Large Language Model-Guided Optimization

Follow this topic Ask about this topic

Momentum

67 papers in the last four weeks, up 219% on the four weeks before. 0.7% of all new papers.

Jul 13Week of Sep 28

Latest papers 404

All topics

CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution
May 13, 2026Tom ZehleMulti-Agent LLM Systems Multi-Agent System Optimization
University of Freiburg · ELLIS Institute Tübingen
An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing
May 13, 2026Hanwen Zhang, Dusit Niyato, Wei Zhang +2Large Language Model-Guided Optimization Edge Computing
College of Computing and Data Science, Nanyang Technological University, Singapore, 639798, Singapore · Information and Communications Technology Cluster, Singapore Institute of Technology, Singapore, 828608, Singapore
TriVAL: A Tri-Validation Framework for Faithful Automatic Optimization Modeling
May 12, 2026Ziyang Fang, JinXi Wang, Jinghui Zhong +1Large Language Model-Guided Optimization Combinatorial Optimization
School of Computer Science and Engineering, South China University of Technology, Guangzhou 510000, China · Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore 138632 · College of Computing and Data Science, Nanyang Technological University, Singapore 639798
Towards Discovery of Polymers for Insulin Delivery via Physics-Grounded Agentic Workflows
May 12, 2026Martins OtunMolecular Optimization Large Language Model-Guided Optimization
1Algonix AI Ltd., Scotland, United Kingdom
Task-Adaptive Embedding Refinement via Test-time LLM Guidance
May 12, 2026Ariel Gera, Shir Ashury-Tahan, Gal Bloch +2Zero-Shot Text Classification Large Language Model-Guided Optimization
IBM Research
Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers
May 12, 2026Haoyu Wang, Yuliang Song, Tao Li +5Large Language Model-Guided Optimization LLM-Based Program Synthesis
University of Pennsylvania · University of Toronto · Google DeepMind +1
Large Language Models as Amortized Pareto-Front Generators for Constrained Bi-Objective Convex Optimization
May 12, 2026Peipei Xu, SiYuan Ma, Yaohua Liu +4Large Language Model-Guided Optimization Constrained Optimization
University of Shanghai for Science and Technology · The Hong Kong University of Science and Technology
Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models
May 12, 2026Jinbiao Chen, Shuang Jin, Guoyun Zhang +3Memory-Augmented Language Models Large Language Model-Guided Optimization
Department of Industrial Systems Engineering and Management, National University of Singapore · Department of Data and Systems Engineering, The University of Hong Kong · Institute of Operations Research and Analytics, National University of Singapore +1
AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensive
May 12, 2026Taicheng Guo, Nitesh V. Chawla, Olaf Wiest +1Multi-Fidelity Optimization Large Language Model-Guided Optimization
University of Notre Dame
SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing
May 11, 2026Mingxu Zhang, Yuhan Li, Lujundong Li +3Molecular Optimization LLM Interpretability
The Hong Kong University of Science and Technology (Guangzhou) · Nanjing University of Aeronautics and Astronautics · The 63rd Research Institute, National University of Defense Technology, Nanjing
Budget-Efficient Automatic Algorithm Design via Code Graph
May 11, 2026Maxime Bouscary, Manxi Wu, Saurabh AminAutomated Algorithm Discovery Large Language Model-Guided Optimization
Operations Research Center Massachusetts Institute of Technology · Department of Civil and Environmental Engineering University of California, Berkeley · Laboratory for Information & Decision Systems Massachusetts Institute of Technology
LLM4Branch: Large Language Model for Discovering Efficient Branching Policies of Integer Programs
May 11, 2026Zhinan Hou, Xingchen Li, Yankai Zhang +2Branch and Bound Mixed-Integer Linear Programming
Department of Automation, BNRist, Tsinghua University, Beijing, China.
FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization
May 11, 2026Qingchuan Zhang, He Cao, Hao Li +6Molecular Optimization Large Language Model-Guided Optimization
University of Science and Technology of China · International Digital Economy Academy · Peking University +5
Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution
May 10, 2026Dongxin Guo, Jikun Wu, Siu Ming YiuEvolutionary Optimization Large Language Model-Guided Optimization
The University of Hong Kong, China · Stellaris AI Limited, China
LEVI: Stronger Search Architectures Can Substitute for Larger LLMs in Evolutionary Search
May 10, 2026Temoor TanveerEvolutionary Optimization Large Language Model-Guided Optimization
Independent Researcher
Metal-Sci: A Scientific Compute Benchmark for Evolutionary LLM Kernel Search on Apple Silicon
May 10, 2026Víctor GallegoGPU Kernel Optimization Benchmark Design
Komorebi AI Technologies, Madrid, Spain
ARES-LSHADE: Autoresearch-Enhanced LSHADE with Memetic Polish for the GNBG Benchmark
May 9, 2026Abdullah Naeem, Md Wasi Ul kabir, Manish Bhatt +3Differential Evolution Evolutionary Optimization
University of New Orleans · Amazon†
Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs
May 9, 2026Xiaozhe Li, Xinyu Fang, Shengyuan Ding +5RL Benchmarks Reinforcement Learning
Tongji University1 · Shanghai AI Lab2 · Zhejiang University3 +3
OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces
May 9, 2026Xiaozhe Li, Jixuan Chen, Xinyu Fang +4Large Language Model-Guided Optimization LLM Agent Self-Improvement
Tongji University1 · Shanghai AI Lab2 · University of California San Diego5 +2
CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs
May 8, 2026Shiyang Li, Zijian Zhang, Guangyan Sun +5LLM Evaluation GPU Kernel Optimization
University of Minnesota · Northeastern University
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
May 8, 2026Tong Zheng, Haolin Liu, Chengsong Huang +10LLM Inference Efficiency Automated Algorithm Discovery
UMD · UVA · WUSTL +3
ADKO: Agentic Decentralized Knowledge Optimization
May 8, 2026Lucas Nerone Rillo, Zhanhong Jiang, Nastaran Saadati +4Multi-Agent System Optimization AI Agents for Scientific Discovery
Iowa State University · New York University
POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles
May 8, 2026Nicolas Menet, Andreas Krause, Abbas RahimiThompson Sampling Black-Box Optimization
IBM Research – Zurich · Department of Computer Science, ETH Zürich
HMACE: Heterogeneous Multi-Agent Collaborative Evolution for Combinatorial Optimization
May 8, 2026Yuping Yan, Jirui Han, Fei Ming +2Multi-Agent LLM Systems Multi-Agent System Optimization
School of Engineering Westlake University
Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts
May 8, 2026Zixuan Huang, Da Chen, Kecheng Huang +5GPU Kernel Optimization GPU Acceleration
1The Chinese University of Hong Kong · 2Noah’s Ark Lab, Huawei
PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
May 7, 2026Minghao Yan, Bo Peng, Benjamin Coleman +11Test-Time Adaptation Reinforcement Learning
1Google · University of Wisconsin–Madison · 3Google DeepMind
Causal-Aware Foundation-Model for Bilevel Optimization in Discrete Choice Settings
May 7, 2026Shivaram Subramanian, Zhengliang Xue, Markus Ettl +2Large Language Model-Guided Optimization Discrete Choice Modeling
IBM T.J. Watson Research Center Yorktown Heights, New York, 10598, U.S.A.
A Reproducible Optimisation Protocol for Calibrating Prompt-Based Large Language Model Workflows in Evidence Synthesis
May 7, 2026Teo SusnjakLarge Language Model-Guided Optimization Language Model Calibration
School of Mathematical and Computational Sciences Massey University, Auckland, New Zealand
AgenticPrecoding: LLM-Empowered Multi-Agent System for Precoding Optimization
May 7, 2026Zijiu Yang, Zixiang Zhang, Shunpu Tang +2Multi-Agent LLM Systems Large Language Model-Guided Optimization
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China
CoupleEvo: Evolving Heuristics for Coupled Optimization Problems Using Large Language Models
May 7, 2026Thomas Bömer, Bastian Amberg, Max Disselnmeyer +1Automated Heuristic Design Evolutionary Optimization
Karlsruhe Institute of Technology Karlsruhe, Germany

May 13, 2026, cs.CLJ/K move · Enter open · S save

CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution

Tom Zehle

University of Freiburg · ELLIS Institute Tübingen

Multi-Agent LLM Systems Multi-Agent System Optimization Large Language Model-Guided Optimization LLM Agent Workflow Optimization Prompt Optimization Multi-Agent Reinforcement Learning

Open paper AskPDF arXiv

LLM-based multi-agent systems have demonstrated strong performance across complex real-world tasks, such as software engineering, predictive modeling, and retrieval-augmented generation. Yet automating their configuration remains a structural challenge, as scores are available only at the system level, whereas the parameters governing agent behavior are local. We argue that optimizing these systems is fundamentally a credit-assignment problem. We therefore introduce CANTANTE, a framework that decomposes system-level rewards into per-agent update signals by contrasting rollouts of multiple joint configurations on the same query. We instantiate it for prompt optimization, treating agent prompts as learnable system parameters. We evaluate CANTANTE against GEPA and MIPROv2 on programming (MBPP), mathematical reasoning (GSM8K), and multi-hop question answering (HotpotQA). Across these benchmarks, CANTANTE achieves the best average rank among all evaluated optimizers and consistently outperforms unoptimized prompts. It improves over the strongest baseline by +18.9 percentage points on MBPP and +12.5 percentage points on GSM8K, while incurring a lower inference cost. It remains within one standard deviation of the strongest baseline on HotpotQA. Crucially, our credit correlation analysis confirms that the attributer produces meaningful per-agent signals rather than echoing the global system score.

Momentum

Related topics

Latest papers 404