A Flexible Multi-Agent LLM-Human Framework for Fast Human Validated Tool Building

2025-12-01 · Daull Xavier, Patrice Bellot, Emmanuel Bruno, Vincent Martin, Elisabeth Murisasco arxiv

We introduce CollabToolBuilder, a flexible multiagent LLM framework with expert-in-the-loop (HITL) guidance that iteratively learns to create tools for a target goal, aligning with human intent and process, while minimizing time for task/domain adaptation effort and human feedback capture. The architecture generates and validates tools via four specialized agents (Coach, Coder, Critic, Capitalizer) using a reinforced dynamic prompt and systematic human feedback integration to reinforce each agent's role toward goals and constraints. This work is best viewed as a system-level integration and methodology combining multi-agent in-context learning, HITL controls, and reusable tool capitalization for complex iterative problems such as scientific document generation. We illustrate it with preliminary experiments (e.g., generating state-of-the-art research papers or patents given an abstract) and discuss its applicability to other iterative problem-solving.

📄 PDF Abstract BibTeX arXiv:2512.01434

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation

Spiking Nonlinear Opinion Dynamics (S-NOD) for Agile Decision-Making

2024-09-18 · Charlotte Cathcart, Ian Xul Belaustegui, Alessio Franci, Naomi Ehrich Leonard

We present, analyze, and illustrate a first-of-its-kind model of two-dimensional excitable (spiking) dynamics for decision-making over two options. The model, Spiking Nonlinear Opinion Dynamics (S-NOD), provides superior…

Decision Making Robot Navigation

A Versatile Agent for Fast Learning from Human Instructors

2022-03-01 · YiWen Chen, Zedong Zhang, Haofeng Liu, Jiayi Tan 외

In recent years, a myriad of superlative works on intelligent robotics policies have been done, thanks to advances in machine learning. However, inefficiency and lack of transfer ability hindered algorithms from pragmati…

Hierarchical Reinforcement Learning Imitation Learning Lifelong learning Transfer Learning

WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU

2021-08-31 · Tian Lan, Sunil Srinivasa, Huan Wang, Stephan Zheng

Deep reinforcement learning (RL) is a powerful framework to train decision-making models in complex environments. However, RL can be slow as it requires repeated interaction with a simulation of the environment. In parti…

CPU Decision Making Deep Reinforcement Learning GPU+3

Multi-Agent Reinforcement Learning for Fast-Timescale Demand Response of Residential Loads

2023-01-06 · Vincent Mai, Philippe Maisonneuve, Tianyu Zhang, Hadi Nekoei 외

To integrate high amounts of renewable energy resources, electrical power grids must be able to cope with high amplitude, fast timescale variations in power generation. Frequency regulation through demand response has th…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

Agent-Based Modular Learning for Multimodal Emotion Recognition in Human-Agent Systems

2025-12-02 · Matvey Nepomnyaschiy, Oleg Pereziabov, Anvar Tliamov, Stanislav Mikhailov 외 arxiv

Effective human-agent interaction (HAI) relies on accurate and adaptive perception of human emotional states. While multimodal deep learning models - leveraging facial expressions, speech, and textual cues - offer high a…

Multimodal Emotion Recognition Multimodal Deep Learning