AGILE: A Novel Reinforcement Learning Framework of LLM Agents

2024-05-23 · Peiyuan Feng, Yichen He, Guanhua Huang, Yuan Lin, Hanchong Zhang, Yuchen Zhang, Hang Li

We introduce a novel reinforcement learning framework of LLM agents named AGILE (AGent that Interacts and Learns from Environments) designed to perform complex conversational tasks with users, leveraging LLMs, memory, tools, and interactions with experts. The agent possesses capabilities beyond conversation, including reflection, tool usage, and expert consultation. We formulate the construction of such an LLM agent as a reinforcement learning (RL) problem, in which the LLM serves as the policy model. We fine-tune the LLM using labeled data of actions and the PPO algorithm. We focus on question answering and release a dataset for agents called ProductQA, comprising challenging questions in online shopping. Our extensive experiments on ProductQA, MedMCQA and HotPotQA show that AGILE agents based on 7B and 13B LLMs trained with PPO can outperform GPT-4 agents. Our ablation study highlights the indispensability of memory, tools, consultation, reflection, and reinforcement learning in achieving the agent's strong performance. Datasets and code are available at https://github.com/bytarnish/AGILE.

📄 PDF Abstract BibTeX arXiv:2405.14751

Code (1)

bytarnish/agile 공식 구현 pytorch

Tasks

Question Answering reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Position-Wise Feed-Forward Layer 설명 없음

Multi-Head Attention 설명 없음

Residual Connection 설명 없음

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Adam 설명 없음

Agile Interception of a Flying Target using Competitive Reinforcement Learning

2026-03-17 · Timothée Gavin, Simon Lacroix, Murat Bronz arxiv

This article presents a solution to intercept an agile drone by another agile drone carrying a catching net. We formulate the interception as a Competitive Reinforcement Learning problem, where the interceptor and the ta…

Reinforcement Learning

Intercepting an Agile Target with Net-Carrying Drones using Competitive Multi-Agent Reinforcement Learning

2026-07-07 · Timothée Gavin, Murat Bronz arxiv

This article presents a solution to intercept an agile drone by a team of agile drone carrying catching nets. We formulate the problem as a competitive Multi-Agent Reinforcement Learning (MARL) task. To address the probl…

Multi-agent Reinforcement Learning

AgilePE: Autonomous UAV Pursuit-Evasion via Self-Play Reinforcement Learning

2026-08-14 · Wenhao Tang, Tianyang Chen, Zhejun Cui, Boyuan An 외 arxiv

Autonomous pursuit-evasion is a fundamental challenge for Unmanned Aerial Vehicles (UAVs), requiring rapid decision-making under tightly coupled dynamics and continuously changing opponent behaviors. Traditional rule-bas…

Reinforcement Learning

AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology

2024-06-16 · Minh Huynh Nguyen, Thang Phan Chau, Phong X. Nguyen, Nghi D. Q. Bui

Software agents have emerged as promising tools for addressing complex software engineering tasks. Existing works, on the other hand, frequently oversimplify software development workflows, despite the fact that such wor…

Code Generation

Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning

2026-05-18 · Sunwoo Lee, Mingu Kang, Yonghyeon Jo, Seungyul Han arxiv

Cooperation is central to multi-agent reinforcement learning (MARL), yet learned coordination can be fragile when external perturbations disrupt inter-agent interactions. Prior robust MARL methods have primarily consider…