CAMEL: Communicative Agents for "Mind" Exploration of Large Scale Language Model Society

By Guohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin, Bernard Ghanem. arXiv.org, 2023

390 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/7ca954844bc1dd405bc43445b1c990e42d865095

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Enhancing Chat Language Models by Scaling High-quality Instructional Conversations (2023, background): “For instance, CAMEL (Li et al., 2023) designed a multi-agent role-play environment for LLMs to solve a given complex task and produced 115k instruction-response pairs that simulate real human conversations.”
ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate (2023, background): “While a single powerful LLM can already tackle various missions, emerging studies suggest that multiple LLMs can further improve one another through debate and cooperation (Li et al., 2023a; Liang et al., 2023).”
AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents (2023, positive): “Parallel findings from recent research suggest that designating specific roles for autonomous agents, similar to recruiting experts to form a team, can augment their efficacy (Li et al., 2023; Salewski et al., 2023; Qian et al., 2023a).”
Instruction Tuning for Large Language Models: A Survey (2023, neutral): “HumanEval [18] consists of 164 programming problems, including language comprehension, algorithms, and simple mathematics, with some comparable to simple software interview questions.”
Large Language Model based Multi-Agents: A Survey of Progress and Challenges (2024, methodology): “Hence, LLM-based agent has been studied and rapidly developed to understand and generate human-like instructions, facilitating sophisticated interactions and decision-making in a wide range of contexts [Yao et al. , 2023; Shinn et al. , 2023; Li et al. , 2023d].”
Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration (2023, methodology): “In Section 4, we further design and compare with two variants of Solo Performance Prompting: one adopting fixed personas, as in Camel (Li et al., 2023), and another with additional persona profiles, as proposed in ExpertPrompting (Xu et al., 2023). drafts of the story, solicits feedback from other p”
LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset (2023, methodology): “Besides these natural conversations, there are synthetic datasets fully generated by LLMs, such as UltraChat (Ding et al., 2023), Baize (Xu et al., 2023b), Camel (Li et al., 2023), Alpaca (Taori et al., 2023), and SODA (Kim et al., 2022).”
MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning (2023, background): “Camel (Li et al., 2023b) leveraged role-playing to enable chat agents to communicate with each other for task completion.”
Self-Collaboration Code Generation via ChatGPT (2023, positive): “CAMEL [28] explores the possibility of interaction between two LLMs.”
ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs (2023, neutral): “…2023), use of scratchpads (Nye et al., 2021), training veri-fiers (Cobbe et al., 2021), self-collaboration (Wang et al., 2023c; Schick et al., 2022; Li et al., 2023a; Feng et al., 2024), self-reflection (Shinn et al., 2023; Madaan et al., 2023; Wang and Zhao, 2023; Yao et al., 2023b), improved…”
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation (2023, positive): “Due to these limitations, even the multi-agent systems in LangChain (e.g., re-implementation of CAMEL) are not based on LangChain Agents but are implemented from scratch.”
Aligning Large Language Models with Human: A Survey (2023, methodology): “, 2023c), CAMEL (Li et al., 2023a), SelFee (Ye et al.”
GAIA: a benchmark for General AI Assistants (2023, methodology): “…(Osika, 2023), AutoGPT (Yang et al., 2023); (ii) using multiple agent LLMs to debate and together reach better conclusions to answer user queries (Li et al., 2023a; Hong et al., 2023; Chan et al., 2023; Talebirad and Nadiri, 2023); (iii) using single agent LLMs augmented with specific tools,…”
MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning (2023, neutral): “Type Annotation # Samples Characteristics Fields GSM8K (Cobbe et al., 2021) CoT Human 7K Grade Schol Exam ∎ GSM8K-RFT (Yuan et al., 2023) CoT Llama 28K Llama + Validated ∎ AQuA-RAT (Ling et al., 2017) CoT Human 90K GRE/GMAT Exam ∎ MATH (Hendrycks et al., 2021b) CoT Human 7K Math Competition ∎ ∎ ∎ ∎ ”
MetaGPT: Meta Programming for Multi-Agent Collaborative Framework (2023, background): “Li et al. [2] proposed a simple role-play agent framework that realizes automatic programming based on one-sentence user requirements through the interaction of two roles.”