- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes TRACE, an LLM-orchestrated Bayesian Optimization framework for analog circuit transistor sizing. Unlike previous LLM-based BO approaches that generate additional candidates or refine search spaces with the LLM, TRACE dynamically determines when and how to intervene during optimization by selecting among 4 actions: Hold, Refine, Explore, and Revise, where the decision is made by an LLM using diagnostics from circuit simulation results. Experiments across four analog circuits (while the circuits are relatively small) demonstrate reduced simulation counts and wall-clock time, showing its sample-efficiency compared with conventional BO and LLM-BO baselines.
Critical strengths
- Finer control (dynamic intervention) clearly gives improved sample efficiency
- The paper provides fairly comprehensive comparisons, and the experimental results look convincing.
Critical weaknesses
- From an optimization perspective, I don’t see much methodological novelty, and the paper's main contribution is orchestrating existing operations using LLM. While TRACE's improvements over the baselines are promising, it is hard to say that the gap will still maintain with better LLM in the future.
- The benchmark circuits are relatively small.
Questions for authors
- Can you add results for larger circuits such as full differential amplifier with CMFB and biasing circuits, or a three-stage OTA?
- The authors should clarify the actual circuit topologies. The reported number of devices and independent design parameters alone does not necessarily reflect the true circuit complexity. For example, it’s unclear how a circuit with 9 devices ends up with 17 independent design parameters. Have they accounted for parameter sharing among symmetric or matched devices, which would typically have the same sizing parameters?
5 comments
A larger three-stage amplifier
3. Larger and more complex circuits
Two of the current tasks are already of substantial complexity. The BGR has 43 devices, including a PNP core (fixed 1:8:1 emitter ratio), several current-mirror groups, an amplifier, compensation, and a startup circuit; it has 67 sizing parameters before matching and 31 independent parameters after matching, with a search space of about . The LDO contains an error amplifier, a buffer stage, a PMOS pass device (multiplier 300), and RC compensation, and must meet 10 specifications, with phase margin and PSRR constrained at three load currents, over a search space of about . All four circuits and their testbenches were built by experienced circuit designers in our group and verified in the TSMC 28 nm PDK with Spectre across three PVT corners.
We agree that a larger topology provides further evidence. Following the reviewer's suggestion of a three-stage OTA, we added a three-stage OTA with active-feedback frequency compensation (AFFC) (Lee & Mok, 2003). To ensure that the topology itself is correct, we took it from the public AnalogGym suite (Li et al., 2024), where it is listed as HoiLee_AFFC_Pin_3 (netlist), and migrated it to the same TSMC 28 nm PDK with a 2.5 V supply, evaluated with the same Virtuoso/Spectre flow as the existing tasks. The migrated schematic and testbenches were reviewed by experienced analog design engineers in our group. The amplifier has 30 MOS devices and two compensation capacitors: a folded-cascode first stage with a PMOS input pair, a second gain stage, a third-stage output, a feedforward pull-up driven by the first-stage output, a Miller capacitor C0, and an active-feedback path through which C1 is fed back. To allow direct comparison with the AnalogGym netlist, the device names and sizing groups below are aligned with AnalogGym. The task has 32 independent variables, the width W, length L, and multiplier M of each of the ten groups in the table plus C0 and C1; the other 20 devices follow their group, giving 60 linked variables. The groups and the multiplier ratios within each group are the same as in AnalogGym. The only differences are that the bias current is kept fixed rather than optimized (32 instead of 33 variables) and that the ranges are set for the 28 nm PDK: L ∈ [270, 1200] nm (step 10 nm), W ∈ [0.3, 6] µm (step 20 nm), M ∈ {1, …, 20}, and C0, C1 ∈ [20, 1200] fF (step 20 fF), about grid points in total. The task has the 10 specifications below, evaluated at the same three PVT corners as the other tasks (TT25, SS125, and FF−40) with a 10 fF load; four testbenches run seven simulation jobs per corner (21 simulations per full evaluation, counted as in Table 1). The noise target is the same as for our two-stage OTA.
| Specification | Target | Specification | Target |
|---|---|---|---|
| DC gain | ≥ 110 dB | Slew rate (rise and fall) | ≥ 80 V/µs |
| GBW | ≥ 30 MHz | Settling time | ≤ 150 ns |
| Phase margin | ≥ 45° | CMRR | ≥ 70 dB |
| Input-referred noise at 100 kHz | ≤ 120 nV/√Hz | PSRR | ≥ 70 dB |
| Static power | ≤ 220 µW | Output swing | ≥ 1.8 V |
A larger three-stage amplifier (continued)
3. Larger and more complex circuits (continued)
The ten groups of the three-stage amplifier are listed below.
| Group | Devices | Role | Linked sizing |
|---|---|---|---|
| G0 | M0–M7 | PMOS bias, mirror load (M5, M6), tail (M4), pull-up bias (M7) | shared W, L, M; M4 at 2× |
| G18 | M13–M15, M18–M21, M61, M64 | NMOS bias and current sources | shared W, L; M15 at 1×, M20 and M21 at 8×, others at 4× |
| G9 | M9, M10 | PMOS input pair | identical |
| G17 | M16, M17 | folded cascode | identical |
| G22 | M22, M23 | second-stage NMOS mirror | identical |
| G59 | M59, M62 | active-feedback PMOS mirror | identical |
| G60 | M60, M63 | active-feedback common-gate pair (C1 at the source of M63) | identical |
| G11 | M11 | second-stage transconductor | — |
| G12 | M12 | feedforward pull-up from the first-stage output | — |
| G25 | M25 | third-stage NMOS output | — |
| Method | Verified | (min) | |
|---|---|---|---|
| tSS-BO | 3/3 | 7883 | 193.2 |
| ADO-LLM | 3/3 | 2100 | 110.3 |
| LEDRO | 3/3 | 1680 | 98.4 |
| TRACE | 3/3 | 1085 | 70.5 |
Means over three runs. As in Table 2, TRACE and tSS-BO use phased evaluation, while ADO-LLM and LEDRO evaluate every candidate fully.
All methods reached verified designs in all three runs. TRACE required 1085 simulations and 70.5 minutes on average, 7.3 times fewer simulations than tSS-BO and 1.9 and 1.5 times fewer than ADO-LLM and LEDRO, with correspondingly shorter wall time. It also evaluated fewer candidates than both LLM baselines (53 vs. 100 and 80), so its advantage does not come from phased evaluation alone. The gains observed on the original four circuits therefore carry over to this larger three-stage amplifier.
Novelty and stronger LLMs
We thank the reviewer for the assessment and for recognizing that dynamic intervention improves sample efficiency and that the comparisons are comprehensive. Below we address the scope of the contribution, the role of future LLMs, circuit complexity, and parameter counting, including a new three-stage amplifier experiment.
1. Methodological novelty
We agree that, from the perspective of the optimizer itself, TRACE does not propose a new surrogate or acquisition function; its BO backend is the existing tSS-BO. This is also the setting of recent LLM-assisted sizing methods: ADO-LLM pairs a standard GP/qEI loop with LLM-authored candidates, LEDRO runs TuRBO within LLM-proposed ranges, and AutoSizer selects among existing optimizers while revising the search space. Their contributions, like ours, lie in how LLM reasoning is coupled with numerical search rather than in a new surrogate or acquisition function. Within this line of work, our contribution is deciding when, and at what scope, to intervene in a running optimization. As the reviewer kindly noted in the summary, existing LLM-based BO methods use the LLM in a fixed role and on a fixed schedule. ADO-LLM inserts one LLM candidate after every four GP candidates, and LEDRO alternates LLM range proposals with fixed TuRBO budgets (Appendix D.3). In TRACE, whether, when, and at which scope to intervene (a single candidate, an unsampled region, or the task configuration) are decided online.
This decision is not trivial. The most effective single intervention differs across circuits: Explore only is cheaper than Refine only on LDO, whereas the opposite holds on BGR (Table 2). A fixed schedule is therefore unlikely to suit every circuit, and TRACE improves on the better single intervention on both circuits (by 9.8% and 15.3% in simulations). Within the same evaluator, orchestration reduces simulations by 1.46–3.64× relative to Initial design + BO. Replacing the LLM selector with a warm-started, cost-aware contextual-bandit selector over the same views and actions increased the number of evaluated candidates from 36 to 53 on LDO and from 49 to 64 on BGR (see our response to Reviewer GwXy). We will revise the contribution statement in Section 1 to state this scope explicitly.
2. Will the gap persist with stronger LLMs?
The main comparison uses the same LLM and reasoning effort for all LLM-based methods, so the observed differences are not due to a stronger model for TRACE. We cannot predict future gaps and limit our conclusions to the evaluated models. Our measurements do, however, indicate why the problem TRACE addresses should remain relevant. First, TRACE already adapts how much it relies on the LLM: with the same model, it makes about four decisions per run on OTA and COMP and 12–14 on LDO and BGR, using Explore mainly on the two harder circuits (see our response to Reviewer bKer). A fixed schedule, such as ADO-LLM's one LLM candidate in every round of five, cannot make this adjustment. Second, LLM interventions are already worth more than their share of the cost: LLM-authored candidates consume 15–22% of simulations, yet they proposed the final verified design in 13 of the 19 runs that entered BO. A stronger model would raise the value of each intervention, but LLM calls and simulations would still have a cost, so deciding when and at what scope to spend them remains the orchestration problem. Because TRACE makes this decision online, a more capable model can be used more often or at a broader scope without redesigning the workflow. The extrapolation to future models remains a hypothesis rather than a result, and we will add it to the discussion of limitations.