Test-Time Compute: Spending Inference Budget on Search

Test-time compute spends extra inference budget on sampling, verification, and selection; it helps when the generator can produce good candidates and the verifier ranks them reliably.

published · difficulty 4/5 · 22 min read

Intuition

Build the mental picture first so the rest of the page has something to attach to.

PredictName the object in plain language, then predict what should change.Leave with one reusable mental picture before notation appears.

Canonical sources: Kaplan et al., "Scaling Laws for Neural Language Models", Hoffmann et al., "Training Compute-Optimal Large Language Models", Cobbe et al., "Training Verifiers to Solve Math Word Problems", Uesato et al., "Solving Math Word Problems With Process- and Outcome-Based Feedback", Lightman et al., "Let's Verify Step by Step", Brown et al., "Large Language Monkeys: Scaling Inference Compute with Repeated Sampling", Wang et al., "Self-Consistency Improves Chain of Thought Reasoning in Language Models", and Snell et al., "Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters".

Training-time scaling spends more compute before deployment: more parameters, more data, longer training.

Test-time scaling spends more compute after the prompt arrives. In this page, that means sampling more complete candidate traces and scoring them with a verifier.

Here "search" means parallel best-of- $N$ over complete traces, not prefix expansion or tree search.

This page focuses on the smallest useful case: best-of- $N$ with a verifier. For one prompt, the model samples $N$ complete candidate traces. A verifier scores each trace. The system returns the highest-scoring sampled trace.

For this finite best-of- $N$ verifier setup, extra inference compute is useful only when two conditions are both true:

the generator sometimes samples a good trace,
the verifier tends to rank good traces above bad ones.

If the good trace is almost never sampled, extra compute may not be enough. If the verifier has a false-positive trap, more samples can make the system worse by making that trap more likely to appear. The honest question is not "does thinking longer help?" It is: for this prompt, generator, verifier, and cost model, is another sample worth buying?

Section prompt

Copy-only prompts — each action copies a page-grounded prompt to your clipboard. Nothing is sent by this site.

Math

Translate the story into symbols, assumptions, and a derivation you can inspect.

InspectTrack the same object through the notation and check each symbol.Leave with the invariant the equations preserve.

Equation 1Inspect equation objectp_i=\pi_{base}(\tau_i\mid x), \qquad \sum_i p_i=1, \qquad u_i\in\{0,1\}, \qquad s_i=s_\phi(\t...Equation 2Inspect equation object\tau^\star = \arg\max_{\tau\in\{\tau^{(1)},\dots,\tau^{(N)}\}} s_\phi(\tau); F_k = \sum_{i=1}...Equation 3Inspect equation objects_\phi(\tau_i) = \sum_{t=1}^{T_i} r_\phi(h_{i,t-1},a_{i,t}).

For one prompt $x$ , let the base model define a finite distribution over complete candidate traces. Each trace has hidden task correctness and a verifier score:

p_i=\pi_{\mathrm{base}}(\tau_i\mid x), \qquad \sum_i p_i=1, \qquad u_i\in\{0,1\}, \qquad s_i=s_\phi(\tau_i).

Best-of- $N$ draws $N$ independent traces from $p$ and returns the sampled trace with the highest verifier score. Assume verifier scores are distinct and sort traces from lowest to highest verifier score, so $s_1 < \cdots < s_K$ :

\begin{aligned} \tau^\star &= \arg\max_{\tau\in\{\tau^{(1)},\dots,\tau^{(N)}\}} s_\phi(\tau),\\ F_k &= \sum_{i=1}^k p_i,\qquad F_0=0,\\ P_N(k\ \mathrm{selected}) &= F_k^N-F_{k-1}^N,\\ A(N) &= \sum_k u_k \left(F_k^N-F_{k-1}^N\right),\\ \mathrm{coverage}_N &= 1-\left(1-\sum_i p_i u_i\right)^N. \end{aligned}

To connect back to process reward models, a trace score might be an additive step score:

s_\phi(\tau_i) = \sum_{t=1}^{T_i} r_\phi(h_{i,t-1},a_{i,t}).

