Large Language Models

How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?
We study how LLMs handle irrelevant information and find they struggle with content that is semantically related but ultimately not pertinent, highlighting the limitations of current systems in filtering out such distractions.
Siye Wu, Jian Xie, Jiangjie Chen, Tinghui Zhu, Kai Zhang, Yanghua Xiao
PDF Cite Code
How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?
DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence?
We introduce DetectBench, a benchmark for testing LLMs’ evidence detection in long contexts, and demonstrates that while existing LLMs lag behind human performance, the proposed Detective Reasoning Prompt and Finetuning methods can significantly improve their evidence detection and reasoning capabilities.
Zhouhong Gu, Lin Zhang, Xiaoxuan Zhu, Jiangjie Chen, Wenhao Huang, Yikai Zhang, Shusen Wang, Zheyu Ye, Yan Gao, Hongwei Feng, Yanghua Xiao
PDF Cite Code
DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence?
EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms
We introduce EvoAgent, a method using evolutionary algorithms to automatically expand expert agents into multi-agent systems, enhancing the task-solving capabilities of large language model-based agents without additional human design.
Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Dongsheng Li, Deqing Yang
PDF Cite Code
EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms
SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals
We introduce SelfGoal, an automatic approach that enhances language agents’ capabilities to achieve high-level goals with limited instructions and delayed feedback by adaptively breaking down goals into practical subgoals.
Ruihan Yang, Jiangjie Chen, Yikai Zhang, Siyu Yuan, Aili Chen, Kyle Richardson, Yanghua Xiao, Deqing Yang
PDF Cite Code
SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals
From Persona to Personalization: A Survey on Role-Playing Language Agents
This paper surveys Role-Playing Language Agents (RPLAs) by categorizing personas, discussing their development, and examining their applications, challenges, and future directions.
Jiangjie Chen, Xintao Wang, Rui Xu, Siyu Yuan, Yikai Zhang, Wei Shi, Jian Xie, Shuang Li, Ruihan Yang, Tinghui Zhu, Aili Chen, Nianqi Li, Lida Chen, Caiyu Hu, Siye Wu, Scott Ren, Ziquan Fu, Yanghua Xiao
PDF Cite
From Persona to Personalization: A Survey on Role-Playing Language Agents
Character is Destiny: Can Large Language Models Simulate Persona-Driven Decisions in Role-Playing?
We evaluate the potential of LLMs to make decisions as literary characters, using a new dataset and improved method that enhances decision-making accuracy, with future work and resources to be shared publicly.
Rui Xu, Xintao Wang, Jiangjie Chen, Siyu Yuan, Xinfeng Yuan, Jiaqing Liang, Zulong Chen, Xiaoqing Dong, Yanghua Xiao
PDF Cite
Character is Destiny: Can Large Language Models Simulate Persona-Driven Decisions in Role-Playing?
Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works
We propose a new approach to evaluate LLMs’ understanding of fictional characters by summarizing character profiles, using a specially constructed dataset, and shows promising results for their application in role-playing agents.
Xinfeng Yuan, Siyu Yuan, Yuhan Cui, Tianhe Lin, Xintao Wang, Rui Xu, Jiangjie Chen, Deqing Yang
PDF Cite Code
Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works
SurveyAgent: A Conversational System for Personalized and Efficient Research Survey
We propose a novel conversational AI system that enhances researchers’ literature review processes by providing personalized knowledge management, literature recommendations, and query answering through a unified platform.
Xintao Wang, Jiangjie Chen, Nianqi Li, Lida Chen, Xinfeng Yuan, Wei Shi, Xuyang Ge, Rui Xu, Yanghua Xiao
PDF Cite Code Demo
SurveyAgent: A Conversational System for Personalized and Efficient Research Survey
Agent Group Chat: An Interactive Group Chat Simulacra For Better Eliciting Collective Emergent Behavior
We propose a simulation to study language’s influence on collective behavior by having agents engage in free chat within various narrative scenarios, with findings suggesting that greater information exchange promotes more orderly and meaningful emergent behaviors.
Zhouhong Gu, Xiaoxuan Zhu, Haoran Guo, Lin Zhang, Yin Cai, Hao Shen, Jiangjie Chen, Zheyu Ye, Yifei Dai, Yan Gao, Yao Hu, Hongwei Feng, Yanghua Xiao
PDF Cite Code
Agent Group Chat: An Interactive Group Chat Simulacra For Better Eliciting Collective Emergent Behavior
TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation
TimeArena enhances LLMs with temporal dynamics for better multitasking, showing advanced models like GPT-4 still trail behind human temporal awareness.
Yikai Zhang, Siyu Yuan, Caiyu Hu, Kyle Richardson, Yanghua Xiao, Jiangjie Chen
PDF Cite Project
TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation