Large Language Model-Guided Optimization

Follow this topic Ask about this topic

This field studies how language models can use learned patterns and natural-language understanding to help search for better algorithms, programs, designs, prompts, and agent workflows. Common approaches combine model-generated proposals with evolutionary search, Bayesian optimization, reinforcement learning, or classical solvers, then use execution, simulator, or benchmark feedback to select and repair candidates. Applications range from combinatorial and scientific optimization to GPU kernels, compiler code, engineering design, and tuning language-model systems. A central open tension is that language models can suggest useful structures but may be unreliable, costly, or prone to overfitting, so robust evaluation, constraint checks, and comparisons with numerical methods remain essential.

Latest papers

613 papers101 papers in the last four weeks, up 60% on the four weeks before. 0.6% of all new papers.

Mar 24, 2026

A Theory of LLM Information Susceptibility

Large language models (LLMs) are increasingly deployed as optimization modules in agentic systems, yet the fundamental limits of such LLM-mediated improvement remain poorly understood. Here we propose a theory of LLM information susceptibility, centred on the hypothesis that when computational resources are sufficiently large, the intervention of a fixed LLM does not increase the performance susceptibility of a strategy set with respect to budget. We develop a multi-variable utility-function framework that generalizes this hypothesis to architectures with multiple co-varying budget channels, and discuss the conditions under which co-scaling can exceed the susceptibility bound. We validate the theory empirically across structurally diverse domains and model scales spanning an order of magnitude, and show that nested, co-scaling architectures open response channels unavailable to fixed configurations. These results clarify when LLM intervention helps and when it does not, demonstrating that tools from statistical physics can provide predictive constraints for the design of AI systems. If the susceptibility hypothesis holds generally, the theory suggests that nested architectures may be a necessary structural condition for open-ended agentic self-improvement.

Zhuo-Yang Song, Hua Xing Zhu

School of Physics, Peking University, Beijing 100871, China · Center for High Energy Physics, Peking University, Beijing 100871, China

Large Language Model-Guided Optimization Language Model Scaling Recursive Self-Improvement

Mar 24, 2026

Bilevel Autoresearch: Meta-Autoresearching Itself

If autoresearch is itself a form of research, then autoresearch can be applied to research itself. We present Bilevel Autoresearch, a bilevel framework in which an outer autoresearch loop improves an inner autoresearch loop by reading its code and traces, identifying bottlenecks, and generating injectable Python search mechanisms at runtime. The inner loop optimizes task performance; the outer loop optimizes how the inner loop searches. Both loops use the same LLM, so improvements come from the bilevel architecture rather than a stronger meta-level model, although the outer loop consumes additional inference and wall-clock budget. On Karpathy's GPT pretraining benchmark, the meta-autoresearch outer loop achieves a 5x improvement over the standard inner loop alone (-0.045 vs. -0.009 val_bpb), while parameter-level adjustment without mechanism change yields no reliable gain. The outer loop instantiates mechanisms from adjacent search domains, including combinatorial optimization, multi-armed bandits, and design of experiments, without human specification of the final mechanism design. Trace analysis suggests that these mechanisms break deterministic search patterns and force exploration of directions the LLM's priors avoid. The experiments demonstrate, on this benchmark, a first bilevel step: an outer loop improves the search behavior of an inner loop. Code is the mechanism carrier in this implementation, but skills, prompts, workflows, evaluators, domain principles, world-model assumptions, and memory schemas can also encode mechanisms that shape future agent behavior. This suggests a path toward recursive bootstrapping, where mechanisms discovered for the inner loop can be fed back to improve the meta-level loop itself.

Yaonan Qu, Meng Lu

Independent Researcher

Self-Improving Agents Autonomous Research Agents Large Language Model-Guided Optimization Automated Algorithm Discovery Bilevel Optimization

Mar 23, 2026

Programming Manufacturing Robots with Imperfect AI: LLMs as Tuning Experts for FDM Print Configuration Selection

We use fused deposition modeling (FDM) 3D printing as a case study of how manufacturing robots can use imperfect AI. In FDM, print configuration strongly affects output quality. Yet, novice users typically rely on default configurations, trial-and-error, or direct recommendations from generic AI models (e.g., ChatGPT). These strategies can produce complete prints, but they do not reliably meet specific objectives. We present a modular approach that treats an LLM as a source of tuning expertise. We embed this source of expertise within a Bayesian optimization loop. An approximate evaluator scores each candidate print configuration and returns structured diagnostics, which the LLM uses to propose natural-language adjustments that are compiled into machine-actionable guidance for optimization. On 100 Thingi10k parts, our LLM-guided loop achieves the best configuration on 78% objects with 0% likely-to-fail cases, while direct AI model recommendations are rarely best and exhibit 15% likely-to-fail cases. These results suggest that LLMs provide more value as constrained decision modules in optimization loops than as end-to-end oracles for print configuration selection. We expect this result to extend to broader LLM-based robot programming.

Ekta U. Samani, Christopher G. Atkeson

Robotics Institute at Carnegie Mellon University

Manufacturing Large Language Model-Guided Optimization Robotics Additive Manufacturing

Mar 19, 2026

BeamAgent: LLM-Aided MIMO Beamforming with Decoupled Intent Parsing and Alternating Optimization for Joint Site Selection and Precoding

Integrating large language models (LLMs) into wireless communication optimization is a promising yet challenging direction. Existing approaches either use LLMs as black-box solvers or code generators, tightly coupling them with numerical computation. However, LLMs lack the precision required for physical-layer optimization, and the scarcity of wireless training data makes domain-specific fine-tuning impractical. We propose BeamAgent, an LLM-aided MIMO beamforming framework that explicitly decouples semantic intent parsing from numerical optimization. The LLM serves solely as a semantic translator that converts natural language descriptions into structured spatial constraints. A dedicated gradient-based optimizer then jointly solves the discrete base station site selection and continuous precoding design through an alternating optimization algorithm. A scene-aware prompt enables grounded spatial reasoning without fine-tuning, and a multi-round interaction mechanism with dual-layer intent classification ensures robust constraint verification. A penalty-based loss function enforces dark-zone power constraints while releasing optimization degrees of freedom for bright-zone gain maximization. Experiments on a ray-tracing-based urban MIMO scenario show that BeamAgent achieves a bright-zone power of 84.0,dB, outperforming exhaustive zero-forcing by 7.1 dB under the same dark-zone constraint. The end-to-end system reaches within 3.3 dB of the expert upper bound, with the full optimization completing in under 2 s on a laptop.

