# Social Reasoning in Machines: Investigating Collective Truth-Seeking Dynamics in Large Language Model Debate

arXiv: https://arxiv.org/abs/2605.30391 · HTML: https://mlsanity.com/paper/2605.30391/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 16 of its 51 references that are in the map.
- First posted on arXiv 28 May 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, 16 of 16)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [LiveBench: A Challenging, Contamination-Limited LLM Benchmark](https://mlsanity.com/paper/2406.19314/) (2024)
- [Why Language Models Hallucinate](https://mlsanity.com/paper/2509.04664/) (2025)
- [Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs](https://mlsanity.com/paper/2311.17371/) (2023)
- [ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities](https://mlsanity.com/paper/2409.19839/) (2024)
- [Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate](https://mlsanity.com/paper/2509.23055/) (2025)
- [Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debate](https://mlsanity.com/paper/2407.20505/) (2024)
- [Latent Debate: A Surrogate Framework for Interpreting LLM Thinking](https://mlsanity.com/paper/2512.01909/) (2025)
- [A Debate-Driven Experiment on LLM Hallucinations and Accuracy](https://mlsanity.com/paper/2410.19485/) (2024)

## Abstract (arXiv)

Human reasoning has long been theorised to operate socially, not through isolated individual cognition, but through collective adversarial discourse, a framework known as the Argumentative Theory of Reasoning (ATR). Rather than relying on individual "intellectualist reasoners" as the primary vehicle for truth-seeking, ATR reconceptualises truth as an emergent property of social epistemology: the product of imperfect individual reasoning refined under the adversarial pressure of debate. This distributed method of collective intelligence has guided humanity to ever-greater epistemic heights and underpins the foundational principles of all democratic systems. This thesis breaks new ground by, for the first time, simulating ATR through the multi-agent debate (MAD) of large language models (LLMs). With rigorous empirical analysis, we demonstrate that, when correctly engineering an epistemically diverse set of models, LLM-MAD can significantly improve truth-seeking performance on questionnaire-based tasks, even when individual debate participants exhibit limited standalone performance. Furthermore, we present strong empirical evidence that this performance gain is mechanistically grounded in the central principles of ATR, suggesting that collective reasoning may be universally favourable over individualist reasoning, rather than a quirk in biology or evolution. Finally, drawing on our analysis of debate dynamics, we propose a novel benchmarking methodology that leverages LLM-MAD to measure intrinsic model properties (such as hallucination propensity) in order to compare models in ways that current static benchmarking approaches cannot support.