agent-swarm-optimization
gpt-5.6-sol
agent-swarm-optimization — graded by the task's verifier against a measured baseline.
- backend
- modal
- variant
- codex azure_ai/gpt-5.6-sol
- metric
- sealed AIME avg accuracy
- actions
- 345
- duration
- 2h 57m
- recorded
- 2026-08-05
run idswarm-aime-optimization__R6Lb9Ae
Score
reward
0.448
Summary
Implemented and frozen:
- graph.json: 7 nodes, 4 active LLM calls, 3 free compute/verification nodes, 12 edges.
- optimize.py: cost-aware repeated racing, strong one-shot gating, heterogeneous topology search, and edge ablations.
- Visible validation: 8/15 (53.33%), versus best calibrated one-shot 7/15 (46.67%), with zero violations and 4.0 calls.
- All structural and prompt-length checks pass.