Xiucheng Wang, Yue Zhang, Nan Cheng

State Key Laboratory of ISN and School of Telecommunications Engineering, Xidian University, Xi’an 710071, China

Wireless Resource Allocation Large Language Model-Guided Optimization Natural Language to Optimization Modeling

Mar 19, 2026

POET: Power-Oriented Evolutionary Tuning for LLM-Based RTL PPA Optimization

Applying large language models (LLMs) to RTL code optimization for improved power, performance, and area (PPA) faces two key challenges: ensuring functional correctness of optimized designs despite LLM hallucination, and systematically prioritizing power reduction within the multi-objective PPA trade-off space. We propose POET (Power-Oriented Evolutionary Tuning), a framework that addresses both challenges. For functional correctness, POET introduces a differential-testing-based testbench generation pipeline that treats the original design as a functional oracle, using deterministic simulation to produce golden references and eliminating LLM hallucination from the verification process. For PPA optimization, POET employs an LLM-driven evolutionary mechanism with non-dominated sorting, power-first intra-level ranking, and proportional survivor selection to steer the search toward the low-power region of the Pareto front without manual weight tuning. Evaluated on the RTL-OPT benchmark across 40 diverse RTL designs, POET achieves 100% functional correctness, the best power on all 40 designs, and competitive area and delay improvements.

Heng Ping, Peiyu Zhang, Zhenkun Wang +5

University of Southern California, United States

Large Language Model-Guided Optimization Evolutionary Optimization

Mar 16, 2026

FormulaCode: Evaluating Agentic Optimization on Large Codebases

Large language model (LLM) coding agents increasingly operate at the repository level, motivating benchmarks that evaluate their ability to optimize entire codebases under realistic constraints. Existing code benchmarks largely rely on synthetic tasks, binary correctness signals, or single-objective evaluation, limiting their ability to assess holistic optimization behavior. We introduce FormulaCode, a benchmark for evaluating agentic optimization on large, real-world codebases with fine-grained, multi-objective performance metrics. FormulaCode comprises 957 performance bottlenecks mined from scientific Python repositories on GitHub, each paired with expert-authored patches and, on average, 264.6 community-maintained performance workloads per task, enabling the holistic ability of LLM agents to optimize codebases under realistic correctness and performance constraints. Our evaluations reveal that repository-scale, multi-objective optimization remains a major challenge for frontier LLM agents. Project website at: https://formula-code.github.io

Atharva Sehgal, James Hou, Akanksha Sarkar +4

The University of Texas at Austin · California Institute of Technology · Cornell University

Coding Agent Benchmarks Code Optimization AI Agent Benchmarks Large Language Model-Guided Optimization

Mar 16, 2026

POLCA: Stochastic Generative Optimization with LLM

Optimizing complex systems, ranging from LLM prompts to multi-turn agents, traditionally requires labor-intensive manual iteration. We formalize this challenge as a stochastic generative optimization problem where a generative language model acts as the optimizer, guided by numerical rewards and text feedback to discover the best system. We introduce Prioritized Optimization with Local Contextual Aggregation (POLCA), a scalable framework designed to handle stochasticity in optimization -- such as noisy feedback, sampling minibatches, and stochastic system behaviors -- while effectively managing the unconstrained expansion of solution space. POLCA maintains a priority queue to manage the exploration-exploitation tradeoff, systematically tracking candidate solutions and their evaluation histories. To enhance efficiency, we integrate an

\varepsilon

-Net mechanism to maintain parameter diversity and an LLM Summarizer to perform meta-learning across historical trials. We theoretically prove that POLCA converges to near-optimal candidate solutions under stochasticity. We evaluate our framework on diverse benchmarks, including

τ

-bench, HotpotQA (agent optimization), VeriBench (code translation) and KernelBench (CUDA kernel generation). Experimental results demonstrate that POLCA achieves robust, sample and time-efficient performance, consistently outperforming state-of-the-art algorithms in both deterministic and stochastic problems. The codebase for this work is publicly available at https://github.com/rlx-lab/POLCA.

Xuanfei Ren, Allen Nie, Tengyang Xie +1

University of Wisconsin-Madison, Madison, WI · Google DeepMind, Mountain View, CA · Google Research, Kirkland, WA

Large Language Model-Guided Optimization Stochastic Optimization LLM Agent Workflow Optimization

Mar 15, 2026

CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad

Evolve-based agent such as AlphaEvolve is one of the notable successes in using Large Language Models (LLMs) to build AI Scientists. These agents tackle open-ended scientific problems by iteratively improving and evolving programs, leveraging the prior knowledge and reasoning capabilities of LLMs. Despite the success, existing evolve-based agents lack targeted guidance for evolution and effective mechanisms for organizing and utilizing knowledge acquired from past evolutionary experience. Consequently, they suffer from decreasing evolution efficiency and exhibit oscillatory behavior when approaching known performance boundaries. To mitigate the gap, we develop CausalEvolve, equipped with a causal scratchpad that leverages LLMs to identify and reason about guiding factors for evolution. At the beginning, CausalEvolve first identifies outcome-level factors that offer complementary inspirations in improving the target objective. During the evolution, CausalEvolve also inspects surprise patterns during the evolution and abductive reasoning to hypothesize new factors, which in turn offer novel directions. Through comprehensive experiments, we show that CausalEvolve effectively improves the evolutionary efficiency and discovers better solutions in 4 challenging open-ended scientific tasks.

