| Today at a glance |
|
2
s
|
2
New papers
|
3
Categories
|
|
|
AI for Optimization
1 new papers | 1 | 52 total analyzed
| |
2026-02-11 | Peking University, Huawei Technologies Co., Ltd., Great Bay University | 2602.10450
Li et al. introduce MIPLIB-NL, a benchmark of 223 industrial-scale MILP instances (up to 10^7 variables) reverse-engineered from MIPLIB 2017, enforcing strict model-data separation. Results are sobering: SOTA models like GPT-4 and fine-tuned OR-LLMs drop from ~90% accuracy on existing toy benchmarks... ▶ Read moreLi et al. introduce MIPLIB-NL, a benchmark of 223 industrial-scale MILP instances (up to 10^7 variables) reverse-engineered from MIPLIB 2017, enforcing strict model-data separation. Results are sobering: SOTA models like GPT-4 and fine-tuned OR-LLMs drop from ~90% accuracy on existing toy benchmarks to ~18% here, failing primarily on structural consistency and index handling at scale. |
Automated Algorithm Discovery
0 new papers | 0 | 77 total analyzed
| | No new papers this period. |
Optimizing AI Systems
1 new papers | 1 | 61 total analyzed
| |
2026-02-16 | University of Cambridge, Peking University, Shanghai Jiao Tong University, Ant Group, Southeast University | 2602.14516
AMPD introduces a disaggregated serving framework tailored for multi-round LLM agents, utilizing an offline ILP solver to optimize resource allocation (TP/DP configurations) and an online adaptive routing mechanism to handle incremental prefill tasks. The results are strong, showing 67-340% improvem... ▶ Read moreAMPD introduces a disaggregated serving framework tailored for multi-round LLM agents, utilizing an offline ILP solver to optimize resource allocation (TP/DP configurations) and an online adaptive routing mechanism to handle incremental prefill tasks. The results are strong, showing 67-340% improvements in SLO attainment over vLLM and NVIDIA Dynamo by dynamically routing incremental prefill to decode workers when slack exists. 5) for partitioning prefill/decode resources under global GPU constraints and the insight that multi-agent workflows create a unique 'incremental prefill' bottleneck that standard disaggregation handles poorly. |
|