Why LLM agents keep failing (and it’s not the prompt)

Most LLM agent failures I’ve seen share the same pattern:

They don’t break because of the model. They don’t break because of the prompt.

They break because we force the system to “figure everything out” from scratch on every interaction.

In traditional software, we don’t rebuild logic every time we run a function. We define structure, reuse components, and control execution.

With LLM agents, we’re doing the opposite.

This led me to explore a different approach:

-> What if reasoning wasn’t embedded in prompts, → but structured and executed as reusable components?

That’s the idea behind ORCA — a cognitive runtime for LLM agents.

I’ve put the full concept in a paper in zenodo and now also on SSRN:

Zenodo

Beyond Prompting: Decoupling Cognition from Execution in LLM-based Agents...

Recent advances in large language model (LLM) agents have largely relied on prompt-centricdesigns, where complex tasks are executed through monolithic, single-shot or loosely structuredprompting strategies. While effective in some settings, this...

https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6600840

Curious if others are hitting the same limits with prompt-based systems.