harmful-overthinking

Tag

Cards List
#harmful-overthinking

Thinking Past the Answer: Evaluating Harmful Overthinking in Large Reasoning Models

arXiv cs.AI · 2026-06-03 Cached

This paper introduces a prefix-level trajectory evaluation protocol to distinguish harmful overthinking from verbose but harmless overthinking in large reasoning models, showing that continued reasoning after reaching the correct answer can destabilize performance. The authors find that early stopping improves accuracy by up to 21% on multimodal benchmarks, and identify logical drift and visual reinterpretation as key causes of correctness deviations.

0 favorites 0 likes
← Back to home

Submit Feedback