Camel: Communicative agents for" mind" exploration of large language model society
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
The rapid advancement of chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents, and provides insight into their "cognitive" processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing. Our approach involves using inception prompting to guide chat agents toward task completion while maintaining consistency with human intentions. We showcase how role-playing can be used to generate conversational data for studying the behaviors and capabilities of a society of agents, providing a valuable resource for investigating conversational language models. In particular, we conduct comprehensive studies on instruction-following cooperation in multi-agent settings. Our contributions include introducing a novel communicative agent framework, offering a scalable approach for studying the cooperative behaviors and capabilities of multi-agent systems, and open-sourcing our library to support research on communicative agents and beyond: https://github.com/camel-ai/camel.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The development of medical AI agents can be approached through two primary methodologies: graphical user interface (GUI)-based frameworks and coding-based development.110,111,112”
From A foundational architecture for AI agents in healthcare (2025) · cites this paper as [111]
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Cited by
Items 301–369 of 369
Xiang, Y. (2026) · International Conference on Large Models and Intelligent Agent Technologies (LMIAT) · doi:10.1109/lmiat70705.2026.11682229 · Cited by 2
“Decentralized and market-based allocation revives the classical contract-net protocol [25], letting agents bid for tasks; CAMEL’s role-playing dialogue [9] and AgentVerse’s dynamic recruitment [10] sit here, scaling better but weakening any global invariant.”
MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming
Zhao, Z., Sun, J., Hóu, Z., Wei, Z., Cai, C., Qiao, M., & Dong, J. S. (2026) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3744916.3773221 · Cited by 10
“These strategies demonstrate that beyond model training, structured interactions and external tool integration significantly enhance the adaptability of LLMs in complex programming tasks.”
Xu, C., Zhang, X., & Gong, X. (2026) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3744916.3773243
Park, J., Lim, Y., Kim, G., Yun, T., & Min, M. (2026) · ETRI Journal · doi:10.4218/etrij.2026-0186 · Cited by 2
Tao, C. (2026) · International Conference on Digital Society and Artificial Intelligence (DSAI) · doi:10.1145/3833541.3833787
“For example, some studies have constructed multi-agent systems consisting of physicians, nurses, and medical experts to simulate clinical diagnosis and treatment processes [13].”
Liu, Z. (2026) · International Conference on Digital Society and Artificial Intelligence (DSAI) · doi:10.1145/3833541.3833805
Zhang, C. (2026) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia71496.2026.11684535
“Recent studies such as AgentBench, CAMEL, and ChatEval further show that interaction, role assignment, and multi-agent discussion are important components of LLM-based agent evaluation and collaboration [3],[5],[8] .”
Graph-based Multi-Agent LLM Framework for OCR-based Visual Question Answering
Dang, T. L.-T., Nguyen, H. M., & Nguyen, K. V. (2026) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr72750.2026.11685818
“Multi-agent frameworks aggregate diverse reasoning paths [1], [22], and orchestration frameworks such as ReAct [23] and AutoGen [24] have made agent topologies programmable; debate, self-consistency and voting [25] further stabilize outputs.”
Adaptive Solving with Episodic Memory and Serial Multi-Agent Reasoning
Fan, W., Zhou, M., He, J., Chen, F., He, S., Li, S., & Zeng, W. (2026) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia71496.2026.11684607
“In multi-agent collaborative reasoning, CAMEL explores emergent behavior in societies of LLM agents through role playing and verifies the effectiveness of multi-agent dialogue in task completion [19].”
A Workflow-based Intelligent Strategy Assessment Method
Duan, W., Wang, Y., & Li, J. (2026) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia71496.2026.11684602
“…agent topologies and human-in-the-loop interactions [2]; CAMEL demonstrated that communicative agents can autonomously cooperate through role-playing scenarios [3]; and HAWK extended this trend with hierarchical workflow architectures organizing agents into layered decision-making structures [4].”
Vicente-Martínez, P., Casas-Íñigo, T., Soria‐Olivas, E., García-Escrivà, M. Á., William, E., & Sánchez-Montañés, M. A. (2026) · Sustainability · doi:10.3390/su18189505
Research on Local State Assessment Method Based on Complex-Task Time-Series Data
Wang, C., Zhai, W., Liao, Z., Liu, Y., Xie, Y., Wang, X., & Tang, J. (2026) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia71496.2026.11684657
“Multi-agent scheduling is instantiated with instruction-following LLMs accessed through model APIs, while the role separation and conversation protocol follow common LLM multi-agent collaboration patterns [14]–[17].”