Treat this as a ranking score, not a calibrated probability of correctness. Sum-vs-mean aggregation, length normalization, and distribution shift can all change which traces receive high verifier score.

The expected selected verifier score is

S(N) = \sum_k s_k \left(F_k^N-F_{k-1}^N\right).

Selected correctness and sampled-correct coverage can be very different. Sampling a correct trace is coverage. Returning it is selection. More samples can make $S(N)$ rise while $A(N)$ falls if the highest-scoring trace is a verifier error.

A simple cost model is

C(N)=N(c_{\mathrm{gen}}+c_{\mathrm{score}}).

Here $N$ is only a teaching proxy for inference budget. Real serving cost also depends on generation length, verifier cost, batching, latency, and traffic volume.

Section prompt

Copy-only prompts — each action copies a page-grounded prompt to your clipboard. Nothing is sent by this site.

Code

Keep the implementation aligned with the notation so the algorithm is legible.

TraceMatch variables to symbols before reading the implementation.Leave with a runnable witness for the math.

Code witness 1def selected_distribution(candidates, n): ranked = sorted(candidates, key=lambda item: item["...python

This witness uses the same finite best-of- $N$ object as the demo. With a clean verifier, more samples improve selected correctness. With a noisy verifier, selected verifier score improves while true correctness eventually falls.

def selected_distribution(candidates, n):
    ranked = sorted(candidates, key=lambda item: item["score"])
    cumulative = 0.0
    selected = {}
    for item in ranked:
        p = item["prior"]
        next_cumulative = cumulative + p
        selected[item["id"]] = next_cumulative ** n - cumulative ** n
        cumulative = next_cumulative
    return selected

def expected(candidates, selected, key):
    return sum(selected[item["id"]] * item[key] for item in candidates)

def scored(candidates, mode):
    return [{**item, "score": item[f"{mode}_score"]} for item in candidates]

def expected_accuracy(candidates, n, mode):
    rows = scored(candidates, mode)
    return expected(rows, selected_distribution(rows, n), "correct")

def expected_score(candidates, n, mode):
    rows = scored(candidates, mode)
    return expected(rows, selected_distribution(rows, n), "score")

candidates = [
    {"id": "common_wrong", "prior": 0.50, "correct": 0, "clean_score": -2.0, "noisy_score": -2.0},
    {"id": "plausible_slip", "prior": 0.25, "correct": 0, "clean_score": -0.3, "noisy_score": -0.3},
    {"id": "clean_correct", "prior": 0.18, "correct": 1, "clean_score": 1.8, "noisy_score": 1.8},
    {"id": "rare_exploit", "prior": 0.07, "correct": 0, "clean_score": 0.2, "noisy_score": 2.6},
]

clean_1 = expected_accuracy(candidates, 1, "clean")
clean_32 = expected_accuracy(candidates, 32, "clean")
noisy_1 = expected_accuracy(candidates, 1, "noisy")
noisy_64 = expected_accuracy(candidates, 64, "noisy")

assert clean_32 > clean_1
assert noisy_64 < noisy_1
assert expected_score(candidates, 64, "noisy") > expected_score(candidates, 1, "noisy")
print(round(clean_32, 3), round(noisy_64, 3))

Section prompt

Copy-only prompts — each action copies a page-grounded prompt to your clipboard. Nothing is sent by this site.

Interactive Demo

Use direct manipulation to connect the explanation to a moving system.

ManipulateChange one control and predict the visible response before reveal.Leave with the observed invariant or a repaired model.

Live Concept Demo

Explore Test-Time Compute: Spending Inference Budget on Search

The stage is code-native and interactive. Use it to test the explanation against the mechanism.

difficulty 4/5undergraduatecode-aligned

Demo inquiry checkpoint

Manipulate one control and predict the visible change.

01Choose lensTrace a quantity

02ObserveDemo state pending

03GroundName the equation, invariant, or control that explains it.

