← Back to context

Comment by gas9S9zw3P9c

6 days ago

It depends. If you have an LLM that uses reasoning the explanation for why decisions are made can often be found in the reasoning token output. So if the agent later has access to that context it could see why a decision was made.

LLMs often already "know" the answer starting from the first output token and then emulate "reasoning" so that it appeared as if it came to the conclusion through logic. There's a bunch of papers on this topic. At least it used to be the case a few months ago, not sure about the current SOTA models.

  • Wait, that's not right, let me think through this more carefully...

Reasoning, in majority of cases, is pruned at each conversation turn.