- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper introduces CoMILP, an LLM-driven framework for cross-component algorithm design in MILP solvers. CoMILP jointly searches over initial configurations, dynamic configuration policies, and decision rules for cut selection and branching. Three LLM agents (planning, proposal, reflection) apply component-level edits. Tree search is used to expand alternative refinement paths and balance exploration and exploitation. In an instance-specific setting, CoMILP attains the lowest solve time or primal-dual integral (often both) among the compared methods on five generated benchmarks and MIPLIB 2017.
Critical strengths
The paper is well motivated and addresses an important limitation of existing LLM-based solver design methods, which focus on either heuristic design or parameter tuning for a single component. The experiments are broad, covering the full MIPLIB 2017 benchmark set and five additional problem families against a comprehensive set of baselines.
Critical weaknesses
The main results are instance-specific: the method optimizes the PDI on a single instance, using 100 trials of up to 300 seconds each. If the objective is a reusable strategy, the paper should show a clear advantage on unseen instances, but CoMILP+Hydra is only compared to default SCIP. If the objective is instead to solve the instance at hand, the quality of the best incumbent found would be a more meaningful measure than the PDI. As it stands, the evaluation falls between these two objectives without convincingly supporting either.
Questions for authors
- Could you give some insights into why LLM4Branch and MILP-Evo perform worse than SCIP-default on MIPLIB 2017?
- On unseen instances, CoMILP+Hydra is only compared with SCIP-default. Could you discuss how it compares with the other baselines?
- Could you report the best incumbent value found by CoMILP and the baselines in your experiments?
5 comments
W1 and Q3. Incumbents and final optimality gaps
The MIPLIB results also show improvements in feasible solution quality. An incumbent is the best feasible solution found during a solve. We compare its objective value and the final optimality gap with each baseline on the same 240 instances. Pairwise wins, ties, and losses make these comparisons meaningful across MIPLIB's different objective scales and optimization directions. A win means a better feasible objective for that instance, or a smaller final gap.
Table R3.2. CoMILP wins / ties / losses against each baseline on MIPLIB.
| Comparator | Incumbent W / T / L | Final-gap W / T / L |
|---|---|---|
| SCIP-default | 100 / 134 / 6 | 117 / 100 / 23 |
| GP-BO | 71 / 124 / 45 | 80 / 93 / 67 |
| SMAC-I | 71 / 132 / 37 | 86 / 92 / 62 |
| ColdStart | 78 / 107 / 55 | 105 / 86 / 49 |
| GRIMIP | 81 / 105 / 54 | 80 / 92 / 68 |
| LLM4Branch | 111 / 94 / 35 | 124 / 67 / 49 |
| MILP-Evo | 76 / 114 / 50 | 90 / 103 / 47 |
CoMILP wins more often than it loses against every baseline for both metrics. Against GRIMIP, the strongest PDI baseline, CoMILP returns a better incumbent on 81 instances and a worse one on 54. It also finds a feasible solution in 19 cases where SCIP-default fails to do so, compared with two cases in the reverse direction.
Ties include cases where neither method finds an incumbent or both final gaps are infinite. CoMILP's win-loss advantage also holds when both methods find feasible incumbents, and when both have finite final gaps.
Q1. Interpreting the MIPLIB PDI results
Thank you for asking why LLM4Branch and MILP-Evo have higher PDI than SCIP-default. Their mean solving times improve, while their PDI increases slightly. PDI integrates the optimality gap over time, so a shorter solve can still have a larger PDI if the gap stays high early in the search.
Table R3.3. Mean solving time and PDI on MIPLIB, lower is better. PDI reduction is relative to SCIP-default.
| Method | Time (s) | PDI | PDI reduction (%) |
|---|---|---|---|
| SCIP-default | 246.6 | 15603.5 | 0.0 |
| SMAC-I | 230.2 | 14909.5 | 4.4 |
| GP-BO | 231.2 | 13703.6 | 12.2 |
| GRIMIP | 223.8 | 12006.0 | 23.1 |
| ColdStart | 245.2 | 15041.8 | 3.6 |
| LLM4Branch | 244.7 | 16218.2 | -3.9 |
| MILP-Evo | 238.4 | 15625.0 | -0.1 |
| CoMILP | 211.3 | 10235.9 | 34.4 |
In our reproductions, we retain each baseline's specified search objective and use PDI when the objective is unspecified or configurable. Accordingly, LLM4Branch optimizes node count [1], which measures search-tree size, and MILP-Evo optimizes solving time [2], which measures time to completion. PDI additionally rewards finding good incumbents and tightening bounds early. This distinction explains why shorter solving times can coexist with a larger PDI.
CoMILP's PDI-guided evolution reduces PDI by 34.4% relative to SCIP-default and also achieves the lowest mean solving time in this comparison.
References
[1] Hou et al. LLM4Branch: Large Language Model for Discovering Efficient Branching Policies of Integer Programs. arXiv, 2026.
[2] Nie et al. MILP-Evo: Closed-Loop Fully Automatic Design of MILP Solvers. arXiv, 2026.
W1 and Q2. Designing strategies for reuse on new instances
Thank you for asking us to clarify the objective and compare unseen-instance performance with the other baselines. CoMILP's contribution is the automated design of effective solver strategies. The instance-specific experiments evaluate the resulting strategies, and the unseen-instance experiments test their reuse. Reported solving time measures strategy execution.
The table below presents the learned-policy and configuration baselines from the paper alongside CoMILP+Hydra. We add a graph neural network (GNN) selector to improve on the original random forest (RF). Each selector is used throughout Hydra, guiding the generation of its own complementary portfolio and selecting a strategy at test time.
The GNN uses the original, unpresolved variable–constraint bipartite graph, combining variable and constraint features with row-normalized coefficient features on edges to predict per-strategy costs. Across all five families, we use two bidirectional GATv2 layers with hidden dimension 64, eight attention heads, sum pooling, and zero dropout. Training uses measured strategy costs and Adam (learning rate 3×10−4, weight decay 10−4, batch size 4), with a maximum of 1,000 epochs and early-stopping patience of 80 epochs. Each family's checkpoint is selected by the actual mean PDI of the strategies chosen on its validation set, then frozen for testing. Both versions use the same 200/100/100 training/validation/test split, solver seeds, and five-second SCIP-default probe followed by a selected solve of up to 295 seconds.
Table R3.1. Unseen-instance comparison. Mean solving time (s, 300-second cap) and PDI (percentage-seconds), lower is better.
GNN-based CoMILP+Hydra achieves the lowest mean PDI on SC, MK, and CFL. It is within 0.8% of the best baseline on MIS and CA and has the lowest mean solving time on SC and CFL. The GNN-based version improves on RF in every family. GNN-guided portfolio construction and test-time selection translate CoMILP's strategy-design gains into improved solving performance on new instances across all five families.
The portfolio and selector are built offline, and each new instance is solved by selecting and executing an existing strategy. On SC, this reuse reduces mean solving time from 120.9 to 54.9 seconds. The design investment is shared across the workload, while solving-time savings accumulate with reuse.