Yongqiang Chen, Chenxi Liu, Zhenhao Chen +3

MBZUAI · Carnegie Mellon University · TMLR Group, Hong Kong Baptist University +1

AI Agents for Scientific Discovery Large Language Model-Guided Scientific Discovery Open-Ended Evolution Large Language Model-Guided Optimization

Mar 13, 2026

SemRep: Generative Code Representation Learning with Code Transformations

Code transformation is a foundational capability in the software development process, where its effectiveness relies on constructing a high-quality code representation to characterize the input code semantics and guide the transformation. Existing approaches treat code transformation as an end-to-end learning task, leaving the construction of the representation needed for semantic reasoning implicit in model weights or relying on rigid compiler-level abstractions. We present SemRep, a framework that improves code transformation through generative code representation learning. Our key insight is to employ the semantics-preserving transformations as the intermediate representation, which serves as both a generative mid-training task and the guidance for subsequent instruction-specific code transformations. Across general code editing and optimization tasks (e.g., GPU kernel optimization), SemRep outperforms the extensively finetuned baselines with strictly the same training budget by 6.9% in correctness, 1.1x in performance, 13.9% in generalization, and 6.7% in robustness. With the improved exploration of diverse code transformations, SemRep is particularly amenable to evolutionary search. Combined with an evolutionary coding agent, SemRep finds optimizations that 685B larger-weight baselines fail to discover while achieving the same performance with 25% less inference compute.

Weichen Li, Jiamin Song, Bogdan Alexandru Stoica +4

The University of Chicago · University of Illinois Urbana-Champaign · Columbia University +1

Code Optimization Large Language Model-Guided Optimization

Mar 13, 2026

PrefPO: Pairwise Preference Prompt Optimization

Prompt engineering is effective but labor-intensive, motivating automated optimization methods. Existing methods typically require labeled datasets, which are often unavailable, and produce verbose, repetitive prompts. We introduce PrefPO, a minimal prompt optimization approach inspired by reinforcement learning from human feedback (RLHF). Its preference-based approach reduces the need for labeled data and hyperparameter tuning-only a starting prompt and natural language criteria are needed. PrefPO uses an LLM discriminator to express pairwise preferences over model outputs and provide feedback to an LLM optimizer, iteratively improving performance. We evaluate PrefPO on 9 BIG-Bench Hard (BBH) tasks and IFEval-Hard, a newly-curated, challenging subset of IFEval. PrefPO matches or exceeds SOTA methods, including GEPA, MIPRO, and TextGrad, on 6/9 tasks and performs comparably to TextGrad on IFEval-Hard (82.4% vs 84.5%). Unlike other methods, PrefPO can optimize in both labeled and unlabeled settings. Without labels, PrefPO closely matches its labeled performance on 6/9 tasks, proving effective without ground truth. PrefPO also improves prompt hygiene: we find existing methods produce prompts 14.7x their original length or with 34% repetitive content; PrefPO reduces these issues by 3-5x. Furthermore, both LLM and human judges rate PrefPO's prompts higher than TextGrad's. Finally, we identify prompt hacking in prompt optimizers, where methods game evaluation criteria, and find PrefPO is susceptible at half the rate of TextGrad (37% vs 86%), generating fewer brittle, misaligned prompts.

Rahul Singhal, Pradyumna Tambwekar, Karime Maamari

Distyl AI

Automatic Prompt Optimization Prompt Optimization Large Language Model-Guided Optimization

Mar 13, 2026

SciDesignBench: Benchmarking and Improving Language Models for Scientific Inverse Design

Many of the most important problems in science and engineering are inverse problems: given a desired outcome, find a design that achieves it. Evaluating whether a candidate meets the spec is often routine; a binding energy can be computed, a reactor yield simulated, a pharmacokinetic profile predicted. But searching a combinatorial design space for inputs that satisfy those targets is fundamentally harder. We introduce SciDesignBench, a benchmark of 520 simulator-grounded tasks across 14 scientific domains and five settings spanning single-shot design, short-horizon feedback, long-horizon refinement, and seed-design optimization. On the 10-domain shared-core subset, the best zero-shot model reaches only 29.0% success despite substantially higher parse rates. Simulator feedback helps, but the leaderboard changes with horizon: Sonnet 4.5 is strongest in one-turn de novo design, whereas Opus 4.6 is strongest after 20 turns of simulator-grounded refinement. Providing a starting seed design reshuffles the leaderboard again, demonstrating that constrained modification requires a fundamentally different capability from unconstrained de novo generation. We then introduce RLSF, a simulator-feedback training recipe. An RLSF-tuned 8B model raises single-turn success rates by 8-17 percentage points across three domains. Together, these results position simulator-grounded inverse design as both a benchmark for scientific reasoning and a practical substrate for amortizing expensive test-time compute into model weights.

David van Dijk, Ivan Vrkic

CellType Inc.

Inverse Design Large Language Model-Guided Optimization Scientific Reasoning in Language Models Benchmark Design Fine-Tuning

Mar 13, 2026

Deciphering Scientific Reasoning Steps from Outcome Data for Molecule Optimization

Emerging reasoning models hold promise for automating scientific discovery. However, their training is hindered by a critical supervision gap: experimental outcomes are abundant, whereas intermediate reasoning steps are rarely documented at scale. To bridge this gap, we propose DESRO, a framework for deciphering scientific reasoning from outcomes. By analyzing shared patterns and key differences within grouped data, a large language model (LLM) can recover the underlying logic. We instantiate this framework in molecule optimization, a pivotal stage in drug discovery that traditionally relies on the iterative reasoning of medicinal chemists. Across 2.3 million molecular property records, our framework infers optimization rationales by grouping molecules with shared fragments, then using an LLM to analyze how structural variations correlate with property differences. Based on the derived data, we train a model that conducts molecule optimization through an interpretable reasoning process. DESRO achieves the highest success rates on 15 out of 18 tasks, spanning both single- and multi-property optimization of bioactivity and ADMET properties. The reasoning process enables robust generalization to out-of-distribution scenarios, including novel property combinations, unseen biological targets, and unseen properties defined solely by natural language descriptions. In retrospective case studies under strict temporal splits, the model autonomously reconstructs expert-level lead optimization trajectories. Additionally, our framework extends beyond molecule optimization to reaction ligand selection. Our results establish deciphering reasoning steps from outcome data as a viable paradigm for enabling scientific reasoning, providing a scalable approach to accelerate scientific discovery.

