Heavy Thinking: A Test-Time Scaling Pattern for Hard Problems May 17, 2026 paperAgenticReasoningTestTimeScalingAgentSkillsHarnessDesignReasoningModels Now we have GPT Pro at home
Optimising Computation At The Token-Level Jul 21, 2025 paperLargeLanguageModelsLatentReasoningTestTimeScalingReasoningModels Optimising computation at the token-level