A Flexible Multi-Agent LLM-Human Framework for Fast Human Validated Tool Building
On the map: LLM agents and tool use → Tool learning and function calling
Abstract (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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 20 of its 26 references that are in the map. First posted on arXiv 1 Dec 2025.
Builds on
20 of 26 references.
Closest ancestors · 1
Same direction, newest first
- 2023Large Language Models as Tool Makers26 May
Other references · 19
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
- 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
- 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
- 2023ChatDev: Communicative Agents for Software Developmentcited by 893
- 2023Large Language Models as Optimizerscited by 830
- 2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervisioncited by 445
- 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 405
- 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 329
- 2024RLHF Workflow: From Reward Modeling to Online RLHFcited by 265
- 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 201
- 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agentscited by 169
- 2024Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervisioncited by 95
7 more
- 2024Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMscited by 62
- 2024Human-In-the-Loop Software Development Agentscited by 42
- 2024CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solvingcited by 31
- 2024CollabStory: Multi-LLM Collaborative Story Generation and Authorship Analysiscited by 26
- 2025DocAgent: A Multi-Agent System for Automated Code Documentation Generationcited by 16
- 2023Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processescited by 15
- 2024Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Frameworkcited by 5
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Advanced Tool Learning and Selection System (ATLASS): A Closed-Loop Framework Using LLM
- 2024Learning to Use Tools via Cooperative and Interactive Agents
- 2026Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning
- 2026Multi-Agent LLM Collaboration for Unit Test Generation via Human-Testing-Inspired Workflows
- 2026Learning to Construct Practical Agentic Systems
- 2026SkillGym: Training Skill-Use Agents with Automatic Verifiable Environment Generation
- 2026AgentEscapeBench: Evaluating Out-of-Domain Tool-Grounded Reasoning in LLM Agents
- 2025Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning