Fetching the paper…
Reading the bibliography…
Large language models have achieved remarkable capabilities across domains, yet mechanisms underlying sophisticated reasoning remain elusive.
The looking-glass self
Cooley, C. H · 1902
Earlier work this paper cites.
A set of categories for the analysis of small group interaction
Bales, R. F · 1950
Earlier work this paper cites.
Problems of Dostoevsky’s Poetics (University of Minnesota Press, 1984)
Bakhtin, M · 1984
Earlier work this paper cites.
Society of Mind (Simon & Schuster, 1987)
Minsky, M. L · 1987
Earlier work this paper cites.
The dialogical self: Beyond individualism and rationalism
Hermans, H. J., Kempen, H. J. & Van Loon, R. J · 1992
Earlier work this paper cites.
Collaborative reasoning: Evidence for collective rationality
Moshman, D. & Geil, M · 1998
Earlier work this paper cites.
Relating member ability and personality to work-team processes and team effectiveness
Barrick, M. R., Stewart, G. L., Neubert, M. J. & Mount, M. K · 1998
Earlier work this paper cites.
Devil’s advocate versus authentic dissent: stimulating quantity and quality
Nemeth, C., Brown, K. & Rogers, J · 2001
Earlier work this paper cites.
Groups of diverse problem solvers can outperform groups of high-ability problem solvers
Hong, L. & Page, S. E · 2004
Earlier work this paper cites.
Emotion in social relations: Cultural, group, and interpersonal processes (Psychology Press, London, England, 2004)
Parkinson, B., Fischer, A. H. & Manstead, A. S. R · 2004
Earlier work this paper cites.
Surprise as an interactional achievement: Reaction tokens in conversation
Wilkinson, S. & Kitzinger, C · 2006
Earlier work this paper cites.
Measuring personality in one minute or less: A 10-item short version of the big five inventory in english and german
Rammstedt, B. & John, O. P · 2007
Earlier work this paper cites.
Evidence for a collective intelligence factor in the performance of human groups
Woolley, A. W., Chabris, C. F., Pentland, A., Hashmi, N. & Malone, T. W · 2010
Earlier work this paper cites.
Optimally interacting minds
Bahrami, B. et al · 2010
Earlier work this paper cites.
The cognitive underpinnings of effective teamwork: a meta-analysis
DeChurch, L. A. & Mesmer-Magnus, J. R · 2010
Earlier work this paper cites.
Information sharing and team performance: a meta-analysis
Mesmer-Magnus, J. R. & Dechurch, L. A · 2012
Earlier work this paper cites.
Boosting wisdom: distance from the self enhances wise reasoning, attitudes, and behavior
Kross, E. & Grossmann, I · 2012
Earlier work this paper cites.
Processing power limits social group size: computational evidence for the cognitive costs of sociality
Dávid-Barrett, T. & Dunbar, R. I. M · 2013
Earlier work this paper cites.
Reading the mind in the eyes or reading between the lines? theory of mind predicts collective intelligence equally well online and face-to-face
Engel, D., Woolley, A. W., Jing, L. X., Chabris, C. F. & Malone, T. W · 2014
Earlier work this paper cites.
Arguments, more than confidence, explain the good performance of reasoning groups
Trouche, E., Sander, E. & Mercier, H · 2014
Earlier work this paper cites.
Exploring solomon’s paradox: self-distancing eliminates the self-other asymmetry in wise reasoning about close relationships in younger and older adults
Grossmann, I. & Kross, E · 2014
Earlier work this paper cites.
The social brain
Dunbar, R. I. M · 2014
Earlier work this paper cites.
Cognitive diversity in teams
Mello, A. L. & Rentsch, J. R · 2015
Earlier work this paper cites.
The Enigma of Reason (Harvard University Press, 2017)
Mercier, H. & Sperber, D · 2017
Earlier work this paper cites.
Proximal policy optimization algorithms (2017)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A. & Klimov, O · 2017
Earlier work this paper cites.
Self-distancing reduces probability-weighting biases
Sun, Q., Zhang, H., Sai, L. & Hu, F · 2018
Cited alongside, same era.
The Diversity Bonus: How Great Teams Pay Off in the Knowledge Economy (Princeton University Press, 2019)
Page, S. E · 2019
Cited alongside, same era.
Advances in Neural Information Processing Systems , Vol. 33, 1877–1901 (2020)
Brown, T. B. et al. Language models are few-shot learners · 2020
Cited alongside, same era.
Emergent abilities of large language models
Wei, J. et al · 2022
Cited alongside, same era.
Advances in Neural Information Processing Systems , Vol. 36, 11809–11822 (2023)
Yao, S. et al. Tree of thoughts: Deliberate problem solving with large language models · 2023
Cited alongside, same era.
Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (ACM, New York, NY, USA, 2023)
Proceedings of the 2nd Conference on Language Modeling (2025)
Gandhi, K., Chakravarthy, A., Singh, A., Lile, N. & Goodman, N. D. Cognitive behaviors that enable self-improving reasoners, or, four habits of highly effective STaRs · 2025
Later among the works it cites.
