Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent

Hao Peng, Tongxu Luo, Fangyu Lei, Yiming Huang, Yifan Wei, Xiaoyan Yu, Liehuang Zhu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• weiyifan1023/neeko — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large Language Models (LLMs) have revolutionized open-domain dialogue agents but encounter challenges in multi-character roleplaying (MCRP) scenarios. To address this issue, this work presents Neeko, an innovative framework designed for efficient multiplecharacter role-playing. The proposed framework breaks down the role-playing agent's training process into agent pre-tuning, multiple character playing, and character incremental learning, effectively handling both seen and unseen roles. Neeko employs a dynamic low-rank adapter (LoRA) strategy by training separate LoRA blocks independently for each character, alongside incorporating a gating network for role selection. This design allows Neeko to seamlessly adjust to a wide range of characters, thereby bolstering its adaptability to distinctive attributes, personalities, and speech patterns. As a result, Neeko demonstrates superior performance in MCRP over most existing methods, offering more engaging and versatile user interaction experiences. Code and data are available at https://github.com/ weiyifan1023/Neeko.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.13717")
get_code_for_paper("2402.13717")
have("2402.13717")

Connect an agent — have() is free.