04CarryNext: Tree Search Reasoning: Allocating Inference Budget Across Prefixes

Choose what to inspect in Test-Time Compute: Spending Inference Budget on Search. This shared fallback is an observation guide, not evidence of learning.

Loading interactive demo...

Use the demo to compare a clean verifier against a noisy verifier on the same four traces. Increase $N$ to spend more inference compute. Watch the gap between "sampled at least one correct trace" and "selected a correct trace"; that gap is where verifier quality matters.

Section prompt

Copy-only prompts — each action copies a page-grounded prompt to your clipboard. Nothing is sent by this site.

Object

4/4 sections ready

Concept: Test-Time Compute: Spending Inference Budget on Search

What is the smallest example that makes Test-Time Compute: Spending Inference Budget on Search click without losing the math?

BeforeScaling Laws & Emergent AbilitiesNow4/4 sections readyTryManipulate one control and predict the visible change.NextTree Search Reasoning: Allocating Inference Budget Across Prefixes

Object contextScaling

StateScaling

3 sources attachedChecking local snapshot

concept:scaling/test-time-compute

Math3 equation objectsp_i=\pi_{base}(\tau_i\mid x), \qquad \sum_i p_i=1, \qquad u_i\in\{0,1\}, \qquad s_i=s_\phi(\t...CodeTest-Time Compute: Spending Inference Budget on Search code witness 1def selected_distribution(candidates, n): ranked = sorted(candidates, key=lambda item: item["...DemoTest-Time Compute: Spending Inference Budget on Search predictionManipulate one control and predict the visible change.

ConceptLearner lens

Test-Time Compute: Spending Inference Budget on Search

What is the smallest example that makes Test-Time Compute: Spending Inference Budget on Search click without losing the math?

Mode questionCan I say the mechanism back in one sentence before I reveal anything?

Start with the prediction checkpoint, then compare the reveal to the mental model.

Take this move

Study modes

Keep the object fixed; change the lens.

01PredictCommit before reveal.02ExplainName the invariant.03Ground3 source links nearby.04ExperimentChange one knob.05CarrySave the next question.

Route back through the notebook

Carry the same object through intuition, math, code, and demo.

4/4 sections ready

Carry inScaling Laws & Emergent Abilities

Bring the mental model from Scaling Laws & Emergent Abilities; this page will reuse it instead of restarting from zero.

Work hereTest-Time Compute: Spending Inference Budget on Search

Test-time compute spends extra inference budget on sampling, verification, and selection; it helps when the generator can produce good candidates and the verifier ranks them reliably.

Carry outTree Search Reasoning: Allocating Inference Budget Across Prefixes

The next edge should feel earned: use the demo prediction here before following Tree Search Reasoning: Allocating Inference Budget Across Prefixes.

After The First Pass

Turn the concept into an inspected object.

The lower panels are one second act: keep the object fixed, inspect it visually, check source boundaries, practice transfer, then attach the research question.

ConceptTest-Time Compute: Spending Inference Budget on SearchScaling

01MechanismInspect motionSee how the idea changes form before adding more explanation.02VisualChoose a cueBind one visible mark to one mathematical role.03SourcesCheck boundary3 source links attached to the object.04ClaimAudit evidenceTreat the page claim as something to verify.05PracticeAttempt transferWrite before feedback so the model has something to repair.06RoomAsk groundedAttach the question to the same exact object.

Mechanism Storyboard

See the idea move before the page explains it

Test-time compute spends extra inference budget on sampling, verification, and selection; it helps when the generator can produce good candidates and the verifier ranks them reliably.

Demo notes open01 / Intuition

Editorial scaling illustration of branching candidate traces scored by verifier gauges and selected through a budgeted funnel.

Prediction lens

Start with the picture, metaphor, or geometric mechanism.

Commit first

Before reading further, choose the kind of change Test-Time Compute: Spending Inference Budget on Search should make visible.

Visual Inquiry

Make the image answer a mathematical question

Test-time compute spends extra inference budget on sampling, verification, and selection; it helps when the generator can produce good candidates and the verifier ranks them reliably.

4/4 stages readyDemo notes connected

Visual cueWhich visible object should carry the first intuition?