Differential impact from individual versus collective misinformation tagging on the diversity of twitter (x) information engagement and mobility
Kim, J., Wang, Z., Shi, H., Ling, H.-K. & Evans, J · 2025
Later among the works it cites.
Towards reasoning era: A survey of long chain-of-thought for reasoning large language models (2025)
Chen, Q. et al · 2025
Later among the works it cites.
Advances in Neural Information Processing Systems (2025)
Wang, S. et al. Beyond the 80/20 rule: High-entropy minority tokens drive effective reinforcement learning for LLM reasoning · 2025
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Park, J. S. et al. Generative agents: Interactive simulacra of human behavior · 2023
Cited alongside, same era.
SlimPajama-DC: Understanding data combinations for LLM training (2023)
Shen, Z. et al · 2023
Cited alongside, same era.
Activation addition: Steering language models without optimization (2023)
Turner, A. M. et al · 2023
Cited alongside, same era.
The Twelfth International Conference on Learning Representations , Vol. 2024 (2024)
Chan, C.-M. et al. ChatEval: Towards better LLM-based evaluators through multi-agent debate · 2024
Cited alongside, same era.
Al-Onaizan, Y., Bansal, M. & Chen, Y.-N. (eds) Encouraging divergent thinking in large language models through multi-agent debate
Liang, T. et al · 2024
Cited alongside, same era.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , 14544–14607 (Association for Computational Linguistics, Stroudsburg, PA, USA, 2024)
Zhang, J. et al. Exploring collaboration mechanisms for LLM agents: A social psychology view · 2024
Cited alongside, same era.
The Twelfth International Conference on Learning Representations (2024)
Chen, W. et al. AgentVerse: Facilitating multi-agent collaboration and exploring emergent behaviors · 2024
Cited alongside, same era.
Yeo, E., Tong, Y., Niu, M., Neubig, G. & Yue, X · 2025
Later among the works it cites.
Understanding reasoning in thinking language models via steering vectors (2025)
Venhoff, C., Arcuschin, I., Torr, P., Conmy, A. & Nanda, N · 2025
Later among the works it cites.
Galichin, A. et al · 2025
Later among the works it cites.
Reasoning-finetuning repurposes latent representations in base models (2025)
Ward, J., Lin, C., Venhoff, C. & Nanda, N · 2025
Later among the works it cites.
Base models know how to reason, thinking models learn when (2025)
Venhoff, C., Arcuschin, I., Torr, P., Conmy, A. & Nanda, N · 2025
Later among the works it cites.
Debate only when necessary: Adaptive multiagent collaboration for efficient LLM reasoning (2025)
Eo, S., Moon, H., Zi, E. H., Park, C. & Lim, H · 2025
Later among the works it cites.
Proceedings of the 31st International Conference on Computational Linguistics , 4689–4703 (Association for Computational Linguistics, Abu Dhabi, UAE, 2025)
Hu, Z., Chan, H. P., Li, J. & Yin, Y. Debate-to-write: A persona-driven multi-agent framework for diverse argument generation · 2025
Later among the works it cites.
Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing (SAC ’25) , 1009–1011 (ACM, 2025)
Sumita, Y., Takeuchi, K. & Kashima, H. Cognitive biases in large language models: A survey and mitigation experiments · 2025
Later among the works it cites.
Talk isn’t always cheap: Understanding failure modes in multi-agent debate (2025)
Wynn, A., Satija, H. & Hadfield, G · 2025
Later among the works it cites.
Findings of the Association for Computational Linguistics: EMNLP 2025 (Association for Computational Linguistics, 2025)
Feng, Y. et al. Unraveling misinformation propagation in LLM reasoning · 2025
Later among the works it cites.
Towards monosemanticity: Decomposing language models with dictionary learning
Bricken, T. et al · 2025
Later among the works it cites.
Proceedings of the 42nd International Conference on Machine Learning (2025)
Paulo, G., Mallen, A., Juang, C. & Belrose, N. Automatically interpreting millions of features in large language models · 2025
Later among the works it cites.
Persona vectors: Monitoring and controlling character traits in language models (2025)
Chen, R., Arditi, A., Sleight, H., Evans, O. & Lindsey, J · 2025
Later among the works it cites.
Twentieth European Conference on Computer Systems (EuroSys ’25) (2025)
Sheng, G. et al. HybridFlow: A flexible and efficient RLHF framework · 2025
Later among the works it cites.
Collaborating with AI agents: Field experiments on teamwork, productivity, and performance (2025)
Ju, H. & Aral, S · 2025
Later among the works it cites.
Yang, J. et al · 2025
Later among the works it cites.
EmbeddingGemma: Powerful and lightweight text representations (2025)
Vera, H. S. et al · 2025
Later among the works it cites.
Towards monosemanticity: Decomposing language models with dictionary learning
Bricken, T. et al · 2026
Closest in time.
Scaling monosemanticity: Extracting interpretable features from claude 3 sonnet
Templeton, A. et al · 2026
Closest in time.
Language models can explain neurons in language models
Bills, S. et al · 2026
Closest in time.