🤖 AI Summary
This work addresses the long-standing reliance on manual intervention in post-routing engineering change order (ECO) for 3D integrated circuits, which suffers from poor traceability and an inability of conventional full re-routing to disentangle repair efficacy from unnecessary perturbations. The paper introduces AgenticECO, the first agent-based tool-calling framework for 3D-IC ECO, integrating an evidence-gated mechanism with EcoRoute—a minimal-perturbation routing layer—within the open-source TaiWei flow to enable attributable and low-impact defect correction. The approach precisely localizes defects via pixel-level visualization and blind testing, while ensuring correctness through structural equivalence checking and timing validation. Evaluated on nine real-world defect cases, it successfully repairs seven (versus only two by the baseline), with an average perturbation of merely 0.66%, leaving clock networks untouched; all sealed-contract cross-backbone re-runs succeed and pass DRC, timing, and equivalence checks.
📝 Abstract
As Moore's law slows, the industry is turning to three-dimensional integration; yet in merged 3D-IC flows, routed designs expose bond-level defects with no 2D analogue, and post-route engineering change orders (ECO) remain manual, expertise-bound work. Worse, the standard edit-then-fully-reroute practice entangles a repair with router churn, so a signoff number cannot be attributed to the edit that motivated it. We present AgenticECO, an evidence-gated tool-using agent workflow for 3D-IC ECO on the open-source TaiWei flow, paired with EcoRoute, a minimal-disturbance ECO-routing layer that drives the unmodified pinned router so a repair is attributable to its edit. Across nine matched natural defect cases under identical budgets, AgenticECO clears seven versus two for both full reroute and stock repair, at 0.66\% mean disturbance over cleared cases and zero clock nets touched, and a cross-backbone rerun under the same sealed contract clears all nine. Controlled studies show that the repair moves are necessary under preservation, that occupancy-aware choice buys legal landings rather than repair success, and that under tightened clocks minimal disturbance flips accept versus reject. Three preregistered visual studies localize the pixel instrument's edge to contested landing sites, and a preregistered blind diagnostic exactly restores every held-out injected defect, the only arm with zero wrong edits. Every accepted result passes routing, fresh extraction, max/min timing, DRC, and structural-equivalence gates. Code, environment, and per-episode audit artifacts are released as supplementary material.