# Cheap Talking Algorithms

arXiv: https://arxiv.org/abs/2310.07867 · HTML: https://mlsanity.com/paper/2310.07867/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 41 references that are in the map.
- First posted on arXiv 11 Oct 2023.

## Builds on (most cited first, 6 of 6)

- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols](https://mlsanity.com/paper/1705.11192/) (2017)
- [Emergent Communication through Negotiation](https://mlsanity.com/paper/1804.03980/) (2018)
- [Artificial Intelligence and Auction Design](https://mlsanity.com/paper/2202.05947/) (2022)
- [Emergent Communication under Competition](https://mlsanity.com/paper/2101.10276/) (2021)

## Built on by (most cited first, 1 of 1)

- [Truthful AI Advisors: A Pre-Specified Benchmark for Large Language Model Honesty Under Preference Misalignment](https://mlsanity.com/paper/2606.01456/) (2026)

## Abstract (arXiv)

We simulate behaviour of two independent reinforcement learning algorithms playing the Crawford and Sobel (1982) game of strategic information transmission. We adopt memoryless algorithms to capture learning in a static game where a large population interacts anonymously. We show that sender and receiver converge to Nash equilibrium play. The level of informativeness of the sender's cheap talk decreases as the bias increases and, at intermediate level of the bias, it matches the level predicted by the Pareto optimal equilibrium or by the second best one. Conclusions are robust to alternative specifications of the learning hyperparameters and of the game.