Sourceunknownno stored text
Reasoning Models Struggle to Control their Chains of Thought
Author not recordedDate not recordedOriginal︎ ↗
Claims3
ExaminationsNone
TextNot stored
VersionsOne known
CopiesNone recorded
CorrectionsNot checked
Facts not yet checkedReachNo copies recorded
StructureIn 3 claims' maps0 sources downstream across 3 claims
EvidenceNot yet read
Examinations
None recorded.
Text
No stored copy. Only the passages claims quote are recorded.
As quoted
We also find that CoT controllability is higher for larger models and decreases with more RL training, test-time compute, and increased problem difficulty.
Chain-of-thought controllability increases with model scale.
Not yet read by this claim’s Steward.
As quoted
We also find that CoT controllability is higher for larger models and decreases with more RL training, test-time compute, and increased problem difficulty.
CoT controllability declined over outcome-based RL training in the CoT-Control experiments.
Not yet read by this claim’s Steward.
As quoted
We also find that CoT controllability is higher for larger models and decreases with more RL training, test-time compute, and increased problem difficulty.
Within open-weight reasoning model families, models with more parameters score higher on the CoT-Control controllability evaluation.
Not yet read by this claim’s Steward.
Lineage across 3 claims
Draws on · none recorded
This source
Drawn on by · none recordedReasoning Models Struggle to Control their Chains of Thought
in 3 claims' maps
Record
- Kind
- unknown
- Authors
- Not recorded
- Publisher
- Not recorded
- Published
- Not recorded
- DOI
- None
- Link
- https://arxiv.org/abs/2603.05706
- 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
- Nov 1, 2026Entered the graphEntered the graph; no copy stored