Inspection depth2/4

Prediction

Which visible object should carry the first intuition?

Commit first

Pick the cue that should make Test-Time Compute: Spending Inference Budget on Search easier to reason about before the page gives the answer.

Source Grounding

Canonical references for the mechanism on this page.

Object - ConceptTest-Time Compute: Spending Inference Budget on SearchQuestion

What is the smallest example that makes Test-Time Compute: Spending Inference Budget on Search click without losing the math?

concept:scaling/test-time-compute

Boundary

sources: wang-2022-self-consistency, lightman-2023-verify-step-by-step, snell-2024-test-time-compute

Check

Open the closest source note before trusting the local explanation.

Evidence

3 selected-object sources shown first; 3 references total.

Next move

Audit the claim boundary, then ask from the same selected object.

selected object source · paper · 2022Self-Consistency Improves Chain of Thought Reasoning in Language ModelsWang et al.

Located CF editorial boundary

Grounds repeated sampling and answer aggregation as a simple way to spend more inference compute.

Used here as

Wang et al. ground drawing multiple reasoning paths and aggregating answers. Lightman et al. evaluate reward models by best-of-N search: select the sampled solution ranked highest by the...

Caveat

This checks a finite, fixed-distribution best-of-N verifier model, not tree search, adaptive reasoning policies, universal scaling laws, exact serving costs, calibrated verifier probabili...

Open source

selected object source · paper · 2023Let's Verify Step by StepLightman et al.

Located CF editorial boundary

Grounds process-supervised reward models as learned verifiers evaluated by best-of-N selection over sampled reasoning solutions.

Used here as

Wang et al. ground drawing multiple reasoning paths and aggregating answers. Lightman et al. evaluate reward models by best-of-N search: select the sampled solution ranked highest by the...

Caveat

This checks a finite, fixed-distribution best-of-N verifier model, not tree search, adaptive reasoning policies, universal scaling laws, exact serving costs, calibrated verifier probabili...

Open source

selected object source · paper · 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model ParametersSnell et al.

Located CF editorial boundary

Grounds the scaling question of when extra inference budget beats larger base models.

Used here as

Wang et al. ground drawing multiple reasoning paths and aggregating answers. Lightman et al. evaluate reward models by best-of-N search: select the sampled solution ranked highest by the...

Caveat

This checks a finite, fixed-distribution best-of-N verifier model, not tree search, adaptive reasoning policies, universal scaling laws, exact serving costs, calibrated verifier probabili...

Open source

Claim Review

Test-time compute spends extra inference budget on sampling, verification, and selection; it helps when the generator can produce good candidates and the verifier ranks them reliably.

Object - ConceptTest-Time Compute: Spending Inference Budget on SearchQuestion

What is the smallest example that makes Test-Time Compute: Spending Inference Budget on Search click without losing the math?

concept:scaling/test-time-compute

Boundary

sources: wang-2022-self-consistency, lightman-2023-verify-step-by-step, snell-2024-test-time-compute

Check

Treat every claim as provisional until source support and a local witness agree.

Evidence

1 structured claim check on this concept.

Next move

Run the prediction or practice transfer before asking for a grounded review.

1 CF editorial source-scope review recorded

Publisher-side editorial review is not independent replication. Claims without it still need exact source-support review. 3 references and 3 local witnesses are available for inspection.

In the page's finite best-of-N model, extra test-time compute can improve selected correctness when more samples cover good traces and the verifier ranks them highly; as N grows, clean ranking can help, while a rare high-scoring verifier error can be selected more often.

Registered CF editorial boundary

Self-Consistency Improves Chain of Thought Reasoning in Language ModelsGrounds repeated sampling and answer aggregation as a simple way to spend more inference compute.Let's Verify Step by StepGrounds process-supervised reward models as learned verifiers evaluated by best-of-N selection over sampled reasoning solutions.Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model ParametersGrounds the scaling question of when extra inference budget beats larger base models.

Used here as

Wang et al. ground drawing multiple reasoning paths and aggregating answers. Lightman et al. evaluate reward models by best-of-N search: select the sampled solution ranked highest by the reward model. Snell...

Local witness

source-span-wang-2022-self-consistency source-span-lightman-2023-verify-step-by-step source-span-snell-2024-test-time-compute math-object-1 math-object-2 code-witness-1 interactive-demo

Equation 1

p_i=\pi_{\mathrm{base}}(\tau_i\mid x), \qquad \sum_i p_i=1, \qquad u_i\in\{0,1\}, \qquad s_i=s_\phi(\tau_i).

Equation 2

\begin{aligned} \tau^\star &= \arg\max_{\tau\in\{\tau^{(1)},\dots,\tau^{(N)}\}} s_\phi(\tau),\\ F_k &= \sum_{i=1}^k p_i,\qquad F_0=0,\\ P_N(k\ \mathrm{selected}) &= F_k^N-F_{k-1}^N,\\ A(N) &= \sum_k u_k \left(F_k^N-F_{k-1}^N\right),\\ \mathrm{coverage}_N &= 1-\left(1-\sum_i p_i u_i\right)^N. \end{aligned}

Caveat

This checks a finite, fixed-distribution best-of-N verifier model, not tree search, adaptive reasoning policies, universal scaling laws, exact serving costs, calibrated verifier probabilities, or guaranteed...

Review stateCF editorial source-scope reviewClaim metadata: source checkedPublisher-side editorial review only; not independent replication. Check caveats and exact source scope.

Reviewed arXiv/source TeX: Wang et al. support repeated diverse reasoning-path sampling and answer aggregation; Lightman et al. support reward-model best-of-N selection and high-scoring wrong-answer failure cases; Snell et al. support verifier-search test-time compute, best-of-N baselines, and PRM exploitation/degradation. Local math/code/demo support the finite coverage-vs-selection model.

Reviewer: codex; reviewed 2026-05-20

Practice notebook

Use the idea, then test it somewhere new

Test-time compute spends extra inference budget on sampling, verification, and selection; it helps when the generator can produce good candidates and the verifier ranks them reliably.

AttemptNo learning claim inferred

Object - ConceptTest-Time Compute: Spending Inference Budget on SearchQuestion

What is the smallest example that makes Test-Time Compute: Spending Inference Budget on Search click without losing the math?

concept:scaling/test-time-compute

Boundary

sources: wang-2022-self-consistency, lightman-2023-verify-step-by-step, snell-2024-test-time-compute

Check

Use one state from Test-Time Compute: Spending Inference Budget on Search to explain what changes, why it changes, and which assumption the explanation needs.

Evidence

No learner move yet; no learning state is inferred.

Next move

Write first, use only the help you need, then try a new case without it.

Explain

Use one state from Test-Time Compute: Spending Inference Budget on Search to explain what changes, why it changes, and which assumption the explanation needs.

Hint 1

Reveal when your model needs a nudge.

Hint 2

Reveal when your model needs a nudge.

Hint 3

Reveal when your model needs a nudge.

Your answer canvas

Attempt context

Learner move

Write an attempt before asking the companion.

Assistance used

0 of 3 progressive hints opened.

Evidence boundary

This draft and any AI response do not establish mastery; a later unassisted case can.

Misconception check

Grounded object roomClose

Selected object routeAsk from this object; carry one invariant back.sources: wang-2022-self-consistency, lightman-2023-verify-step-by-step, snell-2024-test-time-compute

ObjectConceptTest-Time Compute: Spending Inference Budget on Search
PredictBefore revealTest-Time Compute: Spending Inference Budget on Search prediction
WitnessCompare codeTest-Time Compute: Spending Inference Budget on Search code witness 1
RoomAsk groundedChecking local snapshot

ConceptTest-Time Compute: Spending Inference Budget on SearchScaling

Code witness comparisonTest-Time Compute: Spending Inference Budget on Search code witness 1def selected_distribution(candidates, n): ranked = sorted(candidates, key=lambda item: item["...Prediction before revealTest-Time Compute: Spending Inference Budget on Search predictionManipulate one control and predict the visible change.

