Advancements in AI-Powered Systems and Agent-Based Modeling

The field of artificial intelligence and agent-based modeling is witnessing significant developments, with a focus on creating more efficient, adaptive, and transparent systems. Researchers are exploring the integration of machine learning and system dynamics to predict technological maturity in R&D projects, as well as the development of hybrid frameworks that combine the strengths of different approaches. The use of large language models and multi-agent systems is becoming increasingly prominent, with applications in areas such as structural engineering, data analysis, and mobile automation. Noteworthy papers in this area include: AQORA, which presents a novel adaptive query optimizer that reduces execution time by up to 90%. MASSE, which introduces a multi-agent system for structural engineering that can fully automate real-world workflows and reduce expert workload. ColorBench, which proposes a graph-structured benchmarking framework for evaluating mobile agents on complex long-horizon tasks.

Sources

A Hybrid Agent-Based and System Dynamics Framework for Modelling Project Execution and Technology Maturity in Early-Stage R&D

AQORA: A Learned Adaptive Query Optimizer for Spark SQL

Simpliflow: A Lightweight Open-Source Framework for Rapid Creation and Deployment of Generative Agentic AI Workflows

Automating Structural Engineering Workflows with Large Language Model Agents

DMAS-Forge: A Framework for Transparent Deployment of AI Applications as Distributed Systems

Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation

Aixel: A Unified, Adaptive and Extensible System for AI-powered Data Analysis

ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks

Built with on top of