Zequn Liu, Kehan Wu, Shufang Xie +5

Zhongguancun Academy · School of Computer Science and Technology, University of Science and Technology of China · Global Health Drug Discovery Institute

Scientific Reasoning in Language Models Molecular Optimization Large Language Model-Guided Optimization LLM Reasoning Drug Discovery

Mar 12, 2026

KernelFoundry: Hardware-aware evolutionary GPU kernel optimization

GPU kernel optimization challenges LLMs beyond standard coding tasks, as it requires an understanding of hardware architecture, parallel computing optimization strategies, and profiling outputs. However, most existing approaches leveraging LLMs for kernel generation apply standard prompting and feedback loops, considering hardware only through profiling feedback. We introduce KernelFoundry, an evolutionary framework that efficiently explores the space of GPU kernels through (1) MAP-Elites quality diversity search with kernel-specific behavioral dimensions to sustain exploration; (2) meta-prompt evolution that co-evolves prompts with kernels to uncover task-specific optimization strategies, and (3) a template-based parameter optimization approach to tune kernels to inputs and hardware. We evaluate this framework on Kernel-Bench, robust-kbench and custom tasks, generating SYCL kernels as a cross-platform GPU programming paradigm, and CUDA kernels for comparison to prior work. Our approach consistently outperforms the baseline methods and achieves an average speedup of 2.3 on KernelBench for SYCL. Moreover, KernelFoundry is implemented as a distributed framework with remote access to diverse hardware, allowing quick benchmarking and featuring a flexible user input layer to support kernel generation for a wide range of real use cases beyond benchmarking.

Nina Wiedemann, Quentin Leboutet, Michael Paulitsch +2

Intel Corporation

GPU Kernel Optimization GPU Acceleration Evolutionary Optimization Large Language Model-Guided Optimization LLM-Based Program Synthesis GPU Kernel Generation+1

Mar 12, 2026

Resource-Efficient Iterative LLM-Based NAS with Feedback Memory

Neural Architecture Search (NAS) automates network design, but conventional methods demand substantial computational resources. We propose a closed-loop pipeline leveraging large language models (LLMs) to iteratively generate, evaluate, and refine convolutional neural network architectures for image classification on a single consumer-grade GPU without LLM fine-tuning. Central to our approach is a historical feedback memory inspired by Markov chains: a sliding window of

K{=}5

recent improvement attempts keeps context size constant while providing sufficient signal for iterative learning. Unlike prior LLM optimizers that discard failure trajectories, each history entry is a structured diagnostic triple -- recording the identified problem, suggested modification, and resulting outcome -- treating code execution failures as first-class learning signals. A dual-LLM specialization reduces per-call cognitive load: a Code Generator produces executable PyTorch architectures while a Prompt Improver handles diagnostic reasoning. Since both the LLM and architecture training share limited VRAM, the search implicitly favors compact, hardware-efficient models suited to edge deployment. We evaluate three frozen instruction-tuned LLMs (

{\leq}7

B parameters) across up to 2000 iterations in an unconstrained open code space, using one-epoch proxy accuracy on CIFAR-10, CIFAR-100, and ImageNette as a fast ranking signal. On CIFAR-10, DeepSeek-Coder-6.7B improves from 28.2% to 69.2%, Qwen2.5-7B from 50.0% to 71.5%, and GLM-5 from 43.2% to 62.0%. A full 2000-iteration search completes in

{\approx}18

GPU hours on a single RTX~4090, establishing a low-budget, reproducible, and hardware-aware paradigm for LLM-driven NAS without cloud infrastructure.

Xiaojie Gu, Dmitry Ignatov, Radu Timofte

Computer Vision Lab, CAIDAS & IFI, University of Würzburg, Germany

Large Language Model-Guided NAS Neural Architecture Search Large Language Model-Guided Optimization Hardware-Aware NAS

Mar 11, 2026

Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis

Deploying Large Language Models to data-scarce programming domains poses significant challenges, particularly for kernel synthesis on emerging Domain-Specific Architectures where a "Data Wall" limits available training data. While models excel on data-rich platforms like CUDA, they suffer catastrophic performance drops on data-scarce ecosystems such as NPU programming. To overcome this cold-start barrier without expensive fine-tuning, we introduce EvoKernel, a self-evolving agentic framework that automates the lifecycle of kernel synthesis from initial drafting to continual refining. EvoKernel addresses this by formulating the synthesis process as a memory-based reinforcement learning task. Through a novel value-driven retrieval mechanism, it learns stage-specific Q-values that prioritize experiences based on their contribution to the current objective, whether bootstrapping a feasible draft or iteratively refining latency. Furthermore, by enabling cross-task memory sharing, the agent generalizes insights from simple to complex operators. By building an NPU variant of KernelBench and evaluating on it, EvoKernel improves frontier models' correctness from 11.0% to 83.0% and achieves a median speedup of 3.60x over initial drafts through iterative refinement. This demonstrates that value-guided experience accumulation allows general-purpose models to master the kernel synthesis task on niche hardware ecosystems. Our official page is available at https://evokernel.zhuo.li.

