H
Howardism
Howardism · Vol. 03Plate I · No. 01

Test Time Compute, tagged.

Notes22TagTest Time ComputeOldest9 Jul 2026Newest23 Sept 2026

Every article tagged test time compute, newest first.

  1. C01
    Pre-Reasoning Commitment
    Test Time ComputeReasoning ModelsChain Of Thought+2
    · 15′
  2. C02
    Shared-Budget Compute Allocation
    Test Time ComputeReasoning ModelsMetacognition+2
    · 21′
  3. C03
    Many-Agent Proof Harnesses
    AI For MathematicsAgent EngineeringAgent Orchestration+2
    · 43′
  4. C04
    The Navier–Stokes AI Claim
    AI For MathematicsFormal MethodsMulti Agent+2
    · 28′
  5. C05
    Tree Search over Agent Trajectories (LATS)
    Agent EngineeringPlanningSearch+2
    · 16′
  6. E06
    Azalia Mirhoseini
    EntityPersonResearcher+2
    · 15′
  7. E07
    CS329A: Self-Improving AI Agents (Stanford)
    EntityDocumentCourse+2
    · 54′
  8. C08
    Inference-Time Architecture Search
    Test Time ComputeInference ScalingLLM Architecture+2
    · 12′
  9. C09
    Intra-Trace Parallel Planning (SPRINT)
    Post TrainingReasoningPlanning+2
    · 14′
  10. C10
    Process vs Outcome Reward Models
    LLM EvaluationTest Time ComputeReward Modeling+2
    · 26′
  11. C11
    Rationale Bootstrapping (STaR)
    LLM ArchitecturePost TrainingReasoning+2
    · 26′
  12. C12
    Selection Under a Submission Budget
    Test Time ComputeInference ScalingSearch+2
    · 15′
  13. C13
    Weak-Verifier Ensembling
    EvaluationLLM As A JudgeTest Time Compute+2
    · 51′
  14. C14
    Invisible Reasoning (Filler-Token Latent Computation)
    InterpretabilityReasoningChain Of Thought+2
    · 24′
  15. C15
    Open-Ended Discovery Harnesses
    Agent EngineeringAgent OrchestrationOpen Ended Discovery+2
    · 37′
  16. C16
    Dynamic Workflows: An Algebra for Agents
    Agent EngineeringAgent OrchestrationTest Time Compute+1
    · 40′
  17. C17
    Unproductive Self-Verification
    CapabilityTest Time ComputeAgents+2
    · 18′
  18. E18
    UK AI Security Institute
    EntityOrgAI Evaluation+2
    · 33′
  19. C19
    Inference Efficiency as Capability
    LLM ArchitectureInference ScalingTest Time Compute+2
    · 51′
  20. C20
    Large-Scale Test-Time Compute
    LLM ArchitectureTest Time ComputeInference Scaling+2
    · 41′
  21. C21
    Latent Capability Overhang
    LLM ArchitectureTest Time ComputeCapability Trajectory+1
    · 32′
  22. C22
    Open-Weight Elicitation Irreversibility
    GovernanceSafetyOpen Weights+2
    · 25′