RI

#1Strategy-Aware Optimization Modeling with Reasoning LLMs

2026-05-04 | Beihang University, JIUTIAN Research |2605.02545

SAGE is a framework for automated optimization modeling that explicitly separates high-level modeling strategy from concrete formulation, training an LLM via supervised fine-tuning and Segment-Weighted GRPO with solver feedback. The results are backed by strong empirical evidence, improving average pass@1 from 72.7% to 80.3% over the strongest open-source baseline across eight OR benchmarks, while also producing more compact, solver-efficient constraint systems. The key insight is the use of Segment-Weighted GRPO, which assigns higher optimization weights to early, high-level strategic reasoning tokens than to later surface-level tokens, effectively mitigating the credit assignment problem in long-horizon reasoning.

#2EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible Solutions

2026-05-04 | Nanyang Technological University, The Chinese University of Hong Kong, Shenzhen, The University of Sydney, INSAIT Sofia University “St. Kliment Ohridski”, AIRS |2605.02289

EngiAgent is a multi-agent LLM framework that uses a fully connected coordinator to dynamically route debugging feedback across specialized agents (Analyzer, Modeler, Verifier, Solver) to generate feasible Pyomo models for open-ended engineering problems. The results are strongly backed by empirical data on a new 53-problem benchmark, achieving up to 75.4% feasibility with DeepSeek-V3—a massive improvement over fixed-pipeline baselines like DS-Agent. The key insight is that rigid multi-agent pipelines fail on complex OR tasks because errors can stem from semantic extraction, mathematical formulation, or solver execution; dynamically routing specific error traces to the responsible agent significantly improves the rate of physically and mathematically feasible solutions.

#3Relation Reasoning with LLMs in Expensive Optimization

2026-04-30 | Shanghai Institute of AI for Education, East China Normal University |2605.02933

This paper proposes R2SAEA, an evolutionary algorithm that uses a compact LLM (Qwen2.5) fine-tuned via GRPO as a zero-shot, relation-based surrogate model to rank offspring in expensive optimization problems. The results are rigorously backed by numerical experiments on standard continuous benchmarks (LZG, DTLZ), demonstrating that the fine-tuned model outperforms both traditional surrogate models and prompted frontier LLMs (GPT-4o) while running efficiently via quantization. The key insight is to cast surrogate evaluation as an in-context pairwise relation reasoning task, utilizing an anchor-based iterative prompt strategy to reduce $O(N^2)$ comparisons to $O(N)$ before aggregating them via voting. This is highly relevant for LLM evolutionary search; the team can adapt the GRPO relation-training pipeline and anchor-based voting mechanism to improve candidate evaluation and sample efficiency when evolving algorithms or heuristics.

#1AlphaInventory: Evolving White-Box Inventory Policies via Large Language Models with Deployment Guarantees

2026-05-01 | Tsinghua University, Boston College, Shanghai Jiao Tong University, The Chinese University of Hong Kong, Shenzhen, Shanghai University of Finance and Economics |2605.00369

AlphaInventory uses an RL-fine-tuned LLM (via GRPO) to iteratively evolve and certify white-box inventory policies for non-stationary environments. Backed by strong empirical results on synthetic and real-world retail data, it outperforms classical and deep learning baselines, discovering novel structural extensions to the Capped Base Stock policy (Tilted-CBS and Tilted-PIC). The key insight is the integration of a confidence-interval-based certification gate during the evolutionary search, which ensures that generated heuristics are statistically safe for future deployment by bridging the gap between historical replay and online performance.

#2Beyond the Training Distribution: Mapping Generalization Boundaries in Neural Program Synthesis

2026-04-30 | Friedrich Schiller University Jena |2604.27551

Voigt et al. evaluate the out-of-distribution generalization limits of transformers in program synthesis by mapping arithmetic programs into continuous syntactic and semantic manifolds. Backed by rigorous evaluation on millions of programs, they demonstrate that while transformers can extrapolate semantically using known syntax, they suffer a massive >30% performance drop when forced to extrapolate to novel syntactic structures. The key insight is that pure autoregressive scaling yields strictly log-linear returns for structural extrapolation, exposing a fundamental bottleneck in LLMs that cannot be overcome by compute alone. This is highly relevant for LLM evolutionary search, as it provides empirical proof that evolutionary algorithms are strictly necessary to navigate beyond the learned data manifold. Furthermore, the community could directly adopt their dual-manifold projection technique to measure and enforce population diversity during evolutionary search.

#1SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters

2026-05-01 | The University of Hong Kong, Stellaris AI Limited, Brain Investing Limited |2605.00528

SAGA introduces a workflow-atomic scheduler for AI agent inference on GPU clusters that uses Agent Execution Graphs to proactively manage KV cache retention across multi-step reasoning and tool-call boundaries. Backed by strong empirical results on a 64-GPU cluster, it achieves a 1.64x geometric mean speedup in task completion time and 1.22x better memory utilization over state-of-the-art vLLM with automatic prefix caching. The key insight is the Workflow-Aware LRU (WA-LRU) eviction policy, which uses the agent's execution graph to predict future KV cache reuse probabilities, effectively bridging the gap between online cache management and the offline-optimal Bélády policy.

#2Position: LLM Serving Needs Mathematical Optimization and Algorithmic Foundations, Not Just Heuristics

2026-05-02 | HKUST |2605.01280

This position paper argues that LLM inference serving must transition from generic heuristics to rigorous mathematical optimization, synthesizing recent advances in applying operations research to AI infrastructure. Rather than presenting new experiments, it aggregates empirical evidence from recent literature—such as LP-based load balancers for Mixture-of-Experts and online integer programming for data parallelism—to demonstrate that OR methods consistently outperform heuristics. The key insight is the formalization of LLM serving bottlenecks, like dynamically growing KV caches and prefill-decode asymmetry, into specific OR problem classes, alongside a roadmap of open problems including scheduling for agentic workloads.