Yujie Zheng, Zhuo Li, Shengtao Zhang +8

Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · Independent Researcher +1

Memory-Augmented Language Model Agents RL for Code Generation Large Language Model-Guided Optimization Continual Learning for LLM Agents

Mar 11, 2026

SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs

Evaluating LLM agents for scientific tasks has focused on token costs while ignoring tool-use costs like simulation time and experimental resources. As a result, metrics like pass@k become impractical under realistic budget constraints. To address this gap, we introduce SimulCost, the first benchmark targeting cost-sensitive parameter tuning in physics simulations. SimulCost compares LLM tuning cost-sensitive parameters against traditional scanning approach in both accuracy and computational cost, spanning 2,643 single-round (initial guess) and 2,304 multi-round (adjustment by trial-and-error) tasks across 11 simulators from fluid dynamics, solid mechanics, and plasma physics, whose costs are analytically defined and platform-independent. A twelfth simulator, a production plasma code measurable only by wall clock, is reported separately. Frontier LLMs achieve 45-62% success rates in single-round mode, dropping to 34-50% under high accuracy requirements, rendering their initial guesses unreliable especially for high accuracy tasks. Multi-round mode improves rates to 66-81%, but LLMs are 1.5-2.7x slower than traditional scanning, making them uneconomical choices. We also investigate parameter group correlations for knowledge transfer potential, and the impact of in-context examples and reasoning effort, providing practical implications for deployment and fine-tuning. We open-source SimulCost as a static benchmark and extensible toolkit to facilitate research on improving cost-aware agentic designs for physics simulations, and for expanding new simulation environments. Code and data are available at https://github.com/Rose-STL-Lab/SimulCost-Bench

Yadi Cao, Sicheng Lai, Jiahe Huang +12

University of California San Diego · The Chinese University of Hong Kong, Shenzhen · Peking University +3

AI Agent Benchmarks Large Language Model-Guided Optimization LLM Agent Evaluation Benchmark Design Physics-Based Simulation

Mar 11, 2026

Utility Function is All You Need: LLM-based Congestion Control

Congestion is a critical and challenging problem in communication networks. Congestion control protocols allow network applications to tune their sending rate in a way that optimizes their performance and the network utilization. In the common distributed setting, the applications cannot collaborate with each other directly but instead obtain similar estimations about the state of the network using latency and loss measurements. These measurements can be fed into analytical functions, referred to by utility functions, whose gradients help each and all distributed senders to converge to a desired state. The above process becomes extremely complicated when each application has different optimization goals and requirements. Crafting these utilization functions has been a research subject for over a decade, with small incremental changes requiring rigorous mathematical analysis as well as real-world experiments. In this work, we present GenCC, a framework leveraging the code generation capabilities of large language models (LLMs) coupled with realistic network testbed, to design congestion control utility functions. Using GenCC, we analyze the impact of different guidance strategies on the performance of the generated protocols, considering application-specific requirements and network capacity. Our results show that LLMs, guided by either a generative code evolution strategy or mathematical chain-of-thought (CoT), can obtain close to optimal results, improving state-of-the-art congestion control protocols by 37%-142%, depending on the scenario.

Neta Rozen-Schiff, Liron Schiff, Stefan Schmid

TU Berlin · Akamai Technologies · TU Berlin, Weizenbaum Institute & Fraunhofer SIT

Large Language Model-Guided Optimization LLM Code Generation

Mar 10, 2026

From Phase Prediction to Phase Design: A ReAct Agent Framework for High-Entropy Alloy Discovery

Discovering high-entropy alloy (HEA) compositions that reliably form a target crystal phase is a high-dimensional inverse design problem that conventional trial-and-error experimentation and forward-only machine learning models cannot efficiently solve. Here we present a ReAct (Reasoning + Acting) LLM agent that autonomously proposes, validates, and iteratively refines HEA compositions by querying a calibrated XGBoost surrogate trained on 4,753 experimental records across four phases (FCC, BCC, BCC+FCC, BCC+IM), achieving 94.66% accuracy (F1 macro = 0.896). Against Bayesian optimisation (BO) and random search baselines, the full-prompt agent achieves descriptor-space rediscovery rates of 38%, 18%, and 38% for FCC, BCC, and BCC+FCC (Mann--Whitney

p \leq 0.039

), with proposals lying 2.4--22.8

\times

closer to the experimental phase manifold than random search. An ablation reveals that domain priors shift the agent from landmark-alloy recall toward compositionally diverse exploration -- an uninformed agent scores higher rediscovery by concentrating on literature-dense families, while the full-prompt agent explores underrepresented space (unique ratio 1.0 vs.\ 0.39 for BCC+FCC). These regimes represent distinct criteria: proximity to known literature versus genuine discovery. Spearman analysis confirms agent reasoning is statistically aligned with empirical phase distributions (

ρ= 0.736

,

p = 0.004

for BCC). This work establishes LLM-guided agentic reasoning as a principled, transparent, and manifold-aware complement to gradient-free optimisation for inverse alloy design.

Iman Peivaste, Salim Belouettar

Luxembourg Institute of Science and Technology (LIST), 5, Avenue des Hauts-Fourneaux, Esch-sur-Alzette, 4362, Luxembourg · Department of Physics and Materials Science, University of Luxembourg, L-4365 Esch-sur-Alzette, Luxembourg

Inverse Design Materials Science Large Language Model-Guided Scientific Discovery AI Agents for Scientific Discovery Large Language Model-Guided Optimization

Mar 10, 2026

KernelClaw: A Multi-Agent Framework for GPU Kernel Optimization with Dual-Memory Mechanisms

Improving GPU kernel efficiency is crucial for efficient AI systems. Recent work has explored leveraging large language models (LLMs) for GPU kernel generation and optimization. However, existing LLM-based kernel optimization pipelines typically rely on opaque, implicitly learned heuristics within the LLMs to determine optimization strategies. This leads to inefficient trial-and-error and weakly interpretable optimizations. Our key insight is to replace implicit heuristics with expert optimization knowledge that is aware of task trajectories. Specifically, we present KernelClaw, a multi-agent framework with a dual-level memory architecture. KernelClaw operates by coordinating agents with long-term memory of reusable expert knowledge and short-term memory to prevent repetitive backtracking. On KernelBench Levels 1-3, KernelClaw achieves a 100% success rate and average speedups of 6.98x, 7.89x, and 1.94x over Torch Eager on Levels 1, 2, and 3, respectively, outperforming prior baselines. Code is available at https://github.com/0satan0/KernelMem/.

