control-harness

Tag

Cards List
#control-harness

LLMs Know When They Know, but Do Not Act on It: A Metacognitive Harness for Test-time Scaling

arXiv cs.LG · 3d ago Cached

This paper proposes a metacognitive harness that separates monitoring from reasoning in LLMs, using pre-solve feeling-of-knowing and post-solve judgment-of-learning signals to control when to trust, retry, or aggregate answers, improving accuracy on text, code, and multimodal benchmarks without parameter updates.

0 favorites 0 likes
← Back to home

Submit Feedback