A Controller-Mediated Multi-agent LLM Framework for Real-Time Digital Banking Workflow Execution
Arafat, M. E., Saha, S., Refat, S. R., & Orosz, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36871-3_30
Commit Before Trust: Transactional Shared Memory for Multi-Agent LLMs
Kim, C., Ojha, M., Konnur, S., Kolachana, S., & Hu, L. (2026) · International Conference on Artificial Intelligence, Internet of Things and Cloud Computing Technology (AIoTC) · doi:10.1109/aiotc71250.2026.11689396
“In full-history sharing [4], [9], each down-stream agent receives the complete trace of previous agent messages, including reasoning steps, intermediate outputs, and reviewer feedback.”
Enhanced Cooperative Multi-agent System for Named Entity Recognition in Dravidian Languages
Reddy, G. V. A. V., Rao, P. O., & Premjith, B. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-30957-0_31
Chang, X., Tao, S., Kawai, M., & Takizawa, H. (2026) · International Conference on Computational Intelligence and Machine Learning (CIML) · doi:10.1109/ciml69155.2026.11692797
Qavi, A., & Ghafarian, T. (2026) · Electronics · doi:10.3390/electronics15194379
KG-MAFMEA: A Knowledge Graph-Driven Multi-Agent Framework for Failure Mode and Effects Analysis
Wang, S., Yang, Y., Gan, W., & Hu, H. (2026) · International Conference on System Reliability and Safety Engineering (SRSE) · doi:10.1109/srse70977.2026.11694991
“Multi-agent systems can improve such workflows through role specialization, structured communication, and iterative feedback [16][17].”
Singthong, U., Cholamjiak, W., & Farid, M. (2026) · Mathematics · doi:10.3390/math14193463
Rustamov, Z., Pashayev, M. A., Jafarov, S., Aslanli, U., Mammadov, A., Valizada, A., & Rustamov, S. (2026) · Journal of Advances in Information Technology · doi:10.12720/jait.17.9.1716-1723
“More recently, multi-agent conversational frameworks have been proposed to coordinate multiple role-specialized agents through structured interaction protocols [8, 15, 16].”
Configuring and Diagnosing Conversational Agents for Process Mining Tasks
Berti, A., Kourani, H., & van der Aalst, W. M. P. (2026) · Lecture notes in business information processing · doi:10.1007/978-3-032-36710-5_11
Language Models in Video Anomaly Detection: A Dynamic Survey
Mumcu, F., Bekit, L., Jones, M., Cherian, A., & Yılmaz, Y. (2026) · IEEE Access · doi:10.1109/access.2026.3737989
An Interpretable Framework for Agentic Design in Combinatorial Optimization
Li, M., Yan, Y., & Jin, Y. (2026) · International Conference on Data-driven Optimization of Complex Systems (DOCS) · doi:10.1109/docs70981.2026.11698643
“General LLM-based multi-agent systems such as CAMEL [5] and AutoGen [6] show that multiple role-specialized AI agents can support task decomposition, interaction, and intermediate trace generation.”
Multi Agent LLMs for Diversified Large Scale Spatial Consistent 3D Scene Data Synthesis
Venkatesh, S. B., Muraleedharan, L. P., Hegde, A. N., & Su, G.-M. (2026) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr70517.2026.00089
“Multi-agent LLM frameworks such as CAMEL [9] and Auto-Gen [10] have shown that decomposing complex tasks across specialized agents yields deeper reasoning than a monolithic model, though they typically operate with a fixed roster of roles.”
ARCIS: Autonomous Reasoning and Contextual Intelligence System
Vinayak, M., V, Namboothiri, R. S., A, V. V., Varghese, J., & Jophin, S. (2026) · International Conference on Innovations in Engineering and Technology (ICIET) · doi:10.1109/iciet70550.2026.11712865
“MetaGPT [7] and CAMEL [9] lack human oversight mechanisms, while ARCIS integrates strategic interrupts that preserve user control without sacrificing autonomy.”
