# A Roadmap towards Machine Intelligence

arXiv: https://arxiv.org/abs/1511.08130 · HTML: https://mlsanity.com/paper/1511.08130/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2015.

## Built on by (most cited first, 15 of 15)

- [Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models](https://mlsanity.com/paper/2409.20222/) (2024)
- [A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices](https://mlsanity.com/paper/2406.08787/) (2024)
- [Towards Socially Intelligent Agents with Mental State Transition and Human Utility](https://mlsanity.com/paper/2103.07011/) (2021)
- [Towards More Human-like AI Communication: A Review of Emergent Communication Research](https://mlsanity.com/paper/2308.02541/) (2023)
- [Deep Network Approximation in Terms of Intrinsic Parameters](https://mlsanity.com/paper/2111.07964/) (2021)
- [Benchmarking Compositionality with Formal Languages](https://mlsanity.com/paper/2208.08195/) (2022)
- [Shaping Shared Languages: Human and Large Language Models' Inductive Biases in Emergent Communication](https://mlsanity.com/paper/2503.04395/) (2025)
- [NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communication](https://mlsanity.com/paper/2407.13999/) (2024)
- [Construction Grammar and Artificial Intelligence](https://mlsanity.com/paper/2309.00135/) (2023)
- [PatchGame: Learning to Signal Mid-level Patches in Referential Games](https://mlsanity.com/paper/2111.01785/) (2021)
- [Preventing Rogue Agents Improves Multi-Agent Collaboration](https://mlsanity.com/paper/2502.05986/) (2025)
- [Situated Language Learning via Interactive Narratives](https://mlsanity.com/paper/2103.09977/) (2021)
- [Towards Learning Abstractions via Reinforcement Learning](https://mlsanity.com/paper/2212.13980/) (2022)
- [Towards Learning Through Open-Domain Dialog](https://mlsanity.com/paper/2202.03040/) (2022)
- [Towards a cognitive architecture to enable natural language interaction in co-constructive task learning](https://mlsanity.com/paper/2503.23760/) (2025)

## Abstract (arXiv)

The development of intelligent machines is one of the biggest unsolved challenges in computer science. In this paper, we propose some fundamental properties these machines should have, focusing in particular on communication and learning. We discuss a simple environment that could be used to incrementally teach a machine the basics of natural-language-based communication, as a prerequisite to more complex interaction with human users. We also present some conjectures on the sort of algorithms the machine should support in order to profitably learn from the environment.