Agent-as-Tool: A Study on the Hierarchical Decision Making with Reinforcement Learning
By: Yanfei Zhang
Potential Business Impact:
AI learns better by splitting tasks.
Large Language Models (LLMs) have emerged as one of the most significant technological advancements in artificial intelligence in recent years. Their ability to understand, generate, and reason with natural language has transformed how we interact with AI systems. With the development of LLM-based agents and reinforcement-learning-based reasoning models, the study of applying reinforcement learning in agent frameworks has become a new research focus. However, all previous studies face the challenge of deciding the tool calling process and the reasoning process simultaneously, and the chain of reasoning was solely relied on the unprocessed raw result with redundant information and symbols unrelated to the task from the tool, which impose a heavy burden on the model's capability to reason. Therefore, in our research, we proposed a hierarchical framework Agent-as-tool that detach the tool calling process and the reasoning process, which enables the model to focus on the verbally reasoning process while the tool calling process is handled by another agent. Our work had achieved comparable results with only a slight reinforcement fine-tuning on 180 samples, and had achieved exceptionally well performance in Bamboogle with 63.2% of exact match and 75.2% in cover exact match, exceeding Search-R1 by 4.8% in exact match and 3.2% in cover exact match.
Similar Papers
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
Computation and Language
Teaches AI to learn and solve problems better.
Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Use
Machine Learning (CS)
Lets computers use tools to solve hard problems.
Toward Efficient Exploration by Large Language Model Agents
Machine Learning (CS)
Lets computers learn faster by exploring better.