Grounded room questionWhat is the smallest example that makes Test-Time Compute: Spending Inference Budget on Search click without losing the math?Checking local snapshot

Research Room

Attach the question to an exact object

Pick the concept, equation, source, code witness, claim, misconception, or demo state before asking for help. The handoff stays grounded to that object.

Next local actionNo local draft saved yet

Open the draft below to save one note and next action in this browser.

conceptScaling

Test-Time Compute: Spending Inference Budget on Search

Anchored question

What is the smallest example that makes Test-Time Compute: Spending Inference Budget on Search click without losing the math?

Source boundaryInspect source ids: wang-2022-self-consistency, lightman-2023-verify-step-by-step, snell-2024-test-time-computeStable content-object key attached

Role lenses for this object

These are fixed, deterministic perspectives derived from the selected object. They do not represent people, community contributions, or independent review.

Learner evidence requestAsk what would make "Test-Time Compute: Spending Inference Budget on Search" feel predictable rather than familiar.

Assumption

Source ids wang-2022-self-consistency, lightman-2023-verify-step-by-step, snell-2024-test-time-compute must support the exact object, not just the surrounding topic.

Source-checking summary

Treat this as a mechanism object: connect the definition to one equation, code witness, or demo before broadening the discussion.

Proposed experiment

Ask the learner to perturb one representation, then check whether the same invariant survives in math, code, and demo.

Next action

The learner can state the mechanism in their own words

Evidence4 checks

PredictionChecking carried observation

ActionReady for one action

AILearner handoff ready

Open source object

01PredictionChecking browser-local route memory

02EvidenceChecking for a carried observation

03BoundaryInspect source ids: wang-2022-self-consistency, lightman-2023-verify-step-by-step, snell-2024-test-time-compute

04Next moveSave one next action

Local action draftNo local draft saved yetExpand only when ready to capture one local next action

Local action draft

This draft stays locally in this browser for concept:scaling/test-time-compute.

Draft noteNext action

No local draft saved.

Evidence to inspect

Source ids to inspect: wang-2022-self-consistency, lightman-2023-verify-step-by-step, snell-2024-test-time-compute
Definition, prerequisite, and contrast concept links
The equation or code witness that makes the concept operational
One demo state that shows the invariant instead of a slogan

What would resolve this

The learner can state the mechanism in their own words
The learner can name the prerequisite that would repair confusion
The learner can predict how the mechanism changes under one perturbation