Qitong Sun, Jun Han, Tianlin Li +6

School of Computer Science and Engineering, Beihang University, China · Zhejiang Lab, China · Nanyang Technological University, Singapore

GPU Kernel Optimization GPU Kernel Generation Large Language Model-Guided Optimization Agent Skill Learning

Mar 9, 2026

AutoAdapt: An Automated Domain Adaptation Framework for LLMs

Large language models (LLMs) excel in open domains but struggle in specialized settings with limited data and evolving knowledge. Existing domain adaptation practices rely heavily on manual trial-and-error processes, incur significant hyperparameter complexity, and are highly sensitive to data and user preferences, all under the high cost of LLM training. Moreover, the interactions and transferability of hyperparameter choices across models/domains remain poorly understood, making adaptation gains uncertain even with substantial effort. To solve these challenges, we present AutoAdapt, a novel end-to-end automated framework for efficient and reliable LLM domain adaptation. AutoAdapt leverages curated knowledge bases from literature and open-source resources to reduce expert intervention. To narrow the search space, we design a novel multi-agent debating system in which proposal and critic agents iteratively interact to align user intent and incorporate data signals and best practices into the planning process. To optimize hyperparameters under tight budgets, we propose AutoRefine, a novel LLM-based surrogate that replaces costly black-box search. Across 10 tasks, AutoAdapt achieves a 25% average relative accuracy improvement over state-of-the-art Automated Machine Learning baselines with minimal overhead.

Sidharth Sinha, Anson Bastos, Xuchao Zhang +3

Microsoft, M365 Research, India · Microsoft, M365 Research, Redmond · Microsoft Research, India

Domain Adaptation for LLMs Domain Adaptation Large Language Model-Guided Optimization

Mar 8, 2026

Large Language Model for Discrete Optimization Problems: Evaluation and Step-by-step Reasoning

This work investigated the capabilities of different models, including the Llama-3 series of models and CHATGPT, with different forms of expression in solving discrete optimization problems by testing natural language datasets. In contrast to formal datasets with a limited scope of parameters, our dataset included a variety of problem types in discrete optimization problems and featured a wide range of parameter magnitudes, including instances with large parameter sets, integrated with augmented data. It aimed to (1) provide an overview of LLMs' ability in large-scale problems, (2) offer suggestions to those who want to solve discrete optimization problems automatically, and (3) regard the performance as a benchmark for future research. These datasets included original, expanded and augmented datasets. Among these three datasets, the original and augmented ones aimed for evaluation while the expanded one may help finetune a new model. In the experiment, comparisons were made between strong and week models, CoT methods and No-CoT methods on various datasets. The result showed that stronger model performed better reasonably. Contrary to general agreement, it also showed that CoT technique was not always effective regarding the capability of models and disordered datasets improved performance of models on easy to-understand problems, even though they were sometimes with high variance, a manifestation of instability. Therefore, for those who seek to enhance the automatic resolution of discrete optimization problems, it is recommended to consult the results, including the line charts presented in the Appendix, as well as the conclusions drawn in this study for relevant suggestions.

Tianhao Qian, Guilin Qi, Z. Y. Wu +3

School of Mathematics, Southeast University, Nanjing, China · School of Computer Science and Engineering, Southeast University, Nanjing, China · School of Mathematical Sciences, Chongqing Normal University, Chongqing, China

LLM Evaluation Large Language Model-Guided Optimization Combinatorial Optimization CoT Reasoning

Mar 8, 2026

CDEoH: Category-Driven Automatic Algorithm Design With Large Language Models

With the rapid advancement of large language models (LLMs), LLM-based heuristic search methods have demonstrated strong capabilities in automated algorithm generation. However, their evolutionary processes often suffer from instability and premature convergence. Existing approaches mainly address this issue through prompt engineering or by jointly evolving thought and code, while largely overlooking the critical role of algorithmic category diversity in maintaining evolutionary stability. To this end, we propose Category Driven Automatic Algorithm Design with Large Language Models (CDEoH), which explicitly models algorithm categories and jointly balances performance and category diversity in population management, enabling parallel exploration across multiple algorithmic paradigms. Extensive experiments on representative combinatorial optimization problems across multiple scales demonstrate that CDEoH effectively mitigates convergence toward a single evolutionary direction, significantly enhancing evolutionary stability and achieving consistently superior average performance across tasks and scales.

Yu-Nian Wang, Shen-Huan Lyu, Ning Chen +3

Key Laboratory of Water Big Data Technology of Ministry of Water Resources, College of Computer Science and Software Engineering, Hohai University, Nanjing, China · Department of Computer Science, City University of Hong Kong, Hong Kong, China · State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China

Automated Heuristic Design Automated Algorithm Discovery Large Language Model-Guided Optimization Evolutionary Optimization Combinatorial Optimization

Mar 7, 2026

Making LLMs Optimize Multi-Scenario CUDA Kernels Like Experts

Optimizing GPU kernels manually is a challenging and time-consuming task. With the rapid development of LLMs, automated GPU kernel optimization is gradually becoming a tangible reality. However, current LLM-driven automated optimization methods narrowly focus on machine learning applications, such as PyTorch operator optimization, while overlooking broader domains like sparse matrix operations in scientific computing. Extending to these broader applications brings new challenges for the benchmark and algorithm. Therefore, developing a general-purpose automated kernel optimization method becomes our primary focus. In this paper, we address the absence of systematic evaluation for multi-scenario settings by introducing MSKernelBench, which spans multiple scenarios, including fundamental algebraic operations, common LLM kernels, sparse matrix operators, and scientific computing routines, each supporting both FP32 and BF16 precision. Building on this benchmark, we introduce CUDAMaster, a multi-agent, hardware-aware system for kernel optimization that leverages profiling information and automatically constructs the full compilation and execution toolchain. Experimental results demonstrate that CUDAMaster achieves significant speedups across most operators, outperforming Astra by about 35%. In several cases, its performance matches or surpasses that of highly optimized, closed-source libraries such as cuBLAS. A demo showcasing the original and optimized code for each operator is available at https://hanyx2021.github.io/MSKernelBenchDemo/.

Yuxuan Han, Meng-Hao Guo, Zhengning Liu +2

Tsinghua University · Proxseer Inc.

