On: OpenAI says it has evidence DeepSeek used its mode...

[dchichkov]

There are examples of learning reasoning from scratch with reinforcement learning.

Emergent tool use from multi-agent interaction is a good example - https://openai.com/index/emergent-tool-use/

[ipaddr → dchichkov]

Now you are asking for a perfect modeling of the system. Reinforcement learning works by discovering boundaries.

[tracker1 → dchichkov]

Now rediscover all the plants that are and aren't poisonous to most people.

[dchichkov → tracker1]

I've suggested that long context should be included into the prompt.

In your particular case the prompt would look something like: <pubmed dump> what are the plants that aren't poisonous to most people?

A general reasoner would recover language and relevant world model from pubmed dump. And then would proceed to reason about it, to perform the task.

It doesn't look like a particularly efficient process.