# Beyond Fixed Representations: The Vocabulary and Verifier Gaps in Open-Ended AI

arXiv: https://arxiv.org/abs/2607.09560 · HTML: https://mlsanity.com/paper/2607.09560/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 59 references that are in the map.
- First posted on arXiv 10 Jul 2026.

## Builds on (most cited first, 19 of 19)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions](https://mlsanity.com/paper/1901.01753/) (2019)
- [Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions](https://mlsanity.com/paper/2003.08536/) (2020)
- [Abstraction and Analogy-Making in Artificial Intelligence](https://mlsanity.com/paper/2102.10717/) (2021)
- [AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence](https://mlsanity.com/paper/1905.10985/) (2019)
- [Open-Endedness is Essential for Artificial Superhuman Intelligence](https://mlsanity.com/paper/2406.04268/) (2024)
- [Top-Down Synthesis for Library Learning](https://mlsanity.com/paper/2211.16605/) (2022)
- [Huxley-G"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine](https://mlsanity.com/paper/2510.21614/) (2025)
- [The Red Queen G"odel Machine: Co-Evolving Agents and Their Evaluators](https://mlsanity.com/paper/2606.26294/) (2026)
- [AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentation](https://mlsanity.com/paper/2509.25651/) (2025)
- [Measuring the Gap Between Human and LLM Research Ideas](https://mlsanity.com/paper/2607.01233/) (2026)
- [Measuring Combinatorial Creativity in Large Language Models and Humans](https://mlsanity.com/paper/2509.21043/) (2025)
- [The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions](https://mlsanity.com/paper/2603.01092/) (2026)
- [Contemporary AI lacks the imagination to diverge or negate in science](https://mlsanity.com/paper/2606.08251/) (2026)
- [A Compositional Framework for Open-ended Intelligence](https://mlsanity.com/paper/2606.15386/) (2026)

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

- [Efficiency Matters in Autonomous Research](https://mlsanity.com/paper/2607.24647/) (2026)

## Abstract (arXiv)

Modern AI systems are increasingly being evaluated for their ability to reason, code, prove theorems, use tools, and long-horizon research tasks. These are powerful capabilities, but they share a structural limitation: the representational frame within which the model operates, including its conceptual vocabulary, the space of admissible solutions it can search, and the criteria by which success is evaluated, is typically fixed and supplied in advance. This paper argues that building stronger intelligent systems capable of open-ended innovation requires additional classes of operations: the creation, stabilization, and reuse of new representational primitives, which alter the space being searched rather than simply searching within it. We characterize the distance between current AI systems and genuinely open-ended intelligence through two gaps. The first is the vocabulary gap, the difficulty of inventing and stabilizing new representational primitives rather than merely recombining existing ones. The second is the verifier gap, the difficulty of judging the value of a new primitive when its full payoff may be visible only after future reuse. We interpret both gaps through a unified framework of intelligence as cognitive discrepancy reduction. By viewing intelligent behaviors as a sequence of cognitive transformations, we distinguish intra-space transformations which operate within a fixed representational frame, from generative transformations which may modify the frame itself. On this basis, we propose a ladder of innovation autonomy and outline several directions for advancing open-ended AI, including objectives that reward useful representational change, persistent memory architectures for invented primitives, and adaptive verification mechanisms capable of evolving alongside the representations they evaluate.