A Structural Survey of Coordination Patterns in LLM-Based Multi-agent Systems
Esposito, N., Aniello, G., Gambino, G., Panariello, C., Alfano, D., & Abbruzzese, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-40774-0_21
CEMAS - a Configurable Embodied Multi-Agent System
Obremski, D., Polifke, L., Latoschik, M. E., & Wienrich, C. (2026) · Companion Publication of the International Conference on Multimodal Interaction (ICMI Companion) · doi:10.1145/3776591.3832498
LLMA-UML: Extending the UML for Modeling LLM-Agent Systems
Walter, L., Rother, K. M., & Henkler, S. (2026) · ACM/IEEE International Conference on Model Driven Engineering Languages and Systems (MODELS) · doi:10.1145/3837062.3838894
Specializing Large-Language Models for Collaboration Workflow Generation in Software Engineering
ELMOUHI, Y. (2026) · ACM/IEEE International Conference on Model Driven Engineering Languages and Systems (MODELS) · doi:10.1145/3837062.3839552
“The first coordinates agents without generating an explicit collaboration workflow artifact [2, 13].”
A critical assessment of the rise of agentic AI, its capabilities, task domains and open challenges
Khan, R. U., Aljuaid, H., & Ning, Z. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02342-5 · Cited by 3
Arena: A Cognitive Multi-agent Framework for Modeling Conflict-Driven Multi-party Conversation
Sun, X., Zuo, L., Zeng, Z., Ngo, T. H., Liu, K., Lechervy, A., Jurie, F., Hatin, J., & Bertin, E. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37682-4_17
CM-USR: Critical-Missing Calibrated User-State Regeneration for Lost-in-Conversation
Xu, Y., & Li, X. (2026) · International Conference on Computer Science and Blockchain (CCSB) · doi:10.1109/ccsb71176.2026.11716468
“CAMEL uses role-playing communication to study cooperation among communicative agents [9].”
Towards AI-Assisted Hardware Engineering: An Overview of LLM-Driven RTL Design Frameworks
Ahir, S., Doboli, A., & Doboli, S. (2026) · IEEE Conference on Information Technology and Data Science (CITDS) · doi:10.1109/citds70571.2026.11706876
“More recent agentic architectures decompose RTL generation into planning, retrieval, synthesis, verification, and repair through coordinated multi-stage workflows [10]–[12], [15].”
InfluentialWhen Tuning Isn't Enough: Limits of Inference-Time Controls and Collaboration in Small Local LLMs
Kumar, P., & Krishna, A. (2026) · International Conference on Emerging Techniques in Computational Intelligence (ICETCI) · doi:10.1109/icetci71772.2026.11710788
“Frameworks such as AutoGen [7], CAMEL [8], and Tree-of-Thoughts [9] coordinate multi-step reasoning through dialog or structured exploration.”
Beyond Syntax: Action Semantics Learning for App Agents
Tang, B., Luo, D., Liu, J., Chen, J., Gong, S., Hao, J., Wang, J., & Shao, K. (2026) · doi:10.1109/cvprf71909.2026.00905
“The rapid development of Large Language Models (LLMs) 1 has led to the emergence of AI agents across a wide range of domains [1, 2, 3, 4].”
Evolutionary Multi-Agent Collaboration for Real-World Video Face Restoration
Tang, B., Wang, T., Zhang, M., Yu, X., Chen, J., Li, B., & Zhang, K. (2026) · doi:10.1109/cvprf71909.2026.00785
“The integration of VLMs into MAS enhances multimodal communication and coordination, making them particularly suitable for tasks that require iterative reasoning [18, 40].”
Postergen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation via Multi-Agent LLMs
Zhang, Z., Zhang, X., Wei, J., Xu, Y., & You, C. (2026) · doi:10.1109/cvprf71909.2026.00939 · Cited by 3
“Recent studies show that LLM-powered multi-agent frameworks can outperform single models on complex multimodal tasks [2, 14, 18, 21, 22, 26, 30, 42, 43, 50, 52, 54, 57–59, 61, 62, 66] by letting agents take on specialized roles and coordinate through mechanisms like self-reflection [1, 51].”
Lam, P.-D., Gu, B.-H., Jo, Y., Ji-Young, O., Soo-Yol, O., & Lee, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-41864-7_25
Hidden Profile Decision Making in Multi-Agent LLM Groups
Toxtli, C., & Delaflor, M. (2026) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/3785651.3831525 · Cited by 2
Chi, Y., Liu, M., Hong, Y., Li, H., & Liang, X. (2026) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/3785651.3831571
GCAL: Group-centered collaborative advantage learning for policy optimization in multi-agent systems
Hu, Y.-W., Shi, S., Tian, Z., & Yuan, R.-D. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.117155
The Decomposition Dilemma: When Do Multi-Agent LLM Workflows Help Grounded Knowledge Generation?
