Research library
ZAN-RN-014Concept noteResearch question

Cost-latency-reliability frontier for agentic workflows

A concept note extending the cost-latency-reliability frontier work (ZAN-RN-010) to explicitly cover test-time compute strategies for agentic workflows.

test-time computecostlatencyagentic workflows
Technical uncertainty

Whether test-time scaling strategies (verification, rollout selection, reflection) move the frontier in ways that differ meaningfully from the retry/routing frontier already measured for compound AI systems.

Expected evidence
  • Test-time compute frontier chart
  • Comparison against retry-only baseline
  • Verifier and rollout cost accounting
Next experiment

Run the same agentic task through a retry-only policy and a verifier-plus-rollout-selection policy at matched compute budgets, then compare resulting frontiers.

Hypothesis

Test-time compute strategies produce a distinct, generally more favourable, frontier region than naive retries because verification and rollout selection can raise reliability without proportionally raising cost.

Scope

Test-time compute as a distinct frontier dimension

ZAN-RN-010 measured cost, latency, and reliability across routing and retry configurations. This note scopes whether test-time compute strategies, verification and rollout selection specifically, deserve separate frontier treatment rather than being folded into generic retry overhead.

References

Related research