infrastructure
The LLM Scheduler Earned Its Cost Only During the Surge
A strong fixed heuristic left no useful headroom for agents until safety-critical demand changed mid-run.
Summary
A strong fixed heuristic left no useful headroom for agents until safety-critical demand changed mid-run.
A deadline-first contract-net heuristic completed 90.2 percent of time-critical tasks across 60 simulated instances, beating 15 baselines and reaching 0.87 of an optimization upper bound. Under stationary load, the auction, per-window language-model policy and adaptation added nothing. During a mid-run safety-critical surge, the agent control plane improved over both the fixed heuristic and a bandit. The evidence is released simulation, not an autonomous-vehicle deployment.
Why it matters
A strong fixed heuristic left no useful headroom for agents until safety-critical demand changed mid-run.
Limits and context
- The evidence is released simulation, not an autonomous-vehicle deployment.
Key claims
A strong fixed heuristic left no useful headroom for agents until safety-critical demand changed mid-run.
Qualification: The evidence is released simulation, not an autonomous-vehicle deployment.
Evidence: source-2026-08-22-015
Sources
- arXiv preprint 2608.19557arXiv · primary research
Corrections
No corrections have been recorded for this story.