Hossain, A. I., Chowdhury, M. Z., Nur, S., & Alhoori, H. (2026) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1145/3805696.3846484
“Systems such as AutoGen, CAMEL, MetaGPT, and ChatDev demonstrate that LLMs can be coordinated through specialized roles and intermediate communication [5, 9, 11, 14].”
Large language model multiagent systems for industrial problem discovery and prioritization
Adoul, M. A., & Ghoul, A. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02468-6
“[39] General purpose”
Sun, Y. (2026) · International Conference on Computer Science, Machine Learning and Agents (CSMLA) · doi:10.1109/csmla70906.2026.11724504
“Multi-agent systems including AutoGen, CAMEL, MetaGPT, and ChatDev coordinate role-specialized LLMs for software and collaborative problem solving [16], [17], [19], [20], and AgentBench systematizes evaluation of LLM agents [18].”
Advancing depression detection with role-playing LLMs and synthetic psychological interviews
Liu, Y., Hu, J., Chen, Y., & Zhang, Y. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-026-03337-5
iBRAHIMOĞLU, N., & Demirezen, M. U. (2026) · Automated Software Engineering · doi:10.1007/s10515-026-00695-w
A Lightweight Dispersion Metric Suite for Real-Time Convergence Monitoring in Synthetic Populations
Martín, R. Á., Soroberto, M., & Carton, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-41794-7_1
Wang, Y., Han, Y., Gao, J., Zhang, W., Wang, J., & Zhang, W. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728474
“Later frameworks such as MetaGPT [15] and ChatDev [17] modeled broader software engineering workflows, while CAMEL [16] studied role-playing and conversation control to improve co-ordination.”
MCIR-RAG: Multi-Agent Chain-of-Thought Iterative Reflection for Multi-modal Document Understanding
Liu, C., Wang, S., Li, Z., Hu, M., Fang, Q., Xiao, Y., Zhang, J., Luo, Z., Luo, W., Yi, Z., et al. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729376
He, H., & Gu, Y. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729492
GD-KS: A Spec-Driven Multi-Agent Framework for LLM-Assisted Game Development
Silvestrini, M. M., & Pereira, L. T. (2026) · Simpósio Brasileiro de Jogos e Entretenimento Digital (SBGames) · doi:10.5753/sbgames.2026.26161
“CAMEL [Li et al. 2023] pioneered role-playing between agents with task specification and critique mechanisms, demonstrating emergent cooperation but without embedding a structured development pipeline.”
Enhancing Multi-Agent LLM Output Quality Through Adversarial Critique: a Cross-Domain Evaluation
Kalra, U., & Gupta, R. K. (2026) · International Conference on Networks, Computers and Communications (ICNCCom) · doi:10.1109/icnccom69117.2026.11736314
“Similar collaborative approaches have been explored through agent-based systems such as CAMEL [4] and AgentVerse [10].”
Coherent Generative Agentic AI Enabled 6G/7G Networking
Galis, A. (2026) · Future Internet · doi:10.3390/fi18100576
Sun, Z., Chen, S., & Bie, M. (2026) · Applied Sciences · doi:10.3390/app162010433
Huang, Y., Li, C., & Fang, C. (2026) · Annual Symposium on Computer-Human Interaction in Play · doi:10.1145/3800965.3834285
“CAMEL [13], MetaGPT [9], and AutoGen [24] support role-based communication and orchestration, but do not prescribe game-specific contracts, schema-validated world mutation, or event-sourced replay.”
Can Dialogue and Role Improve LLM Sidewalk Image Descriptions Across Mobility Groups?
Miyata, A., Go, K., Matsubayashi, R., & Ichikawa, Y. (2026) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3797867.3829022
Zhao, Z., Chen, S., Gao, Z., Yang, L., Zhang, T., Zhang, J., & Li, T. (2026) · International Conference on Embodied Intelligence and Large Models · doi:10.1145/3845562.3845582
“Multi-agentdesignsim-provetaskdecomposition[8],yetwithoutexplicitbusiness-rule verificationtheymaystillgeneratefluentbutnon-compliantre-sponses.”