Sparse Matrix Multiplication GPU Kernel Optimization Large Language Model-Guided Optimization High-Performance Computing

Mar 7, 2026

DyACE: Dynamic Algorithm Co-evolution for Online Automated Heuristic Design with Large Language Model

The prevailing paradigm in Automated Heuristic Design (AHD) typically relies on the assumption that a single, fixed algorithm can effectively navigate the shifting dynamics of a combinatorial search. This static approach often proves inadequate for Perturbative Heuristics, where the optimal algorithm for escaping local optima depends heavily on the specific search phase. To address this limitation, we reformulate heuristic design as a Non-stationary Bi-level Control problem and introduce DyACE (Dynamic Algorithm Co-evolution). Distinct from standard open-loop solvers, DyACE use a Receding Horizon Control architecture to continuously co-evolve the heuristic logic alongside the solution population. A core element of this framework is the Look-Ahead Rollout Search, which queries the landscape geometry to extract Search Trajectory Features. This sensory feedback allows the Large Language Model (LLM) to function as a grounded meta-controller, prescribing phase-specific interventions tailored to the real-time search status. We validate DyACE on three representative combinatorial optimization benchmarks. The results demonstrate that our method significantly outperforms state-of-the-art static baselines, exhibiting superior scalability in high-dimensional search spaces. Furthermore, ablation studies confirm that dynamic adaptation fails without grounded perception, often performing worse than static algorithms. This indicates that DyACE's effectiveness stems from the causal alignment between the synthesized logic and the verified gradients of the optimization landscape.

Guidong Lu, Yiping Liu, Xiangxiang Zeng

Automated Heuristic Design Combinatorial Optimization Large Language Model-Guided Optimization

Mar 7, 2026

Large Language Model-Driven Full-Component Evolution of Adaptive Large Neighborhood Search

Adaptive Large Neighborhood Search (ALNS) is a prominent metaheuristic and a widely adopted approach for production and logistics optimization. However, it has long relied on hand-crafted components built on expert experience, which makes development slow and costly to adapt to new problems. This paper proposes a closed-loop, large-language-model-driven evolutionary framework that decouples ALNS and automatically rebuilds all of its components. We break ALNS into seven key modules: destroy, repair, operator selection, weight update, initial solution construction, acceptance rule, and destroy-rate control, and evolve each module through a dedicated task. By incorporating the Multi-dimensional Archive of Phenotypic Elites mechanism, the framework maintains a multi-dimensional elite archive to simultaneously drive the evolution of solution quality and strategic diversity. In addition, we design multiple mechanisms, including parallel and sequential multi-module evolution as well as single-expert-driven and multi-expert-driven evolution, to systematically evaluate the impact of different evolutionary paradigms on algorithm generation performance. Evaluations on Traveling Salesman Problem and Capacitated Vehicle Routing Problem benchmarks demonstrate that evolved algorithms consistently outperform optimized classic ALNS baselines under both fixed-iteration and fixed-time limits. The framework also shows a degree of generalizability and cross-problem transferability. Code analysis also uncovers several counterintuitive yet meaningful design patterns that emerged naturally during evolution, offering practical and theoretical insights for future ALNS design. Finally, comparisons across multiple language models highlight clear differences in their ability to support evolutionary algorithm design, helping guide model selection for real-world engineering use.

Shaohua Yu, Tianyu Chen, Linyan Liu +1

School of Intelligent Science and Technology, Nanjing University of Science and Technology, Nanjing 210094, China · School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China · Université Paris-Saclay, CentraleSupélec, Laboratoire Génie Industriel, 91190, Gif-sur-Yvette, France +1

Automated Heuristic Design Large Neighborhood Search Large Language Model-Guided Optimization Evolutionary Optimization

Mar 6, 2026

LUMINA: LLM-Guided GPU Architecture Exploration via Bottleneck Analysis

GPU design space exploration (DSE) for modern AI workloads, such as Large-Language Model (LLM) inference, is challenging because of GPUs' vast, multi-modal design spaces, high simulation costs, and complex design optimization objectives (e.g. performance, power and area trade-offs). Existing automated DSE methods are often prohibitively expensive, either requiring an excessive number of exploration samples or depending on intricate, manually crafted analyses of interdependent critical paths guided by human heuristics. We present LUMINA, an LLM-driven GPU architecture exploration framework that leverage AI to enhance the DSE efficiency and efficacy for GPUs. LUMINA extracts architectural knowledge from simulator code and performs sensitivity studies to automatically compose DSE rules,which are auto-corrected during exploration. A core component of LUMINA is a DSE Benchmark that comprehensively evaluates and enhances LLMs' capabilities across three fundamental skills required for architecture optimization, which provides a principled and reproducible basis for model selection and ensuring consistent architectural reasoning. In the design space with 4.7 million possible samples, LUMINA identifies 6 designs of better performance and area than an A100 GPU efficiently, using only 20 steps via LLM-assisted bottleneck analysis. In comparison, LUMINA achieves 17.5x higher than design space exploration efficiency, and 32.9% better designs (i.e. Pareto Hypervolume) than Machine-Learning baselines, showcasing its ability to deliver high-quality design guidance with minimal search cost.

Tao Zhang, Rui Ma, Shuotao Xu +2

Microsoft Research China

Automated Heuristic Design Large Language Model-Guided Optimization

Mar 6, 2026

Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning

Large language models (LLMs) benefit substantially from supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) in reasoning tasks. However, these recipes perform poorly in instruction-based molecular optimization, where each data point typically provides only a single optimized reference molecule and no step-by-step optimization trajectory. We reveal that answer-only SFT on the reference molecules collapses reasoning, and RLVR provides sparse feedback under similarity constraints due to the model's lack of effective exploration, which slows learning and limits optimization. To encourage the exploration of new molecules while balancing the exploitation of the reference molecules, we introduce Reference-guided Policy Optimization (RePO), an optimization approach that learns from reference molecules without requiring trajectory data. At each update, RePO samples candidate molecules with their intermediate reasoning trajectories from the model and trains the model using verifiable rewards that measure property satisfaction under similarity constraints in an RL manner. Meanwhile, it applies reference guidance by keeping the policy's intermediate reasoning trajectory as context and training only the answer in a supervised manner. Together, the RL term promotes exploration, while the guidance term mitigates reward sparsity and stabilizes training by grounding outputs to references when many valid molecular edits exist. Across molecular optimization benchmarks, RePO consistently outperforms SFT and RLVR baselines (e.g., GRPO), achieving improvements on the optimization metric (Success Rate

\times

Similarity), improving balance across competing objectives, and generalizing better to unseen instruction styles. Our code is publicly available at https://github.com/tmlr-group/RePO.

