Thinking Inertia: LLMs keep reasoning in 99.9% of open-ended answers even with thinking off
rohanpaul_ai · x · 2026-10-10
A Tsinghua-Oxford-Stanford paper, "Thinking Inertia" (arXiv 2610.11765), finds LLMs keep writing out reasoning even with thinking mode disabled. DeepSeek-V4-Flash produced explicit reasoning in 99.9% of open-ended answers; a missing think tag doesn't mean reasoning was skipped. Question type drives the effect: yes/no answers are direct, multiple-choice sits in between, open-ended questions pull the model back into reasoning. Forcing answer-only replies raised compliance to 40% across 5 models but cut accuracy by 15 points.
Related event: Thinking Inertia: LLMs Keep Reasoning Even When Told Not To(2 posts)→
More from Research
- 20-minute explainer breaks down how Tesla trains FSD: 8 cameras, 36fps, 2B signals to 2 outputs — PTrubey · 2026-10-10
- 21 researchers release white paper on Visual General Intelligence as a path to AGI — HirokatuKataoka · 2026-10-10
- Epoch AI: Over half of arXiv math papers in 3 subfields now acknowledge AI use — burny_tech · 2026-10-10
- Researcher faults standard Transformer diagrams for hiding self-attention as a black box — PlisSergey · 2026-10-10
- Xiaomi's MiMo-V2.6: agents run their own RL loop, DeepSWE score hits 72.6 for $2.6M — rohanpaul_ai · 2026-10-10
- New fastest deterministic 3SUM algorithm hits n^1.9961, matching randomized bound — basedjensen · 2026-10-10