Object-attached AI handoff

I am working in Continuous Function's research reading room. Object: concept - Test-Time Compute: Spending Inference Budget on Search Object key: concept:scaling/test-time-compute Context: Scaling Anchor id: concept/concept-notebook/scaling/test-time-compute Open question: What is the smallest example that makes Test-Time Compute: Spending Inference Budget on Search click without losing the math? Evidence to inspect: - Source ids to inspect: wang-2022-self-consistency, lightman-2023-verify-step-by-step, snell-2024-test-time-compute - Definition, prerequisite, and contrast concept links - The equation or code witness that makes the concept operational - One demo state that shows the invariant instead of a slogan Deterministic role lenses for this object: - Boundary: fixed perspectives, not people, community contributions, or independent review - Source-checking summary: Treat this as a mechanism object: connect the definition to one equation, code witness, or demo before broadening the discussion. - Proposed experiment: Ask the learner to perturb one representation, then check whether the same invariant survives in math, code, and demo. - Teach/transfer move: Turn the mechanism into one sentence that predicts a neighboring concept. - Assumptions: - Source ids wang-2022-self-consistency, lightman-2023-verify-step-by-step, snell-2024-test-time-compute must support the exact object, not just the surrounding topic. - The stable content-object key lets local drafts, prompts, and route memory attach without changing the source page. - The concept explanation is local atlas prose until checked against its math, code, and source support. - Prerequisite gaps should become a repair route, not a reason to leave the object vague. - Role-lens requests: - Learner: ask for "Ask what would make "Test-Time Compute: Spending Inference Budget on Search" feel predictable rather than familiar." | assumption: Source ids wang-2022-self-consistency, lightman-2023-verify-step-by-step, snell-2024-test-time-compute must support the exact object, not just the surrounding topic. | next action: The learner can state the mechanism in their own words - Researcher: ask for "Source ids to inspect: wang-2022-self-consistency, lightman-2023-verify-step-by-step, snell-2024-test-time-compute" | assumption: The stable content-object key lets local drafts, prompts, and route memory attach without changing the source page. | next action: The learner can name the prerequisite that would repair confusion - Experimenter: ask for "Choose one variable or condition to perturb before asking for an explanation." | assumption: The concept explanation is local atlas prose until checked against its math, code, and source support. | next action: The learner can predict how the mechanism changes under one perturbation - Professor: ask for "Find the smallest transferable rule a learner could reuse without the AI." | assumption: Prerequisite gaps should become a repair route, not a reason to leave the object vague. | next action: Teach or transfer: Turn the mechanism into one sentence that predicts a neighboring concept. What would resolve this: - The learner can state the mechanism in their own words - The learner can name the prerequisite that would repair confusion - The learner can predict how the mechanism changes under one perturbation Answer as a careful research tutor: stay source-grounded, separate verified evidence from assumptions, name the relevant math objects, and end with one next action. Current deterministic role lens for this object: - Role lens: Learner - Evidence request: Ask what would make "Test-Time Compute: Spending Inference Budget on Search" feel predictable rather than familiar. - Assumption to keep visible: Source ids wang-2022-self-consistency, lightman-2023-verify-step-by-step, snell-2024-test-time-compute must support the exact object, not just the surrounding topic. - Proposed experiment: Ask the learner to perturb one representation, then check whether the same invariant survives in math, code, and demo. - Next action: The learner can state the mechanism in their own words

concept/concept-notebook/scaling/test-time-compute
concept:scaling/test-time-compute

Learning Map

Before / Now / Try / Next

BeforeScaling Laws & Emergent Abilities

NowIntuition → Math → Code → Demo

TryManipulate one control and predict the visible change.

NextTree Search Reasoning: Allocating Inference Budget Across Prefixes

Learnerpicture first Researchersource check Experimentertest the demo Professorname invariant

01Predict 02Ground 03Code 04Carry

01Intuitionready
02Mathready
03Codeready
04Interactive Demoready

Object Companion

Ask beside the selected object

Test-time compute spends extra inference budget on sampling, verification, and selection; it helps when the generator can produce good candidates and the verifier ranks them reliably.

Your question

GoalComfortStyleStuck on

Context prompt

You are my AI learning companion for Continuous Function. Current context: Scaling concept. Learning surface: Test-Time Compute: Spending Inference Budget on Search. What this page says: Test-time compute spends extra inference budget on sampling, verification, and selection; it helps when the generator can produce good candidates and the verifier ranks them reliably. Current section: Intuition, math, code, and interactive demo. Suggested next step: Manipulate one control and predict the visible change.. Learner goal: Understand the idea. Learner comfort level: New to this. Preferred explanation style: Visual first. Task: Explain the central idea in plain language, then restate it with the exact math objects from the page. Answer in a way that helps me learn: ask one clarifying question only if needed, use intuition before notation, and end with one thing I should try on the page.

Copy-only tool: this panel composes a prompt for an AI tool you already use. Nothing you enter here is sent from this page.

Domain

Scaling

scalinginferencetest-time-computeverifiersreasoning

Prerequisites

Scaling Laws & Emergent Abilities Process Reward Models: Step-Level Verifiers for Reasoning Reward Hacking: Overoptimizing Preference Proxies Decoding & Sampling: Temperature, Top-p & Inference-Time Control

Leads To

Tree Search Reasoning: Allocating Inference Budget Across Prefixes

RLHF: Reward Modeling + KL-Regularized Policy Optimization LLM Serving at Scale: Prefill, Decode & Continuous Batching Speculative Decoding: Lossless Multi-Token Generation Overparameterization & Generalization (Double Descent)

Within this domain