Xuan Li, Zhanke Zhou, Zongze Li +4

Hong Kong Baptist University · CMIC, Shanghai Jiao Tong University · DAMO Academy, Alibaba Group +1

Molecular Optimization Large Language Model-Guided Optimization Policy Optimization RL for Language Models Reinforcement Learning with Verifiable Rewards

Mar 5, 2026

Escaping the Hydrolysis Trap: An Agentic Workflow for Inverse Design of Durable Photocatalytic Covalent Organic Frameworks

Covalent organic frameworks (COFs) are promising photocatalysts for solar hydrogen production, yet the most electronically favorable linkages, imines, hydrolyze rapidly in water, creating a stability--activity trade-off that limits practical deployment. Navigating the combinatorial design space of nodes, linkers, linkages, and functional groups to identify candidates that are simultaneously active and durable remains a formidable challenge. Here we introduce Ara, a large-language-model (LLM) agent that leverages pretrained chemical knowledge, donor--acceptor theory, conjugation effects, and linkage stability hierarchies, to guide the search for photocatalytic COFs satisfying joint band-gap, band-edge, and hydrolytic-stability criteria. Evaluated against random search and Bayesian optimization (BO) over a space consisting of candidates with various nodes, linkers, linkages, and r-groups, screened with a GFN1-xTB fragment pipeline, Ara achieves a 52.7% hit rate (11.5

\times

random, p = 0.006), finds its first hit at iteration 12 versus 25 for random search, and significantly outperforms BO (p = 0.006). Inspection of the agent's reasoning traces reveals interpretable chemical logic: early convergence on vinylene and beta-ketoenamine linkages for stability, node selection informed by electron-withdrawing character, and systematic R-group optimization to center the band gap at 2.0 eV. Exhaustive evaluation of the full search space uncovers a complementary exploitation--exploration trade-off between the agent and BO, suggesting that hybrid strategies may combine the strengths of both approaches. These results demonstrate that LLM chemical priors can substantially accelerate multi-criteria materials discovery.

Iman Peivaste, Nicolas D. Boscher, Ahmed Makradi +1

Luxembourg Institute of Science and Technology (LIST), 5, Avenue des Hauts-Fourneaux, Esch-sur-Alzette, 4362, Luxembourg · Department of Physics and Materials Science, University of Luxembourg, L-4365 Esch-sur-Alzette, Luxembourg

Materials Science Inverse Design Large Language Model-Guided Scientific Discovery Large Language Model-Guided Optimization

Mar 5, 2026

ReVEL: Multi-Turn Reflective LLM-Guided Heuristic Evolution via Structured Performance Feedback

Designing effective heuristics for NP-hard combinatorial optimization problems remains challenging and often requires substantial domain expertise. Recent LLM-guided evolutionary methods have shown promise for automated heuristic generation, but most existing approaches refine heuristics independently or through limited pairwise feedback. We propose ReVEL: Multi-Turn Reflective LLM-Guided Heuristic Evolution via Structured Performance Feedback, a framework for group-wise multi-turn heuristic refinement. ReVEL organizes heuristics into behavior-aware reflective groups, including similarity-driven groups for localized refinement and diversity-driven groups for exploratory search. Within each group, the LLM performs iterative multi-turn refinement using accumulated performance feedback, enabling related heuristics to be jointly analyzed and progressively improved across evolutionary iterations. Experiments on standard combinatorial optimization benchmarks show that ReVEL generally improves optimization performance over existing LLM-guided evolutionary baselines across multiple settings and LLM backbones. Additional analyses suggest that behavior-aware grouping contributes to more consistent refinement trajectories during iterative heuristic evolution.

Cuong Van Duc, Minh Nguyen Dinh Tuan, Tam Vu Duc +4

VinMotion · Hanoi University of Science and Technology · VinUniversity +2

Automated Heuristic Design Large Language Model-Guided Optimization Evolutionary Optimization Combinatorial Optimization LLM Self-Refinement

Mar 3, 2026

Type-Aware Retrieval-Augmented Generation with Dependency Closure for Solver-Executable Industrial Optimization Modeling

Automated industrial optimization modeling requires reliable translation of natural-language requirements into solver-executable code. However, large language models often generate non-compilable models due to missing declarations, type inconsistencies, and incomplete dependency contexts. We propose a type-aware retrieval-augmented generation (RAG) method that enforces modeling entity types and minimal dependency closure to ensure executability. Unlike existing RAG approaches that index unstructured text, our method constructs a domain-specific typed knowledge base by parsing heterogeneous sources, such as academic papers and solver code, into typed units and encoding their mathematical dependencies in a knowledge graph. Given a natural-language instruction, it performs hybrid retrieval and computes a minimal dependency-closed context, the smallest set of typed symbols required for solver-executable code, via dependency propagation over the graph. We validate the method on two constraint-intensive industrial cases: demand response optimization in battery production and flexible job shop scheduling. In the first case, our method generates an executable model incorporating demand-response incentives and load-reduction constraints, achieving peak shaving while preserving profitability; conventional RAG baselines fail. In the second case, it consistently produces compilable models that reach known optimal solutions, demonstrating robust cross-domain generalization; baselines fail entirely. Ablation studies confirm that enforcing type-aware dependency closure is essential for avoiding structural hallucinations and ensuring executability, addressing a critical barrier to deploying large language models in complex engineering optimization tasks.

Y. Zhong, R. Huang, M. Wang +4

School of Petroleum, China University of Petroleum (Beijing) at Karamay, Karamay, 834000, China

Natural Language to Optimization Modeling Retrieval-Augmented Generation Large Language Model-Guided Optimization