 Mar 2026 21:38 UTC by niplav

The agent-structure problem is the question about whether systems that behave like agents necessarily have an internal structure that makes them agentic. This structure usually involves some search procedure.

A Gen­er­al­iza­tion of the Good Reg­u­la­tor Theorem

Alfred Harwood4 Jan 2025 9:55 UTC
21 points
6 comments10 min readLW link

LLMs as Gi­ant Lookup-Tables of Shal­low Circuits

17 Mar 2026 21:35 UTC
98 points
29 comments7 min readLW link

Ra­tion­al­ists are miss­ing a core piece for agent-like struc­ture (en­ergy vs in­for­ma­tion over­load)

tailcalled17 Aug 2024 9:57 UTC
61 points
9 comments4 min readLW link

[Question] Does Agent-like Be­hav­ior Im­ply Agent-like Ar­chi­tec­ture?

Scott Garrabrant23 Aug 2019 2:01 UTC
72 points
9 comments1 min readLW link

Selec­tion The­o­rems: A Pro­gram For Un­der­stand­ing Agents

johnswentworth28 Sep 2021 5:03 UTC
135 points
28 comments6 min readLW link2 reviews

Clar­ify­ing the Agent-Like Struc­ture Problem

johnswentworth29 Sep 2022 21:28 UTC
64 points
19 comments6 min readLW link

Towards a for­mal­iza­tion of the agent struc­ture problem

Alex_Altair29 Apr 2024 20:28 UTC
55 points
6 comments14 min readLW link

What’s Gen­eral-Pur­pose Search, And Why Might We Ex­pect To See It In Trained ML Sys­tems?

johnswentworth15 Aug 2022 22:48 UTC
158 points
18 comments10 min readLW link
No comments.