FunctionalAgent: Towards end-to-end on-top functional design

• URL: http://arxiv.org/abs/2605.06215v1
• Date: Thu, 07 May 2026 13:16:16 GMT
• Title: FunctionalAgent: Towards end-to-end on-top functional design
• Abstract summary: FunctionalAgent orchestrates a team of specialized sub-agents to decompose the development process into dataset construction, active-space generation, MCSCF calculation and descriptor generation, loss-function construction, and functional fitting, optimization, and evaluation.<n>We develop MC26, a hybrid meta-GGA on-top functional that achieves overall accuracy on the training set compared with other methods evaluated on the same benchmark dataset.<n>We introduce COF26, a new functional form that, owing to the optimized training process, achieves the best performance on both the training and test sets.
• Score: 7.9012744471981184
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multiconfiguration pair-density functional theory (MC-PDFT) offers an efficient and accurate framework for computing electronic energies in strongly correlated molecular systems, with the quality of the on-top functional being a key determinant of its predictive accuracy. Here we introduce FunctionalAgent, an agentic system for fully automated functional development. FunctionalAgent orchestrates a team of specialized sub-agents to decompose the development process into dataset construction, active-space generation, MCSCF calculation and descriptor generation, loss-function construction, and functional fitting, optimization, and evaluation, thereby linking all stages into a closed-loop automated workflow. Using FunctionalAgent, we developed MC26, a hybrid meta-GGA on-top functional that achieves improved overall accuracy on the training set compared with other methods evaluated on the same benchmark dataset. We further introduce COF26, a new functional form that, owing to the optimized training process, achieves the best performance on both the training and test sets.

Related papers

• From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents [90.3279207163486]
  EvoSOP is a framework that empowers agents to extract SOPs from execution trajectories and iteratively optimize the toolset.<n>We show that EvoSOP significantly boosts task success rates while substantially reducing the number of interaction rounds.
  arXiv  Detail & Related papers  (2026-07-08T12:09:49Z)
• Agentic Discovery of Exchange-Correlation Density Functionals [6.373702912974026]
  Development of accurate exchange-correlation (XC) functionals remains a longstanding challenge in density functional theory (DFT)<n>Recent advances in large language models enable a systematic, automated alternative to this human-driven design loop.<n>This report presents an agentic search system in which an LLM proposes structured functional-form changes guided by evolutionary history.
  arXiv  Detail & Related papers  (2026-05-06T21:36:43Z)
• VeriAgent: A Tool-Integrated Multi-Agent System with Evolving Memory for PPA-Aware RTL Code Generation [52.43796056267479]
  We propose a PPA-aware, tool-integrated multi-agent framework for high-quality verilog code generation.<n>Our framework explicitly incorporates EDA tools into a closed-loop workflow composed of a textitProgrammer Agent, a textitCorrectness Agent, and a textitPPA Agent<n>To support continuous improvement without model retraining, we introduce an textitEvolved Memory Mechanism that externalizes optimization experience into structured memory nodes.
  arXiv  Detail & Related papers  (2026-03-18T11:25:40Z)
• EigenData: A Self-Evolving Multi-Agent Platform for Function-Calling Data Synthesis, Auditing, and Repair [18.22665454212814]
  EigenData is an integrated, self-evolving platform that automates the full data lifecycle through a multi-agent architecture.<n>We apply EigenData to audit and repair the Berkeley Function-Calling Leaderboard (BFCL-V3)<n>We demonstrate that the repaired benchmark, coupled with outcome-aware metrics, produces model rankings substantially better correlated with human judgments of functional correctness.
  arXiv  Detail & Related papers  (2026-03-05T04:58:38Z)
• Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling [11.13437934037871]
  We introduce Team-of-Thoughts, a novel Multi-Agent System (MAS) that leverages the complementary capabilities of heterogeneous agents via an orchestrator-tool paradigm.<n>Our framework introduces two key mechanisms to optimize performance: (1) an orchestrator calibration scheme that identifies models with superior coordination capabilities, and (2) a self-assessment protocol.<n>Experiments on five reasoning and code generation benchmarks show that Team-of-Thoughts delivers consistently superior task performance.
  arXiv  Detail & Related papers  (2026-02-18T14:19:01Z)
• An Agentic Framework for Autonomous Materials Computation [70.24472585135929]
  Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery.<n>Recent advances integrate LLMs into agentic frameworks, enabling retrieval, reasoning, and tool use for complex scientific experiments.<n>Here, we present a domain-specialized agent designed for reliable automation of first-principles materials computations.
  arXiv  Detail & Related papers  (2025-12-22T15:03:57Z)
• Function-on-Function Bayesian Optimization [5.200476666831395]
  We propose a novel function-on-function Bayesian optimization (FFBO) framework to address the objective where both inputs and outputs are functions.<n>Experiments on synthetic and real-world data demonstrate the superior performance of FFBO over existing approaches.
  arXiv  Detail & Related papers  (2025-11-16T21:24:57Z)
• Agentic Predictor: Performance Prediction for Agentic Workflows via Multi-View Encoding [56.565200973244146]
  Agentic Predictor is a lightweight predictor for efficient agentic workflow evaluation.<n>By learning to approximate task success rates, Agentic Predictor enables fast and accurate selection of optimal agentic workflow configurations.
  arXiv  Detail & Related papers  (2025-05-26T09:46:50Z)
• On the practical applicability of modern DFT functionals for chemical computations. Case study of DM21 applicability for geometry optimization [55.88862563823878]
  This study focuses on evaluating the efficiency of DM21 functional in predicting molecular geometries.<n>We implement geometry optimization in PySCF for the DM21 functional in geometry optimization problem.<n>Our findings reveal both the potential and the current challenges of using neural network functionals for geometry optimization in DFT.
  arXiv  Detail & Related papers  (2025-01-21T14:01:06Z)
• ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems [80.69865295743149]
  This work attempts to study using LLM-based agents to design collaborative AI systems autonomously.<n>Based on ComfyBench, we develop ComfyAgent, a framework that empowers agents to autonomously design collaborative AI systems by generating.<n>While ComfyAgent achieves a comparable resolve rate to o1-preview and significantly surpasses other agents on ComfyBench, ComfyAgent has resolved only 15% of creative tasks.
  arXiv  Detail & Related papers  (2024-09-02T17:44:10Z)
• Towards Learning Universal Hyperparameter Optimizers with Transformers [57.35920571605559]
  We introduce the OptFormer, the first text-based Transformer HPO framework that provides a universal end-to-end interface for jointly learning policy and function prediction. Our experiments demonstrate that the OptFormer can imitate at least 7 different HPO algorithms, which can be further improved via its function uncertainty estimates.
  arXiv  Detail & Related papers  (2022-05-26T12:51:32Z)
• Hierarchical Collaborative Hyper-parameter Tuning [0.0]
  Hyper- parameter tuning is among the most critical stages in building machine learning solutions. This paper demonstrates how multi-agent systems can be utilized to develop a distributed technique for determining near-optimal values.
  arXiv  Detail & Related papers  (2022-05-11T05:16:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.