LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks · HackerPapers discussions

LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks — mentioned by huevosabio

Tue, 09 Dec 2025 23:46:23 GMT

> Wouldn’t a language designed for vibe coding naturally dispense with much of what is convenient and ergonomic for humans in favor of what is convenient and ergonomic for machines? Why not have it just write C? Or hell, why not x86 assembly? In the game we're building we generate, compile and run code (C#) in real time to let the player "train and command" its monster in creative ways. So, I've thought about this. You need both a popular language and one that has a ton of built-in verifying tools. The author correctly highlights the former, but dismisses the latter as being targeted to…

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

LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks — mentioned by dudeinhawaii

Wed, 30 Apr 2025 02:21:09 GMT

I see a lot of threads pitting models against each other (or whole swarms of them) in the hope that "wisdom of crowds" will magically appear. After a stack of experiments of my own—and after watching the recent ASU/Microsoft-Research work [1].. I've landed on a simpler takeaway: An LLM is a terrible verifier of another LLM. Subbarao Kambhampati's "(How) Do LLMs Reason/Plan?" talk shows GPT-4 confidently producing provably wrong graph-coloring proofs until a symbolic SAT solver is introduced as the referee [1]. Stechly et al. quantify the problem: letting GPT-4 critique its own answers…

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

LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks — mentioned by tannhaeuser

Fri, 18 Oct 2024 09:29:33 GMT

While the paper is about helping an LLM using Prolog, to give an idea for a realistic application for generating Prolog, here's the zero-shot prompt and response of a basic local Instruct LLM on a challenge to a classic 1998 AI Planning Competition "Logistics" problem re-formulated in English from PDDL, running on a very basic local 8B LLM quant'd to run on 12GB and containing even typos, but not showing the system prompt portion though. I mean, it's quite impressive and the generated state and action predicates can be run right away in the browser on eg. Quantum Prolog much like the…

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