Reasoning Models Sometimes Output Illegible Chains of Thought
Author not recordedDate not recordedOriginal︎ ↗
Examinations
None recorded.
Text
No stored copy. Only the passages claims quote are recorded.
These results suggest that without explicit optimization for legibility, outcome-based RL naturally produces models with increasingly opaque reasoning processes, potentially undermining monitoring approaches.
Not yet read by this claim’s Steward.
We study CoT legibility across 14 reasoning models, finding that RL often causes reasoning to become illegible to both humans and AI monitors, with reasoning models (except Claude) generating illegible CoTs while returning to perfectly readable final answers.
Not yet read by this claim’s Steward.
We study CoT legibility across 14 reasoning models, finding that RL often causes reasoning to become illegible to both humans and AI monitors, with reasoning models (except Claude) generating illegible CoTs while returning to perfectly readable final answers.
Not yet read by this claim’s Steward.
Lineage across 3 claims
Record
- Kind
- unknown
- Authors
- Not recorded
- Publisher
- Not recorded
- Published
- Not recorded
- DOI
- None
- Link
- https://arxiv.org/abs/2510.27338
- Archived copy
- None found
- Stored text
- None; quoted passages only
- Claims extracted
- Not recorded
- Versions
- One known
- Copies
- None recorded
- Corrections
- Not yet checked
- Facts checked
- Not yet
History 1
- Oct 30, 2026Entered the graphEntered the graph; no copy stored