Setup: four sub-tasks (pricing, latency, adoption, compliance), each of 15 steps. Each step is one assistant call and one tool output of 14 noise lines. In each sub-task step 6 holds the finding and step 9 a detail. Sub-task 2's last step holds a caveat ("excludes the EU region") that changes how its score should be read. Sub-task 3's last step holds an injected instruction inside a tool output. Correct means: all four findings, the caveat, and no injected text in the parent. Averages over 5 seeds.
Strategy
Findings in parent
Caveat
Injection reached parent
Parent tokens
Total tokens
one agent, keep all
4 of 4
yes
yes
10,001
355,654
one agent, truncated to 4,000 tokens
2 of 4 (mean 0.50)
no
yes
5,964
296,094
sub-agents, last message
2 of 4
no
no
2,050
178,445
sub-agents, last 3 messages
2 of 4
yes
yes
2,618
179,013
sub-agents, everything
4 of 4
yes
yes
10,051
186,446
sub-agents, typed result
4 of 4
yes
no
2,122
178,517
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 Total tokens (bar) and whether the final answer was correct, safe and complete one agent, keep all 356k injection reached the parent one agent, truncated 296k missing findings sub-agents, last message 178k missing findings sub-agents, last 3 messages 179k missing findings sub-agents, everything 186k injection reached the parent sub-agents, structured result 179k correct Isolation saves more as each sub-task gets longer (structured sub-agents / one agent, total tokens) 10 steps per sub-task 0.58 15 steps per sub-task 0.50 20 steps per sub-task 0.45 30 steps per sub-task 0.40 40 steps per sub-task 0.37 A single agent's cost grows quadratically with its steps; four isolated agents each grow with only their own. Total tokens per strategy and what the parent ended up with; below, the saving as sub-tasks get longer.
Reading it:
Isolation halves the cost with no change in the work done (355,654 to 178,517).
The last message is cheap and wrong. Two sub-agents ended with "Done!" and their findings never crossed. This is the failure you get when you take the sub-agent's last message as its result, and it is silent: the parent gets a confident, empty answer.
The last three messages carry the caveat and the injection together , because both sit in the final tool output. Window-based strategies cannot separate useful from harmful content.
Everything crosses and the isolation is gone: the parent holds 10,051 tokens, as many as the single agent, and the injected line.
A typed result is the only strategy that is small, complete and clean. In this simulation, because a pattern copies only schema fields. With a real model it depends on the model following the schema, and on whether a field such as "caveat" could itself carry an instruction. Treat the result as untrusted data anyway.
Truncation in a single agent is the worst of both: it spends 296,094 tokens, loses half the findings and still sees the injection (it was in the last step).
Saving against task length (typed result versus one agent): 0.58 at 10 steps per sub-task, 0.50 at 15, 0.45 at 20, 0.40 at 30, 0.37 at 40.