Protocol-dependent conformity in open-weight large language models under fixed wrong-peer signals
Xu, L., Xue, X., Zhu, Y., Zhang, J., & Xu, D. (2026) · AI Agent · doi:10.20517/aiagent.2026.19
A2A—A Mechanism Driven Framework for Interaction Based Agent Evaluation
Zhang, H., Zhang, R., Li, Y., Zhao, K., Song, Y., Song, Z., & Liu, G. (2026) · International Conference on Artificial Intelligence and Computing Power · doi:10.1145/3843915.3843923
“This formulation is closely related to multi-agent interaction frameworks such as CAMEL [6] and AutoGen [10], where agents interact through structured communication and role assignment.”
Multi-Agent Prompting with In-Context Feedback for Cross-Modal Urban Event Chain Prediction
Gupta, B., Sah, S., Dina, A. S., & Jaimes, L. G. (2026) · International Electronic Conference on Sensors and Applications (ECSA) · doi:10.3390/engproc2026163005
Wang, Y., Wang, Y., & Zhang, L. (2026) · AI Agent · doi:10.20517/aiagent.2026.43
From observation to generation: A complex-systems perspective on generative Human–AI social systems
Ma, Y., Peng, M., Hu, S., Zhu, B., Wang, Y., Chen, Y., Liu, S., & Cheong, K. H. (2026) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2026.119312
More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration
Yadav, A., Black, S., & Sourbut, O. (2026) · arXiv · doi:10.48550/arxiv.2604.07821
“Large language models (LLMs) are increasingly deployed as agents that plan, communicate, and coordinate with others (Park et al., 2023; Wu et al., 2023; Li et al., 2023).”
Zhang, Y., Liu, F., Shan, Y., Huang, X., Yang, X., Zhu, Y., Cheng, X., Liu, C., Zeng, K., Zhang, T. J., et al. (2026) · arXiv · doi:10.48550/arxiv.2603.01045
“Foundational works like CAMEL (Li et al., 2023) and MetaGPT (Hong et al., 2023) utilize role-specialized agents (e.g., assigning “Manager” or “Coder” personas) embedded within fixed hierarchical or waterfall workflows.”
At Equal Inference Cost, Multi-Agent Structure Does Not Beat a Single Frozen Agent
Dylan, D., Brennan, A., Murphy, C., O'Sullivan, N., Kelly, C., & Walsh, S. (2026) · arXiv · doi:10.48550/arxiv.2609.04217 · Cited by 3
“…agents distinct personas and structured workflows: AutoGen frames applications as multi-agent conversations [1]; CAMEL pairs role-playing agents [10]; MetaGPT and ChatDev encode software-team standard operating procedures [2], [11]; AgentVerse studies emergent collaboration [12]; Solo…”
MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
Ye, R., Tang, S., Ge, R., Du, Y., Yin, Z., Chen, S., & Shao, J. (2025) · arXiv · doi:10.48550/arxiv.2503.03686
“Since a single LLM may struggle to handle the diverse and complex range of tasks in practice (Li et al., 2023; Qian et al., 2024b), such limitation has driven recent research towards building LLM-based multi-agent systems (MAS) (Wang et al., 2024c; Wu et al., 2023).”
Piao, J., Yan, Y., Zhang, J., Li, N., Yan, J., Lan, X., Lu, Z., Zheng, Z., Wang, J. Y., Zhou, D., et al. (2025) · arXiv · doi:10.48550/arxiv.2502.08691 · Cited by 43
“Some have discovered that the collaboration of multiple agents can generate believable social organizing behaviors [77] and solve complex tasks [63, 24].”
Zhang, S., Yin, M., Zhang, J., Liu, J., Han, Z., Zhang, J., Li, B., Wang, C., Wang, H., Chen, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2505.00212 · Cited by 1
“We adopt the widely-adopted turn-based LLM multi-agent protocol (Hong et al., 2023; Li et al., 2023a; Wu et al., 2023).”
Metadata
- Authors
- Li, G., Hammoud, H., Itani, H., Khizbullin, D., & Ghanem, B.
- Venue
- Advances in Neural Information Processing Systems 36
- Published
- 2023
- Pages
- 51991-52008
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133220405
- Cited by
- 314
- References
- 0
- Citations by year
- 2026: 197 · 2025: 77 · 2024: 32 · 2023: 8
- FWCI
- 78.60
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- cc-by
- Locations
- neural information processing systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- King Abdullah University of Science and Technology
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › Arts and Humanities › History and Philosophy of Science › Cybernetics and Technology in Society
- Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Keywords
- large language models, multi-agent systems, agent communication, emergent behavior, collective intelligence
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.