Communication Dans Un Congrès Année : 2025

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

Résumé

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.

Fichier principal
Vignette du fichier
A_Flexible_Multi_Agent_LLM_Human_Framework_with_Expert_in_the_Loop_for_Fast_Human_Validated_Tool_Building-3.pdf (555.49 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05374425 , version 1 (24-11-2025)
hal-05374425 , version 2 (26-11-2025)

Licence

Identifiants

  • HAL Id : hal-05374425 , version 2

Citer

Daull Xavier, Patrice Bellot, Emmanuel Bruno, Vincent Martin, Elisabeth Murisasco. A Flexible Multi-Agent LLM-Human Framework for Fast Human Validated Tool Building. 2025 IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), Nov 2025, Londres, United Kingdom. ⟨hal-05374425v2⟩
222 Consultations
475 Téléchargements

Partager

  • More