# Reasoning Models Generate Societies of Thought

arXiv: https://arxiv.org/abs/2601.10825 · HTML: https://mlsanity.com/paper/2601.10825/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 18 of its 74 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 18 of 18)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Demystifying Long Chain-of-Thought Reasoning in LLMs](https://mlsanity.com/paper/2502.03373/) (2025)
- [EmbeddingGemma: Powerful and Lightweight Text Representations](https://mlsanity.com/paper/2509.20354/) (2025)
- [SlimPajama-DC: Understanding Data Combinations for LLM Training](https://mlsanity.com/paper/2309.10818/) (2023)
- [Understanding Reasoning in Thinking Language Models via Steering Vectors](https://mlsanity.com/paper/2506.18167/) (2025)
- [Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate](https://mlsanity.com/paper/2509.05396/) (2025)
- [I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders](https://mlsanity.com/paper/2503.18878/) (2025)
- [Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning](https://mlsanity.com/paper/2504.05047/) (2025)
- [Base Models Know How to Reason, Thinking Models Learn When](https://mlsanity.com/paper/2510.07364/) (2025)
- [Reasoning-Finetuning Repurposes Latent Representations in Base Models](https://mlsanity.com/paper/2507.12638/) (2025)
- [Collaborating with AI Agents: Field Experiments on Teamwork, Productivity, and Performance](https://mlsanity.com/paper/2503.18238/) (2025)
- [Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2505.22467/) (2025)

## Built on by (most cited first, 12 of 12)

- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [ReasonOps: Operator Segmentation for LLM Reasoning Traces](https://mlsanity.com/paper/2605.29192/) (2026)
- [BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning](https://mlsanity.com/paper/2603.04124/) (2026)
- [Contemporary AI lacks the imagination to diverge or negate in science](https://mlsanity.com/paper/2606.08251/) (2026)
- [Scaling Multiagent Systems with Process Rewards](https://mlsanity.com/paper/2601.23228/) (2026)
- [Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation](https://mlsanity.com/paper/2605.15343/) (2026)
- [Directional Reasoning Trajectory Change (DRTC): Identifying Critical Trace Segments in Reasoning Models](https://mlsanity.com/paper/2602.15332/) (2026)
- [Metacognition in LLMs: Foundations, Progress, and Opportunities](https://mlsanity.com/paper/2607.11881/) (2026)
- [Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling](https://mlsanity.com/paper/2602.16485/) (2026)
- [Multi-agent AI systems outperform human teams in creativity](https://mlsanity.com/paper/2605.17885/) (2026)
- [Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems](https://mlsanity.com/paper/2606.05985/) (2026)
- [Mo' Models, Mo' Problems: How to best select model pools when designing Multi-Agent Systems](https://mlsanity.com/paper/2609.17306/) (2026)

## Abstract (arXiv)

Large language models have achieved remarkable capabilities across domains, yet mechanisms underlying sophisticated reasoning remain elusive. Recent reasoning models outperform comparable instruction-tuned models on complex cognitive tasks, attributed to extended computation through longer chains of thought. Here we show that enhanced reasoning emerges not from extended computation alone, but from simulating multi-agent-like interactions -- a society of thought -- which enables diversification and debate among internal cognitive perspectives characterized by distinct personality traits and domain expertise. Through quantitative analysis and mechanistic interpretability methods applied to reasoning traces, we find that reasoning models like DeepSeek-R1 and QwQ-32B exhibit much greater perspective diversity than instruction-tuned models, activating broader conflict between heterogeneous personality- and expertise-related features during reasoning. This multi-agent structure manifests in conversational behaviors, including question-answering, perspective shifts, and the reconciliation of conflicting views, and in socio-emotional roles that characterize sharp back-and-forth conversations, together accounting for the accuracy advantage in reasoning tasks. Controlled reinforcement learning experiments reveal that base models increase conversational behaviors when rewarded solely for reasoning accuracy, and fine-tuning models with conversational scaffolding accelerates reasoning improvement over base models. These findings indicate that the social organization of thought enables effective exploration of solution spaces. We suggest that reasoning models establish a computational parallel to collective intelligence in human groups, where diversity enables superior problem-solving when systematically structured, which suggests new opportunities for agent organization to harness the wisdom of crowds.